dynarmic/externals/xbyak/sample/test_util.cpp

167 lines
4.7 KiB
C++
Raw Normal View History

#include <stdio.h>
#include "xbyak/xbyak_util.h"
#define NUM_OF_ARRAY(x) (sizeof(x) / sizeof(x[0]))
struct PopCountTest : public Xbyak::CodeGenerator {
PopCountTest(int n)
Squashed 'externals/xbyak/' changes from 0140eeff1..590c10e37 590c10e37 fix typo 396715a89 use github action 69a25fd92 change build status to travis-ci.com a6a9dac91 meanings of the name 8d1e41b65 test_util.cpp supports OpenBSD 77ffe7173 Merge pull request #115 from Ryan-rsm-McKenzie/master a1da3403a fix build interface include directory e0136d4ef fix add_library call with INTERFACE 3071eee0c support slightly more modern cmake e626d6209 v5.991 a49c4bc11 disable XBYAK_CONSTEXPR for g++-5 -std=c++-14 70777a699 Merge branch 'atafra-old_mac_fix' into dev 6b81678d0 fixed compile error on some older macOS versions 2c3b43f15 refactor util 91784e2b8 test_util checks AMX and AVX_VNNI 70b70c557 update to v5.99 284cc5bed refactor 6b3eb9c1e default encoding is always evex f85b1100b refactor vnni 276d09bae Merge branch 'akharito-akharito/adl_support' into dev 50df86ce3 v5.98 97ce92d58 Merge branch 'akharito/adl_support' of https://github.com/akharito/xbyak into akharito-akharito/adl_support 1f119a04a support [scale * reg] 9ee1bef9a cpuid - check that GRT CPUID leaf 7 subleaf 0 should return EAX=1 be93adb2c add AVX VNNI instruction support 0c277240a add ADL CPUID a9a5cc2e2 Add option to choose VEX or EVEX encoding 29bfd25ba fix indent a0c49fa2e Merge branch 'atafra-mac_avx512_fix' into dev ea388b3c6 fixed incorrect detection of AVX-512 on macOS ed1b8186f Merge branch 'FEX-Emu-extended_features' into dev 3dacddfec Merge branch 'extended_features' of https://github.com/FEX-Emu/xbyak into FEX-Emu-extended_features 898f78ca3 Merge branch 'kariya-mitsuru-use-sh' 0b7f1411c Merge branch 'use-sh' of https://github.com/kariya-mitsuru/xbyak into kariya-mitsuru-use-sh 99e2b13b2 Fixes extended feature support checking b0a43c7e5 Use sh instead of tcsh for test scripts 87e8f41ae remove warning of _MSC_VER git-subtree-dir: externals/xbyak git-subtree-split: 590c10e3746978dbfcf102d6da933ac2659e4544
2021-03-27 21:08:22 +00:00
: Xbyak::CodeGenerator(4096, Xbyak::DontSetProtectRWE)
{
mov(eax, n);
popcnt(eax, eax);
ret();
}
};
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
void putCPUinfo(bool onlyCpuidFeature)
{
using namespace Xbyak::util;
Cpu cpu;
printf("vendor %s\n", cpu.has(Cpu::tINTEL) ? "intel" : "amd");
static const struct {
Cpu::Type type;
const char *str;
} tbl[] = {
{ Cpu::tMMX, "mmx" },
{ Cpu::tMMX2, "mmx2" },
{ Cpu::tCMOV, "cmov" },
{ Cpu::tSSE, "sse" },
{ Cpu::tSSE2, "sse2" },
{ Cpu::tSSE3, "sse3" },
{ Cpu::tSSSE3, "ssse3" },
{ Cpu::tSSE41, "sse41" },
{ Cpu::tSSE42, "sse42" },
Squashed 'externals/xbyak/' changes from a1ac3750f..2ce465bbc 2ce465bbc Merge branch 'dev' 0b3f360eb v7.05 66f22b7a4 update doc 13ee4e19f use opSetCC for setCC 383866b42 use opMR with APX d6e6e6f85 tweak a7b02ac80 RAO_INT supports APX 26840492c use Address.immSize e2b40a33e refactor Address class e1b6896c2 Merge branch 'dev' c0888cc45 v7.04 7d9c82835 refactor rex b3e27734b apx supports 0x0f opecode with rex2 2e7b62d78 bswap supports apx 2e93baa6a Merge branch 'dev' e1864642c unify getMap and getMMM 0750873b7 T_MAP3 is not necessary ee4984222 T_MAP1 is not necessary 5c95842be tweak 8c44467af add no_flags sample 523cf1ed0 fix comment of sample/ccmp.cpp 5438fc69d Merge branch 'dev' ee26c094e v7.03 691ce361a [doc] update dfv 8d0e78146 set 0 for the default value of dfv 2255aea0d [doc] add ccmpSCC and ctestSCC b5e115284 add sample/ccmp.cpp bacd8d34b add sample/zero_upper.cpp f17cb9d6b Merge branch 'dev' c9ce3f8f6 v7.02 3427be298 unify opAESKL and opSHA bfd14244a update doc e690a2a47 sha* supports apx c9765588f Merge branch 'dev' 903f7c02e v7.01 54a1f07f9 update cpuid by sde 223ddfaf8 add detection of sse4a/clwb ba943b5b6 reorder cpu detection 30c362df5 Merge branch 'Sonicadvance1-missing_checks' into dev 02bc84ad8 renumber of tSSE4a, tCLWB 84fe3ab9d update doc 90fc0151c add encodekey{128,256} 440972b88 add detection of KEYLOCKER, KEYLOCKER_WIDE 68a30b91f add detection of AESKLE, WIDE_KL e2d36c662 fix detection of AVX10 48551f5cc add aesenc{128,256}kl, aesencwide{128,256}kl d9c7c992f add aesdecwide{128,256}kl cd5231de0 add aesdec256kl fcb3d0dbb add aesdec128kl 85709ace7 mvoe opKmov in private 406199e7a Support cpuid CLWB 1214aad95 Adds back missing SSE4a check 5315658ad add detection of avx10/apx_f 835f6d2e6 Merge pull request #180 from Tachi107/fix-32bit-tests 650b241e3 test: only run apx test when BIT=64 016ce86b6 [doc] add a blank line df0ebc740 v7.00 1ec2adbbb Merge branch 'apx' da1818592 update doc bec145ba9 amx supports apx 944438195 add tests of kmov* bd85d108c kmov* supports apx 93bd6a0b7 rename T_VEX to T_APX b063d276f add misc tests 6d21c7389 add evex tests 05a66d2c0 support V4 in evex 33017d4fb support V4 in evex e228e737d prepare evex extension of evex 45eca7987 update doc 98ce73bb2 add cfcmov tests e2d9685af add cfcmov a4ec97ca9 add tests of ctestscc 45711c502 add ctestscc a1f6c14cc add alias of dfv facb052a1 avoid r15 on 32-bit mode c1c15848c remove warnings be319626b add ccmpscc with imm c4d05037e add ccmpscc 17f7d279c testing ccmpb ff01b1e20 setcc supports apx 25ceea2ef add 3-op cmovcc 2f8cfb9a8 CMPccXADD supports APX a9310deac add tests of push/pop ec2881bfd push/pop support rex2 114152fed add push2/pop2 1aefdb649 support jmpabs 77eca6d0d add tests of 3-op shift 5e54ffdfa add 3-op shift 426814c50 check v instead of r 3f3d6095c disable rol/ror to support NF ee572b7eb add tests of ror/rol 186d63ad9 add tests of shr/sar 26be71a12 2-op shl supports apx 83f5bd25e remove some warnings e43d99762 add crc32 tests 92153b6f8 crc32 supports apx d7ca6a2dd split T_F2 from T_66|T_F3 fb1fc738f tweak 389d73347 movbe supports apx and append test 3636cde22 tests of 1-byte opcode with rex2 1dd020126 check whether or not it is a 1-byte opcode 083822b52 movdiri supports apx 6703d4344 movdir64b supports apx ed5dc3516 add tests of shld/shrd b01c0ed40 shld/shrd support apx c51c4a6f7 add tests of lzcnt and tzcnt 2cc22ea1b lzcnt and tzcnt support apx baddec288 tweak 1d3a19a50 update doc of apx 273d8d5b6 add 3-op imul with T_zu 50875294c add tests of 2-op imul d20142d01 add T_zu eb9de1392 2-op imul supports apx dba2c174f add 2op neg/not_ 95ad5927f add tests of imul/mul/neg/not_ with 1-op 790afb745 add tests o idiv 045ef31a3 add tests of div 1d7e2a6bb div supports apx e5fe58231 remove warning on 32-bit 66b3a3042 check all regs of NF c7dba88df add dec test f55f596ad add inc test 6f6423899 2-op inc/dec 95c0c4e6f tweak inc/dec f5fda7ace change detection of pp with type a18e5aeb5 rorx supports apx 5bb8461b4 blsmsk, blsr support apx a493dc7b4 blsi supports apx 7c1accedc sarx/shlx/shrx support apx and add tests 125d8e740 test bzhi with apx 78be5afd1 add tests of bextr with apx e9603b79d bextr supports apx 3a85aadc6 pdep, pext support apx 16f1a5d8a mulx supports apx 82529af93 andn supports APX 637ad7a4a add test of NF e23f5ad75 fix type for adc 1bcc83303 3-op add supports T_nf 5d46b950b the type of all type is uint64_t 0a8ea9edf fix type b1f0fef4d add test of 3op apx 9b21727ba remove space 6fa1b4a90 reorder of opRO 2d1f229a0 simplify condR b220be972 simplify opRO 24b71a1ce use Reg instead of Operand if possible de1353448 rename opGen with opSSE 4cd8e8eac refactor opGpr as opRRO 01d756917 rename 5037120f7 replace old rex with rexA 45fe94fdd rename opLoadSeg2 with opLoadSeg 253f800bc tweak 4f3939d92 rename opModM2 with opModM fa731a27c rename opModR2 with opModR e5db7d0e4 rename opModRM2 to opModRM dc20fd09b use opModRM2 d4da1561b rename opR_ModM2 with opR_ModM ef3665274 use opR_ModM2 e5b20e5a5 use opModM2 104941db2 use opModM2 6ae769f21 rename opROO2 with opROO 1521cb7ce rename opGen2 to opGen f9c6cb5dc all opGen are replaced with opGen2 249d6978a use opGen2 81ae48922 use opGen2 b9e4bb2fc always put prefix as byte code 3374a158f use opGen2 719f81f45 use opGen2 8d037ebd6 use opGen2 6f8bc28e2 use opGen2 303876cac use opGen2 f0b49752a rewrite opMovXMM 5d4c48ffd rewrite opMMX 189c3488b use opMMX2 1361d0946 use opMMX2 32cafcc61 tweak cf1cfd6c4 add temporary converting code 433bf29e3 replacing opModR with opModR2 ba1d07ed1 senduipi uses opModR2 646da9750 use opModR2 for rdrand, rdseed, movq ccad6cecd use opModR2 for movdq2q, movq2dq 3c21754b9 use opModR2 for movd, movmskps 4718643ef use opModR2 for bswap, maskmovq, pmovmskb e1a148707 try to use opModR2 220a5def7 split avx_type_def.h in gen/ 87b8c8ed2 adox passes the test bd8477292 fix detection of adox without apx 6b19515eb add adcx, adox with APX 77d6acea6 increase the room of type 710e39bfe add test of r, r/m ea9cd9ade tweak 057f09c5b rename T_NF to T_nf 57a0c1935 support NF=1 8f49739da remove cmp of 3-op e3310344c [doc] about APX cdc2533c1 add test of adc/3op 9c6b81c4d return value on nothrow mode 8d524b4a4 add op(r, r/m, imm) and op(r, r/m, r/m) 4c62d1fdc test adc2(r, op, mem) and adc2(r, mem, op) 6f593a1cb test of adc2 (3op APX) 61addb9d9 simplify opMIB 575c447f1 remove rex2p a95bd9cc5 add test of adc/add/and_/cmp/or_/sbb/sub/xor_ f7d3c17e8 tweak d7a7ea912 refactoring rex acd797139 use opModM instead of opMIB ad3334ba6 add modRM with rex2 059d115b5 add test of apx.cpp 873c93a51 add test of regs of apx e25b1cd62 [not tested] add(r1, r2) with rex2 eb118504d remove warning of VC 6c580b1f7 fix cvt test for extended r16-r31 981fa6f05 add r16 - r31 244623812 Merge branch 'dev' aafe3cb62 build(cmake): bump minimum required to version 3.5 76d7477d7 Merge branch 'dev' 151c8ab04 v6.73 dd66cfb76 add tests of avx-vnni-int{8,16} 4a6132d66 update cpuid list bea25541a add detection of AVX_VNNI_INT16 d9e76b1c6 add tests of SM4 e1c4c360b add SM4 d79717dbe add tests of SM3 48f8dbeb6 add SM3 5473d3933 vsha512* check regs 9b3687a68 add detection of SHA512, SM3, SM4 ecdd01ee5 mov crypt test in 64-bit mode c4550b6a9 sde 9.24.0 5762819de add vsha512{msg1, msg2, rnds2} 3255d606a Merge branch 'dev' 322665e72 v6.72 ad178a219 add xabort/xbegin/xend 0924ff4aa Merge branch 'dev' 8980934c1 v6.71 76292b310 add SystemInfo class for win 3e42709ab ignore space and cr 66b2768a6 disable wrong detection of gcc 1855985e1 remove / for mingw64 5bdccc0b8 64bit only for mingw64 33882d0a0 use sysconf(_SC_PAGESIZE) instead of const value 4096 on linux 33075c2bd add link to other projects 60e71402e reorder 79854aa08 add new cpus 5921e270c update cpuid ce083a0dc Merge branch 'dev' b538485f3 v6.70 461dd34ee udpate doc 2149c79e3 add test of alias of vpclmulqdq 2c59c5c91 add alias of vpclmulqdq 729ae4aa3 fix alias of pclmulqdq 3c248d68a define XBYAK_CONSTEXPR if XBYAK_ONLY_CLASS_CPU is defined c0a932d7b Merge remote-tracking branch 'origin/dev' ef502b5b4 update doc ba3db4730 update version c0d7a704f v6.69.2 c535f4737 update cpuid test list 683249232 change the order of args of diff e81b95583 Merge branch 'Wunkolo-constexpr-typet' into dev ab3f40587 Allow constexpr TypeT `operator|` ad5276fa4 Merge pull request #172 from orz--/patch-1 b4d54f6e1 Update changelog.md 58642e0cd Merge branch 'dev' 3b13d068b v6.69.1 d700f6c35 add detection of xsave 740dff2e8 Merge branch 'dev' dc048a04c v6.69 ad0dfffd2 add senduipi/stui/testui/uiret e78f1121b add clui 23b40331a add detection of uintr 98a0f1924 remove warning of sign/unsigned 0afd71a27 add detection of SERIALIZE 363bbaa57 sample shows cpu cache info for AMD edce72709 Cpu supports AMD git-subtree-dir: externals/xbyak git-subtree-split: 2ce465bbca46e92dde9c44bbe7940fd7f70e3b97
2024-01-30 00:36:49 +00:00
{ Cpu::tSSE4a, "sse4a" },
{ Cpu::tPOPCNT, "popcnt" },
{ Cpu::t3DN, "3dn" },
{ Cpu::tE3DN, "e3dn" },
{ Cpu::tAESNI, "aesni" },
{ Cpu::tRDTSCP, "rdtscp" },
Squashed 'externals/xbyak/' changes from a1ac3750f..2ce465bbc 2ce465bbc Merge branch 'dev' 0b3f360eb v7.05 66f22b7a4 update doc 13ee4e19f use opSetCC for setCC 383866b42 use opMR with APX d6e6e6f85 tweak a7b02ac80 RAO_INT supports APX 26840492c use Address.immSize e2b40a33e refactor Address class e1b6896c2 Merge branch 'dev' c0888cc45 v7.04 7d9c82835 refactor rex b3e27734b apx supports 0x0f opecode with rex2 2e7b62d78 bswap supports apx 2e93baa6a Merge branch 'dev' e1864642c unify getMap and getMMM 0750873b7 T_MAP3 is not necessary ee4984222 T_MAP1 is not necessary 5c95842be tweak 8c44467af add no_flags sample 523cf1ed0 fix comment of sample/ccmp.cpp 5438fc69d Merge branch 'dev' ee26c094e v7.03 691ce361a [doc] update dfv 8d0e78146 set 0 for the default value of dfv 2255aea0d [doc] add ccmpSCC and ctestSCC b5e115284 add sample/ccmp.cpp bacd8d34b add sample/zero_upper.cpp f17cb9d6b Merge branch 'dev' c9ce3f8f6 v7.02 3427be298 unify opAESKL and opSHA bfd14244a update doc e690a2a47 sha* supports apx c9765588f Merge branch 'dev' 903f7c02e v7.01 54a1f07f9 update cpuid by sde 223ddfaf8 add detection of sse4a/clwb ba943b5b6 reorder cpu detection 30c362df5 Merge branch 'Sonicadvance1-missing_checks' into dev 02bc84ad8 renumber of tSSE4a, tCLWB 84fe3ab9d update doc 90fc0151c add encodekey{128,256} 440972b88 add detection of KEYLOCKER, KEYLOCKER_WIDE 68a30b91f add detection of AESKLE, WIDE_KL e2d36c662 fix detection of AVX10 48551f5cc add aesenc{128,256}kl, aesencwide{128,256}kl d9c7c992f add aesdecwide{128,256}kl cd5231de0 add aesdec256kl fcb3d0dbb add aesdec128kl 85709ace7 mvoe opKmov in private 406199e7a Support cpuid CLWB 1214aad95 Adds back missing SSE4a check 5315658ad add detection of avx10/apx_f 835f6d2e6 Merge pull request #180 from Tachi107/fix-32bit-tests 650b241e3 test: only run apx test when BIT=64 016ce86b6 [doc] add a blank line df0ebc740 v7.00 1ec2adbbb Merge branch 'apx' da1818592 update doc bec145ba9 amx supports apx 944438195 add tests of kmov* bd85d108c kmov* supports apx 93bd6a0b7 rename T_VEX to T_APX b063d276f add misc tests 6d21c7389 add evex tests 05a66d2c0 support V4 in evex 33017d4fb support V4 in evex e228e737d prepare evex extension of evex 45eca7987 update doc 98ce73bb2 add cfcmov tests e2d9685af add cfcmov a4ec97ca9 add tests of ctestscc 45711c502 add ctestscc a1f6c14cc add alias of dfv facb052a1 avoid r15 on 32-bit mode c1c15848c remove warnings be319626b add ccmpscc with imm c4d05037e add ccmpscc 17f7d279c testing ccmpb ff01b1e20 setcc supports apx 25ceea2ef add 3-op cmovcc 2f8cfb9a8 CMPccXADD supports APX a9310deac add tests of push/pop ec2881bfd push/pop support rex2 114152fed add push2/pop2 1aefdb649 support jmpabs 77eca6d0d add tests of 3-op shift 5e54ffdfa add 3-op shift 426814c50 check v instead of r 3f3d6095c disable rol/ror to support NF ee572b7eb add tests of ror/rol 186d63ad9 add tests of shr/sar 26be71a12 2-op shl supports apx 83f5bd25e remove some warnings e43d99762 add crc32 tests 92153b6f8 crc32 supports apx d7ca6a2dd split T_F2 from T_66|T_F3 fb1fc738f tweak 389d73347 movbe supports apx and append test 3636cde22 tests of 1-byte opcode with rex2 1dd020126 check whether or not it is a 1-byte opcode 083822b52 movdiri supports apx 6703d4344 movdir64b supports apx ed5dc3516 add tests of shld/shrd b01c0ed40 shld/shrd support apx c51c4a6f7 add tests of lzcnt and tzcnt 2cc22ea1b lzcnt and tzcnt support apx baddec288 tweak 1d3a19a50 update doc of apx 273d8d5b6 add 3-op imul with T_zu 50875294c add tests of 2-op imul d20142d01 add T_zu eb9de1392 2-op imul supports apx dba2c174f add 2op neg/not_ 95ad5927f add tests of imul/mul/neg/not_ with 1-op 790afb745 add tests o idiv 045ef31a3 add tests of div 1d7e2a6bb div supports apx e5fe58231 remove warning on 32-bit 66b3a3042 check all regs of NF c7dba88df add dec test f55f596ad add inc test 6f6423899 2-op inc/dec 95c0c4e6f tweak inc/dec f5fda7ace change detection of pp with type a18e5aeb5 rorx supports apx 5bb8461b4 blsmsk, blsr support apx a493dc7b4 blsi supports apx 7c1accedc sarx/shlx/shrx support apx and add tests 125d8e740 test bzhi with apx 78be5afd1 add tests of bextr with apx e9603b79d bextr supports apx 3a85aadc6 pdep, pext support apx 16f1a5d8a mulx supports apx 82529af93 andn supports APX 637ad7a4a add test of NF e23f5ad75 fix type for adc 1bcc83303 3-op add supports T_nf 5d46b950b the type of all type is uint64_t 0a8ea9edf fix type b1f0fef4d add test of 3op apx 9b21727ba remove space 6fa1b4a90 reorder of opRO 2d1f229a0 simplify condR b220be972 simplify opRO 24b71a1ce use Reg instead of Operand if possible de1353448 rename opGen with opSSE 4cd8e8eac refactor opGpr as opRRO 01d756917 rename 5037120f7 replace old rex with rexA 45fe94fdd rename opLoadSeg2 with opLoadSeg 253f800bc tweak 4f3939d92 rename opModM2 with opModM fa731a27c rename opModR2 with opModR e5db7d0e4 rename opModRM2 to opModRM dc20fd09b use opModRM2 d4da1561b rename opR_ModM2 with opR_ModM ef3665274 use opR_ModM2 e5b20e5a5 use opModM2 104941db2 use opModM2 6ae769f21 rename opROO2 with opROO 1521cb7ce rename opGen2 to opGen f9c6cb5dc all opGen are replaced with opGen2 249d6978a use opGen2 81ae48922 use opGen2 b9e4bb2fc always put prefix as byte code 3374a158f use opGen2 719f81f45 use opGen2 8d037ebd6 use opGen2 6f8bc28e2 use opGen2 303876cac use opGen2 f0b49752a rewrite opMovXMM 5d4c48ffd rewrite opMMX 189c3488b use opMMX2 1361d0946 use opMMX2 32cafcc61 tweak cf1cfd6c4 add temporary converting code 433bf29e3 replacing opModR with opModR2 ba1d07ed1 senduipi uses opModR2 646da9750 use opModR2 for rdrand, rdseed, movq ccad6cecd use opModR2 for movdq2q, movq2dq 3c21754b9 use opModR2 for movd, movmskps 4718643ef use opModR2 for bswap, maskmovq, pmovmskb e1a148707 try to use opModR2 220a5def7 split avx_type_def.h in gen/ 87b8c8ed2 adox passes the test bd8477292 fix detection of adox without apx 6b19515eb add adcx, adox with APX 77d6acea6 increase the room of type 710e39bfe add test of r, r/m ea9cd9ade tweak 057f09c5b rename T_NF to T_nf 57a0c1935 support NF=1 8f49739da remove cmp of 3-op e3310344c [doc] about APX cdc2533c1 add test of adc/3op 9c6b81c4d return value on nothrow mode 8d524b4a4 add op(r, r/m, imm) and op(r, r/m, r/m) 4c62d1fdc test adc2(r, op, mem) and adc2(r, mem, op) 6f593a1cb test of adc2 (3op APX) 61addb9d9 simplify opMIB 575c447f1 remove rex2p a95bd9cc5 add test of adc/add/and_/cmp/or_/sbb/sub/xor_ f7d3c17e8 tweak d7a7ea912 refactoring rex acd797139 use opModM instead of opMIB ad3334ba6 add modRM with rex2 059d115b5 add test of apx.cpp 873c93a51 add test of regs of apx e25b1cd62 [not tested] add(r1, r2) with rex2 eb118504d remove warning of VC 6c580b1f7 fix cvt test for extended r16-r31 981fa6f05 add r16 - r31 244623812 Merge branch 'dev' aafe3cb62 build(cmake): bump minimum required to version 3.5 76d7477d7 Merge branch 'dev' 151c8ab04 v6.73 dd66cfb76 add tests of avx-vnni-int{8,16} 4a6132d66 update cpuid list bea25541a add detection of AVX_VNNI_INT16 d9e76b1c6 add tests of SM4 e1c4c360b add SM4 d79717dbe add tests of SM3 48f8dbeb6 add SM3 5473d3933 vsha512* check regs 9b3687a68 add detection of SHA512, SM3, SM4 ecdd01ee5 mov crypt test in 64-bit mode c4550b6a9 sde 9.24.0 5762819de add vsha512{msg1, msg2, rnds2} 3255d606a Merge branch 'dev' 322665e72 v6.72 ad178a219 add xabort/xbegin/xend 0924ff4aa Merge branch 'dev' 8980934c1 v6.71 76292b310 add SystemInfo class for win 3e42709ab ignore space and cr 66b2768a6 disable wrong detection of gcc 1855985e1 remove / for mingw64 5bdccc0b8 64bit only for mingw64 33882d0a0 use sysconf(_SC_PAGESIZE) instead of const value 4096 on linux 33075c2bd add link to other projects 60e71402e reorder 79854aa08 add new cpus 5921e270c update cpuid ce083a0dc Merge branch 'dev' b538485f3 v6.70 461dd34ee udpate doc 2149c79e3 add test of alias of vpclmulqdq 2c59c5c91 add alias of vpclmulqdq 729ae4aa3 fix alias of pclmulqdq 3c248d68a define XBYAK_CONSTEXPR if XBYAK_ONLY_CLASS_CPU is defined c0a932d7b Merge remote-tracking branch 'origin/dev' ef502b5b4 update doc ba3db4730 update version c0d7a704f v6.69.2 c535f4737 update cpuid test list 683249232 change the order of args of diff e81b95583 Merge branch 'Wunkolo-constexpr-typet' into dev ab3f40587 Allow constexpr TypeT `operator|` ad5276fa4 Merge pull request #172 from orz--/patch-1 b4d54f6e1 Update changelog.md 58642e0cd Merge branch 'dev' 3b13d068b v6.69.1 d700f6c35 add detection of xsave 740dff2e8 Merge branch 'dev' dc048a04c v6.69 ad0dfffd2 add senduipi/stui/testui/uiret e78f1121b add clui 23b40331a add detection of uintr 98a0f1924 remove warning of sign/unsigned 0afd71a27 add detection of SERIALIZE 363bbaa57 sample shows cpu cache info for AMD edce72709 Cpu supports AMD git-subtree-dir: externals/xbyak git-subtree-split: 2ce465bbca46e92dde9c44bbe7940fd7f70e3b97
2024-01-30 00:36:49 +00:00
{ Cpu::tXSAVE, "xsave(xgetvb)" },
{ Cpu::tOSXSAVE, "osxsave" },
{ Cpu::tPCLMULQDQ, "pclmulqdq" },
{ Cpu::tAVX, "avx" },
{ Cpu::tFMA, "fma" },
{ Cpu::tAVX2, "avx2" },
{ Cpu::tBMI1, "bmi1" },
{ Cpu::tBMI2, "bmi2" },
{ Cpu::tLZCNT, "lzcnt" },
{ Cpu::tPREFETCHW, "prefetchw" },
{ Cpu::tENHANCED_REP, "enh_rep" },
{ Cpu::tRDRAND, "rdrand" },
{ Cpu::tADX, "adx" },
{ Cpu::tRDSEED, "rdseed" },
{ Cpu::tSMAP, "smap" },
{ Cpu::tHLE, "hle" },
{ Cpu::tRTM, "rtm" },
{ Cpu::tMPX, "mpx" },
{ Cpu::tSHA, "sha" },
{ Cpu::tPREFETCHWT1, "prefetchwt1" },
{ Cpu::tF16C, "f16c" },
{ Cpu::tMOVBE, "movbe" },
{ Cpu::tAVX512F, "avx512f" },
{ Cpu::tAVX512DQ, "avx512dq" },
{ Cpu::tAVX512IFMA, "avx512_ifma" },
{ Cpu::tAVX512PF, "avx512pf" },
{ Cpu::tAVX512ER, "avx512er" },
{ Cpu::tAVX512CD, "avx512cd" },
{ Cpu::tAVX512BW, "avx512bw" },
{ Cpu::tAVX512VL, "avx512vl" },
{ Cpu::tAVX512VBMI, "avx512_vbmi" },
{ Cpu::tAVX512_4VNNIW, "avx512_4vnniw" },
{ Cpu::tAVX512_4FMAPS, "avx512_4fmaps" },
{ Cpu::tAVX512_VBMI2, "avx512_vbmi2" },
{ Cpu::tGFNI, "gfni" },
{ Cpu::tVAES, "vaes" },
{ Cpu::tVPCLMULQDQ, "vpclmulqdq" },
{ Cpu::tAVX512_VNNI, "avx512_vnni" },
{ Cpu::tAVX512_BITALG, "avx512_bitalg" },
{ Cpu::tAVX512_VPOPCNTDQ, "avx512_vpopcntdq" },
Squashed 'externals/xbyak/' changes from 73ac5866..0140eeff 0140eeff Merge branch 'dev' 1efe14b2 change the original behavior of SetError 83c89c7a rename and fix indent 8be7ca93 Merge branch 'sbogusev-master' into dev 070b4c09 make l_err() inline with block scope static TLS l_error 9a4e6579 v5.97 d0ced1bc XBYAK_ONLY_CLASS_CPU is for only util::Cpu bb967ae7 replace uint32 with uint32_t etc. c306b8e5 update to v5.95 605e4224 use noexcept if C++11 or later 7a17c2c8 remove warning 5dfa4462 use constexpr if c++14 or later 18c9caaa Merge branch 'densamoilov-fix-mov-interface' into dev 3966ba9d fix mov interface be492be1 change the behavior of push((byte|word), imm) to cast imm to int8_t/int16_t d9696b54 Merge pull request #102 from igorsafo/master ea73267f Cpu: make getNumCores constant ff0b10e9 Merge pull request #101 from densamoilov/use-thread_local-when-supported 0c4eafc3 use thread_local for XBYAK_TLS when supported c1aea35e CodeGenerator::reset() calls ClearError() b4df97b1 Merge branch 'cursey-no-winsock2-header' 6a47bb0e v5.94 9a1749e6 define WIN32_LEAN_AND_MEAN for including winsock2.h after xbyak.h 42dddb74 Remove #include <winsock2.h> 615b85fa update doc 9cd796a9 rename XBYAK_NOEXCEPTION to XBYAK_NO_EXCEPTION 7cdf227f use static to avoid multiple instance 38a28dec test_nm.bat supports noexcept 0fdffc6b XBYAK_NOEXCEPTION for -fno-exceptions eda6e2a3 v5.92 5c26c8bb mov(rax, imm64) on 32-bit env with XBYAK64 6208e3ae throw exception if not supported amx sibmem 2 c6737d14 mov amx insts from avx512 34ea5c16 throw exception if not supported amx sibmem 6f93fe35 fix test of sizeof(Operand) 5b89c3b2 remove T_TMM 5ce32858 gen_amx.cpp is merged into gen_avx512.cpp fe4f965f remove my alias for tmm registers 92f904d8 bit_ contains 8192 98b51da9 extend mnemonics with Intel(R) AMX ISA 8d1b4c9e add generation of Intel(R) AMX ISA mnemonics 8ded45d1 add support of Intel(R) AMX ISA b23c4b02 v5.912 ffe32a60 Merge branch 'rsdubtso-master' e7b7fd2f use MAP_JIT on macOS regardless of Xcode version 82b70e66 v5.911 ; XBYAK_USE_MMAP_ALLOCATOR is defined 2f6d9e34 fix test for mac a7d10a1e add link to GitHub Sponsor 96076265 accept k0 mask register (it means no mask) 7e3167e4 kmov{b,w,d,q} throws for unsupported reg f487d7b7 Merge pull request #91 from marcelotrevisani/patch-1 dc9e6a79 Possibility to specify a different PREFIX 5fc69fc8 remove warning of test e69e0b42 fix typo of type of Zmi 34f797e8 perf does not recognize too short function name 6cc0f4df Consider max defined as a macro on Windows 5722393d fix for zeroed-out 0xb leaf 6a4459a8 Merge branch 'tyfkda-feature/fix-segfault-in-calc' 47922ed9 Fix segmentation fault in calc sample 8f696e93 add test_avx512 to bat 00114d79 add .travis.yml a29fa27b refactor test 508b543c fix error of vfpclasspd 0d54f1b1 fix for windows 4da8fd4e add setDefaultJmpNEAR da7f7317 revert to the behavior before v5.84 if -fno-operator-names is defined 7dac9f61 update to v5.85 fe639332 enable MAP_JIT only if mojave or later 4443d791 specify MAP_JIT mmap flag on macOS 20ee4c2d update doc ca0e8395 [changed] XBYAK_NO_OP_NAMES is defined f32836da remove exit(1) a1e9adf2 v5.82 08b8b1ba Support AMD Zen New Instructions. 2501ba9a remove *.user and *.vcproj 5c2ea988 Merge branch 'jrmwng-feature/upgrade-to-vs2017/jrmwng' 35847f7a Merge branch 'feature/upgrade-to-vs2017/jrmwng' of https://github.com/jrmwng/xbyak into jrmwng-feature/upgrade-to-vs2017/jrmwng ef267775 address "warning LNK4075: ignoring '/EDITANDCONTINUE' due to '/SAFESEH' specification" 4a6c59bb address a conflict of sharing intermediate directory by different projects 9577cbf3 inherit "some output locations" from parent or project defaults 6c5f7186 upgrade projects from VS2018 to VS2017 4ca0434b v5.81 72b4e95d add lds/lss/les/lfs/lgs cc8f037c fix ; move ERR_INTERNAL to the end 9e9ec1c3 add repe, repne, repne, prez eea0edc3 add some fpu mnemonics 06235fa6 add loop/loope/loopne 7fc0c2bb add enter/leave 9fa2ef3c add in_, out_ df208648 add lods{b,w,d,q}, outs{b,w,d} 4672d2cb add int3, int_, into 431977cb add pushfq, popfq 81c4749f syscall, sysenter, sysexit, sysret 1f1b53c4 add clflushopt, fldenv, fnstw b765db33 Profiler uses append mode 44dc3546 add Profiler class 42949334 update version to v5.802 91cb919b Merge branch 'vpirogov-master' a6452f82 fixed avx512_bf16 detection f41da5aa tweak ; vcvtneps2bf16 calls opCvt2 b12460ba [sample] fix typo of quantize.cpp b22f5881 add set_opt.bat for test on Windows f402faad add vp2intersectd/vp2intersectq 4cfd5208 add avx512_bf16 4033564c fix vcmppd/vcmpps for ptr_b git-subtree-dir: externals/xbyak git-subtree-split: 0140eeff1fffcf5069dea3abb57095695320971c
2020-09-19 16:27:42 +01:00
{ Cpu::tAVX512_BF16, "avx512_bf16" },
{ Cpu::tAVX512_VP2INTERSECT, "avx512_vp2intersect" },
Squashed 'externals/xbyak/' changes from 0140eeff1..590c10e37 590c10e37 fix typo 396715a89 use github action 69a25fd92 change build status to travis-ci.com a6a9dac91 meanings of the name 8d1e41b65 test_util.cpp supports OpenBSD 77ffe7173 Merge pull request #115 from Ryan-rsm-McKenzie/master a1da3403a fix build interface include directory e0136d4ef fix add_library call with INTERFACE 3071eee0c support slightly more modern cmake e626d6209 v5.991 a49c4bc11 disable XBYAK_CONSTEXPR for g++-5 -std=c++-14 70777a699 Merge branch 'atafra-old_mac_fix' into dev 6b81678d0 fixed compile error on some older macOS versions 2c3b43f15 refactor util 91784e2b8 test_util checks AMX and AVX_VNNI 70b70c557 update to v5.99 284cc5bed refactor 6b3eb9c1e default encoding is always evex f85b1100b refactor vnni 276d09bae Merge branch 'akharito-akharito/adl_support' into dev 50df86ce3 v5.98 97ce92d58 Merge branch 'akharito/adl_support' of https://github.com/akharito/xbyak into akharito-akharito/adl_support 1f119a04a support [scale * reg] 9ee1bef9a cpuid - check that GRT CPUID leaf 7 subleaf 0 should return EAX=1 be93adb2c add AVX VNNI instruction support 0c277240a add ADL CPUID a9a5cc2e2 Add option to choose VEX or EVEX encoding 29bfd25ba fix indent a0c49fa2e Merge branch 'atafra-mac_avx512_fix' into dev ea388b3c6 fixed incorrect detection of AVX-512 on macOS ed1b8186f Merge branch 'FEX-Emu-extended_features' into dev 3dacddfec Merge branch 'extended_features' of https://github.com/FEX-Emu/xbyak into FEX-Emu-extended_features 898f78ca3 Merge branch 'kariya-mitsuru-use-sh' 0b7f1411c Merge branch 'use-sh' of https://github.com/kariya-mitsuru/xbyak into kariya-mitsuru-use-sh 99e2b13b2 Fixes extended feature support checking b0a43c7e5 Use sh instead of tcsh for test scripts 87e8f41ae remove warning of _MSC_VER git-subtree-dir: externals/xbyak git-subtree-split: 590c10e3746978dbfcf102d6da933ac2659e4544
2021-03-27 21:08:22 +00:00
{ Cpu::tAMX_TILE, "amx(tile)" },
{ Cpu::tAMX_INT8, "amx(int8)" },
{ Cpu::tAMX_BF16, "amx(bf16)" },
{ Cpu::tAVX_VNNI, "avx_vnni" },
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
{ Cpu::tAVX512_FP16, "avx512_fp16" },
{ Cpu::tWAITPKG, "waitpkg" },
{ Cpu::tCLFLUSHOPT, "clflushopt" },
{ Cpu::tCLDEMOTE, "cldemote" },
Squashed 'externals/xbyak/' changes from a1ac3750f..2ce465bbc 2ce465bbc Merge branch 'dev' 0b3f360eb v7.05 66f22b7a4 update doc 13ee4e19f use opSetCC for setCC 383866b42 use opMR with APX d6e6e6f85 tweak a7b02ac80 RAO_INT supports APX 26840492c use Address.immSize e2b40a33e refactor Address class e1b6896c2 Merge branch 'dev' c0888cc45 v7.04 7d9c82835 refactor rex b3e27734b apx supports 0x0f opecode with rex2 2e7b62d78 bswap supports apx 2e93baa6a Merge branch 'dev' e1864642c unify getMap and getMMM 0750873b7 T_MAP3 is not necessary ee4984222 T_MAP1 is not necessary 5c95842be tweak 8c44467af add no_flags sample 523cf1ed0 fix comment of sample/ccmp.cpp 5438fc69d Merge branch 'dev' ee26c094e v7.03 691ce361a [doc] update dfv 8d0e78146 set 0 for the default value of dfv 2255aea0d [doc] add ccmpSCC and ctestSCC b5e115284 add sample/ccmp.cpp bacd8d34b add sample/zero_upper.cpp f17cb9d6b Merge branch 'dev' c9ce3f8f6 v7.02 3427be298 unify opAESKL and opSHA bfd14244a update doc e690a2a47 sha* supports apx c9765588f Merge branch 'dev' 903f7c02e v7.01 54a1f07f9 update cpuid by sde 223ddfaf8 add detection of sse4a/clwb ba943b5b6 reorder cpu detection 30c362df5 Merge branch 'Sonicadvance1-missing_checks' into dev 02bc84ad8 renumber of tSSE4a, tCLWB 84fe3ab9d update doc 90fc0151c add encodekey{128,256} 440972b88 add detection of KEYLOCKER, KEYLOCKER_WIDE 68a30b91f add detection of AESKLE, WIDE_KL e2d36c662 fix detection of AVX10 48551f5cc add aesenc{128,256}kl, aesencwide{128,256}kl d9c7c992f add aesdecwide{128,256}kl cd5231de0 add aesdec256kl fcb3d0dbb add aesdec128kl 85709ace7 mvoe opKmov in private 406199e7a Support cpuid CLWB 1214aad95 Adds back missing SSE4a check 5315658ad add detection of avx10/apx_f 835f6d2e6 Merge pull request #180 from Tachi107/fix-32bit-tests 650b241e3 test: only run apx test when BIT=64 016ce86b6 [doc] add a blank line df0ebc740 v7.00 1ec2adbbb Merge branch 'apx' da1818592 update doc bec145ba9 amx supports apx 944438195 add tests of kmov* bd85d108c kmov* supports apx 93bd6a0b7 rename T_VEX to T_APX b063d276f add misc tests 6d21c7389 add evex tests 05a66d2c0 support V4 in evex 33017d4fb support V4 in evex e228e737d prepare evex extension of evex 45eca7987 update doc 98ce73bb2 add cfcmov tests e2d9685af add cfcmov a4ec97ca9 add tests of ctestscc 45711c502 add ctestscc a1f6c14cc add alias of dfv facb052a1 avoid r15 on 32-bit mode c1c15848c remove warnings be319626b add ccmpscc with imm c4d05037e add ccmpscc 17f7d279c testing ccmpb ff01b1e20 setcc supports apx 25ceea2ef add 3-op cmovcc 2f8cfb9a8 CMPccXADD supports APX a9310deac add tests of push/pop ec2881bfd push/pop support rex2 114152fed add push2/pop2 1aefdb649 support jmpabs 77eca6d0d add tests of 3-op shift 5e54ffdfa add 3-op shift 426814c50 check v instead of r 3f3d6095c disable rol/ror to support NF ee572b7eb add tests of ror/rol 186d63ad9 add tests of shr/sar 26be71a12 2-op shl supports apx 83f5bd25e remove some warnings e43d99762 add crc32 tests 92153b6f8 crc32 supports apx d7ca6a2dd split T_F2 from T_66|T_F3 fb1fc738f tweak 389d73347 movbe supports apx and append test 3636cde22 tests of 1-byte opcode with rex2 1dd020126 check whether or not it is a 1-byte opcode 083822b52 movdiri supports apx 6703d4344 movdir64b supports apx ed5dc3516 add tests of shld/shrd b01c0ed40 shld/shrd support apx c51c4a6f7 add tests of lzcnt and tzcnt 2cc22ea1b lzcnt and tzcnt support apx baddec288 tweak 1d3a19a50 update doc of apx 273d8d5b6 add 3-op imul with T_zu 50875294c add tests of 2-op imul d20142d01 add T_zu eb9de1392 2-op imul supports apx dba2c174f add 2op neg/not_ 95ad5927f add tests of imul/mul/neg/not_ with 1-op 790afb745 add tests o idiv 045ef31a3 add tests of div 1d7e2a6bb div supports apx e5fe58231 remove warning on 32-bit 66b3a3042 check all regs of NF c7dba88df add dec test f55f596ad add inc test 6f6423899 2-op inc/dec 95c0c4e6f tweak inc/dec f5fda7ace change detection of pp with type a18e5aeb5 rorx supports apx 5bb8461b4 blsmsk, blsr support apx a493dc7b4 blsi supports apx 7c1accedc sarx/shlx/shrx support apx and add tests 125d8e740 test bzhi with apx 78be5afd1 add tests of bextr with apx e9603b79d bextr supports apx 3a85aadc6 pdep, pext support apx 16f1a5d8a mulx supports apx 82529af93 andn supports APX 637ad7a4a add test of NF e23f5ad75 fix type for adc 1bcc83303 3-op add supports T_nf 5d46b950b the type of all type is uint64_t 0a8ea9edf fix type b1f0fef4d add test of 3op apx 9b21727ba remove space 6fa1b4a90 reorder of opRO 2d1f229a0 simplify condR b220be972 simplify opRO 24b71a1ce use Reg instead of Operand if possible de1353448 rename opGen with opSSE 4cd8e8eac refactor opGpr as opRRO 01d756917 rename 5037120f7 replace old rex with rexA 45fe94fdd rename opLoadSeg2 with opLoadSeg 253f800bc tweak 4f3939d92 rename opModM2 with opModM fa731a27c rename opModR2 with opModR e5db7d0e4 rename opModRM2 to opModRM dc20fd09b use opModRM2 d4da1561b rename opR_ModM2 with opR_ModM ef3665274 use opR_ModM2 e5b20e5a5 use opModM2 104941db2 use opModM2 6ae769f21 rename opROO2 with opROO 1521cb7ce rename opGen2 to opGen f9c6cb5dc all opGen are replaced with opGen2 249d6978a use opGen2 81ae48922 use opGen2 b9e4bb2fc always put prefix as byte code 3374a158f use opGen2 719f81f45 use opGen2 8d037ebd6 use opGen2 6f8bc28e2 use opGen2 303876cac use opGen2 f0b49752a rewrite opMovXMM 5d4c48ffd rewrite opMMX 189c3488b use opMMX2 1361d0946 use opMMX2 32cafcc61 tweak cf1cfd6c4 add temporary converting code 433bf29e3 replacing opModR with opModR2 ba1d07ed1 senduipi uses opModR2 646da9750 use opModR2 for rdrand, rdseed, movq ccad6cecd use opModR2 for movdq2q, movq2dq 3c21754b9 use opModR2 for movd, movmskps 4718643ef use opModR2 for bswap, maskmovq, pmovmskb e1a148707 try to use opModR2 220a5def7 split avx_type_def.h in gen/ 87b8c8ed2 adox passes the test bd8477292 fix detection of adox without apx 6b19515eb add adcx, adox with APX 77d6acea6 increase the room of type 710e39bfe add test of r, r/m ea9cd9ade tweak 057f09c5b rename T_NF to T_nf 57a0c1935 support NF=1 8f49739da remove cmp of 3-op e3310344c [doc] about APX cdc2533c1 add test of adc/3op 9c6b81c4d return value on nothrow mode 8d524b4a4 add op(r, r/m, imm) and op(r, r/m, r/m) 4c62d1fdc test adc2(r, op, mem) and adc2(r, mem, op) 6f593a1cb test of adc2 (3op APX) 61addb9d9 simplify opMIB 575c447f1 remove rex2p a95bd9cc5 add test of adc/add/and_/cmp/or_/sbb/sub/xor_ f7d3c17e8 tweak d7a7ea912 refactoring rex acd797139 use opModM instead of opMIB ad3334ba6 add modRM with rex2 059d115b5 add test of apx.cpp 873c93a51 add test of regs of apx e25b1cd62 [not tested] add(r1, r2) with rex2 eb118504d remove warning of VC 6c580b1f7 fix cvt test for extended r16-r31 981fa6f05 add r16 - r31 244623812 Merge branch 'dev' aafe3cb62 build(cmake): bump minimum required to version 3.5 76d7477d7 Merge branch 'dev' 151c8ab04 v6.73 dd66cfb76 add tests of avx-vnni-int{8,16} 4a6132d66 update cpuid list bea25541a add detection of AVX_VNNI_INT16 d9e76b1c6 add tests of SM4 e1c4c360b add SM4 d79717dbe add tests of SM3 48f8dbeb6 add SM3 5473d3933 vsha512* check regs 9b3687a68 add detection of SHA512, SM3, SM4 ecdd01ee5 mov crypt test in 64-bit mode c4550b6a9 sde 9.24.0 5762819de add vsha512{msg1, msg2, rnds2} 3255d606a Merge branch 'dev' 322665e72 v6.72 ad178a219 add xabort/xbegin/xend 0924ff4aa Merge branch 'dev' 8980934c1 v6.71 76292b310 add SystemInfo class for win 3e42709ab ignore space and cr 66b2768a6 disable wrong detection of gcc 1855985e1 remove / for mingw64 5bdccc0b8 64bit only for mingw64 33882d0a0 use sysconf(_SC_PAGESIZE) instead of const value 4096 on linux 33075c2bd add link to other projects 60e71402e reorder 79854aa08 add new cpus 5921e270c update cpuid ce083a0dc Merge branch 'dev' b538485f3 v6.70 461dd34ee udpate doc 2149c79e3 add test of alias of vpclmulqdq 2c59c5c91 add alias of vpclmulqdq 729ae4aa3 fix alias of pclmulqdq 3c248d68a define XBYAK_CONSTEXPR if XBYAK_ONLY_CLASS_CPU is defined c0a932d7b Merge remote-tracking branch 'origin/dev' ef502b5b4 update doc ba3db4730 update version c0d7a704f v6.69.2 c535f4737 update cpuid test list 683249232 change the order of args of diff e81b95583 Merge branch 'Wunkolo-constexpr-typet' into dev ab3f40587 Allow constexpr TypeT `operator|` ad5276fa4 Merge pull request #172 from orz--/patch-1 b4d54f6e1 Update changelog.md 58642e0cd Merge branch 'dev' 3b13d068b v6.69.1 d700f6c35 add detection of xsave 740dff2e8 Merge branch 'dev' dc048a04c v6.69 ad0dfffd2 add senduipi/stui/testui/uiret e78f1121b add clui 23b40331a add detection of uintr 98a0f1924 remove warning of sign/unsigned 0afd71a27 add detection of SERIALIZE 363bbaa57 sample shows cpu cache info for AMD edce72709 Cpu supports AMD git-subtree-dir: externals/xbyak git-subtree-split: 2ce465bbca46e92dde9c44bbe7940fd7f70e3b97
2024-01-30 00:36:49 +00:00
{ Cpu::tCLWB, "clwb" },
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
{ Cpu::tMOVDIRI, "movdiri" },
{ Cpu::tMOVDIR64B, "movdir64b" },
Squashed 'externals/xbyak/' changes from a1ac3750f..2ce465bbc 2ce465bbc Merge branch 'dev' 0b3f360eb v7.05 66f22b7a4 update doc 13ee4e19f use opSetCC for setCC 383866b42 use opMR with APX d6e6e6f85 tweak a7b02ac80 RAO_INT supports APX 26840492c use Address.immSize e2b40a33e refactor Address class e1b6896c2 Merge branch 'dev' c0888cc45 v7.04 7d9c82835 refactor rex b3e27734b apx supports 0x0f opecode with rex2 2e7b62d78 bswap supports apx 2e93baa6a Merge branch 'dev' e1864642c unify getMap and getMMM 0750873b7 T_MAP3 is not necessary ee4984222 T_MAP1 is not necessary 5c95842be tweak 8c44467af add no_flags sample 523cf1ed0 fix comment of sample/ccmp.cpp 5438fc69d Merge branch 'dev' ee26c094e v7.03 691ce361a [doc] update dfv 8d0e78146 set 0 for the default value of dfv 2255aea0d [doc] add ccmpSCC and ctestSCC b5e115284 add sample/ccmp.cpp bacd8d34b add sample/zero_upper.cpp f17cb9d6b Merge branch 'dev' c9ce3f8f6 v7.02 3427be298 unify opAESKL and opSHA bfd14244a update doc e690a2a47 sha* supports apx c9765588f Merge branch 'dev' 903f7c02e v7.01 54a1f07f9 update cpuid by sde 223ddfaf8 add detection of sse4a/clwb ba943b5b6 reorder cpu detection 30c362df5 Merge branch 'Sonicadvance1-missing_checks' into dev 02bc84ad8 renumber of tSSE4a, tCLWB 84fe3ab9d update doc 90fc0151c add encodekey{128,256} 440972b88 add detection of KEYLOCKER, KEYLOCKER_WIDE 68a30b91f add detection of AESKLE, WIDE_KL e2d36c662 fix detection of AVX10 48551f5cc add aesenc{128,256}kl, aesencwide{128,256}kl d9c7c992f add aesdecwide{128,256}kl cd5231de0 add aesdec256kl fcb3d0dbb add aesdec128kl 85709ace7 mvoe opKmov in private 406199e7a Support cpuid CLWB 1214aad95 Adds back missing SSE4a check 5315658ad add detection of avx10/apx_f 835f6d2e6 Merge pull request #180 from Tachi107/fix-32bit-tests 650b241e3 test: only run apx test when BIT=64 016ce86b6 [doc] add a blank line df0ebc740 v7.00 1ec2adbbb Merge branch 'apx' da1818592 update doc bec145ba9 amx supports apx 944438195 add tests of kmov* bd85d108c kmov* supports apx 93bd6a0b7 rename T_VEX to T_APX b063d276f add misc tests 6d21c7389 add evex tests 05a66d2c0 support V4 in evex 33017d4fb support V4 in evex e228e737d prepare evex extension of evex 45eca7987 update doc 98ce73bb2 add cfcmov tests e2d9685af add cfcmov a4ec97ca9 add tests of ctestscc 45711c502 add ctestscc a1f6c14cc add alias of dfv facb052a1 avoid r15 on 32-bit mode c1c15848c remove warnings be319626b add ccmpscc with imm c4d05037e add ccmpscc 17f7d279c testing ccmpb ff01b1e20 setcc supports apx 25ceea2ef add 3-op cmovcc 2f8cfb9a8 CMPccXADD supports APX a9310deac add tests of push/pop ec2881bfd push/pop support rex2 114152fed add push2/pop2 1aefdb649 support jmpabs 77eca6d0d add tests of 3-op shift 5e54ffdfa add 3-op shift 426814c50 check v instead of r 3f3d6095c disable rol/ror to support NF ee572b7eb add tests of ror/rol 186d63ad9 add tests of shr/sar 26be71a12 2-op shl supports apx 83f5bd25e remove some warnings e43d99762 add crc32 tests 92153b6f8 crc32 supports apx d7ca6a2dd split T_F2 from T_66|T_F3 fb1fc738f tweak 389d73347 movbe supports apx and append test 3636cde22 tests of 1-byte opcode with rex2 1dd020126 check whether or not it is a 1-byte opcode 083822b52 movdiri supports apx 6703d4344 movdir64b supports apx ed5dc3516 add tests of shld/shrd b01c0ed40 shld/shrd support apx c51c4a6f7 add tests of lzcnt and tzcnt 2cc22ea1b lzcnt and tzcnt support apx baddec288 tweak 1d3a19a50 update doc of apx 273d8d5b6 add 3-op imul with T_zu 50875294c add tests of 2-op imul d20142d01 add T_zu eb9de1392 2-op imul supports apx dba2c174f add 2op neg/not_ 95ad5927f add tests of imul/mul/neg/not_ with 1-op 790afb745 add tests o idiv 045ef31a3 add tests of div 1d7e2a6bb div supports apx e5fe58231 remove warning on 32-bit 66b3a3042 check all regs of NF c7dba88df add dec test f55f596ad add inc test 6f6423899 2-op inc/dec 95c0c4e6f tweak inc/dec f5fda7ace change detection of pp with type a18e5aeb5 rorx supports apx 5bb8461b4 blsmsk, blsr support apx a493dc7b4 blsi supports apx 7c1accedc sarx/shlx/shrx support apx and add tests 125d8e740 test bzhi with apx 78be5afd1 add tests of bextr with apx e9603b79d bextr supports apx 3a85aadc6 pdep, pext support apx 16f1a5d8a mulx supports apx 82529af93 andn supports APX 637ad7a4a add test of NF e23f5ad75 fix type for adc 1bcc83303 3-op add supports T_nf 5d46b950b the type of all type is uint64_t 0a8ea9edf fix type b1f0fef4d add test of 3op apx 9b21727ba remove space 6fa1b4a90 reorder of opRO 2d1f229a0 simplify condR b220be972 simplify opRO 24b71a1ce use Reg instead of Operand if possible de1353448 rename opGen with opSSE 4cd8e8eac refactor opGpr as opRRO 01d756917 rename 5037120f7 replace old rex with rexA 45fe94fdd rename opLoadSeg2 with opLoadSeg 253f800bc tweak 4f3939d92 rename opModM2 with opModM fa731a27c rename opModR2 with opModR e5db7d0e4 rename opModRM2 to opModRM dc20fd09b use opModRM2 d4da1561b rename opR_ModM2 with opR_ModM ef3665274 use opR_ModM2 e5b20e5a5 use opModM2 104941db2 use opModM2 6ae769f21 rename opROO2 with opROO 1521cb7ce rename opGen2 to opGen f9c6cb5dc all opGen are replaced with opGen2 249d6978a use opGen2 81ae48922 use opGen2 b9e4bb2fc always put prefix as byte code 3374a158f use opGen2 719f81f45 use opGen2 8d037ebd6 use opGen2 6f8bc28e2 use opGen2 303876cac use opGen2 f0b49752a rewrite opMovXMM 5d4c48ffd rewrite opMMX 189c3488b use opMMX2 1361d0946 use opMMX2 32cafcc61 tweak cf1cfd6c4 add temporary converting code 433bf29e3 replacing opModR with opModR2 ba1d07ed1 senduipi uses opModR2 646da9750 use opModR2 for rdrand, rdseed, movq ccad6cecd use opModR2 for movdq2q, movq2dq 3c21754b9 use opModR2 for movd, movmskps 4718643ef use opModR2 for bswap, maskmovq, pmovmskb e1a148707 try to use opModR2 220a5def7 split avx_type_def.h in gen/ 87b8c8ed2 adox passes the test bd8477292 fix detection of adox without apx 6b19515eb add adcx, adox with APX 77d6acea6 increase the room of type 710e39bfe add test of r, r/m ea9cd9ade tweak 057f09c5b rename T_NF to T_nf 57a0c1935 support NF=1 8f49739da remove cmp of 3-op e3310344c [doc] about APX cdc2533c1 add test of adc/3op 9c6b81c4d return value on nothrow mode 8d524b4a4 add op(r, r/m, imm) and op(r, r/m, r/m) 4c62d1fdc test adc2(r, op, mem) and adc2(r, mem, op) 6f593a1cb test of adc2 (3op APX) 61addb9d9 simplify opMIB 575c447f1 remove rex2p a95bd9cc5 add test of adc/add/and_/cmp/or_/sbb/sub/xor_ f7d3c17e8 tweak d7a7ea912 refactoring rex acd797139 use opModM instead of opMIB ad3334ba6 add modRM with rex2 059d115b5 add test of apx.cpp 873c93a51 add test of regs of apx e25b1cd62 [not tested] add(r1, r2) with rex2 eb118504d remove warning of VC 6c580b1f7 fix cvt test for extended r16-r31 981fa6f05 add r16 - r31 244623812 Merge branch 'dev' aafe3cb62 build(cmake): bump minimum required to version 3.5 76d7477d7 Merge branch 'dev' 151c8ab04 v6.73 dd66cfb76 add tests of avx-vnni-int{8,16} 4a6132d66 update cpuid list bea25541a add detection of AVX_VNNI_INT16 d9e76b1c6 add tests of SM4 e1c4c360b add SM4 d79717dbe add tests of SM3 48f8dbeb6 add SM3 5473d3933 vsha512* check regs 9b3687a68 add detection of SHA512, SM3, SM4 ecdd01ee5 mov crypt test in 64-bit mode c4550b6a9 sde 9.24.0 5762819de add vsha512{msg1, msg2, rnds2} 3255d606a Merge branch 'dev' 322665e72 v6.72 ad178a219 add xabort/xbegin/xend 0924ff4aa Merge branch 'dev' 8980934c1 v6.71 76292b310 add SystemInfo class for win 3e42709ab ignore space and cr 66b2768a6 disable wrong detection of gcc 1855985e1 remove / for mingw64 5bdccc0b8 64bit only for mingw64 33882d0a0 use sysconf(_SC_PAGESIZE) instead of const value 4096 on linux 33075c2bd add link to other projects 60e71402e reorder 79854aa08 add new cpus 5921e270c update cpuid ce083a0dc Merge branch 'dev' b538485f3 v6.70 461dd34ee udpate doc 2149c79e3 add test of alias of vpclmulqdq 2c59c5c91 add alias of vpclmulqdq 729ae4aa3 fix alias of pclmulqdq 3c248d68a define XBYAK_CONSTEXPR if XBYAK_ONLY_CLASS_CPU is defined c0a932d7b Merge remote-tracking branch 'origin/dev' ef502b5b4 update doc ba3db4730 update version c0d7a704f v6.69.2 c535f4737 update cpuid test list 683249232 change the order of args of diff e81b95583 Merge branch 'Wunkolo-constexpr-typet' into dev ab3f40587 Allow constexpr TypeT `operator|` ad5276fa4 Merge pull request #172 from orz--/patch-1 b4d54f6e1 Update changelog.md 58642e0cd Merge branch 'dev' 3b13d068b v6.69.1 d700f6c35 add detection of xsave 740dff2e8 Merge branch 'dev' dc048a04c v6.69 ad0dfffd2 add senduipi/stui/testui/uiret e78f1121b add clui 23b40331a add detection of uintr 98a0f1924 remove warning of sign/unsigned 0afd71a27 add detection of SERIALIZE 363bbaa57 sample shows cpu cache info for AMD edce72709 Cpu supports AMD git-subtree-dir: externals/xbyak git-subtree-split: 2ce465bbca46e92dde9c44bbe7940fd7f70e3b97
2024-01-30 00:36:49 +00:00
{ Cpu::tUINTR, "uintr" },
{ Cpu::tSERIALIZE, "serialize" },
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
{ Cpu::tCLZERO, "clzero" },
Squashed 'externals/xbyak/' changes from 88f2f771f..a1ac3750f a1ac3750f Merge branch 'dev' 5f4ba971f v6.68 cac2c175f update doc 1b08a8248 add test of prefetchiti bef70d9b1 add prefetchit{0,1} f66785876 add detection of prefetchiti 124617ac9 Merge branch 'dev' 1bce8be17 Merge commit 'fbb18f6' into dev bebfe64a3 [test] X32 is optional and remove CFLAGS d8c332cef Merge branch 'Tachi107-small-changes' into dev fbb18f69d ci: use containers 8a974696c test: simplify makefile 1efe9fe7c Merge branch 'dev' bb70083e6 v6.67 436e452d7 update doc 47ff6ef42 I get an error after all on GitHub action 445c0dcec add test of CMPccXADD c9347907d add CMPccXADD dc792cc56 add detection of cmpccxadd 62be84cc8 fix detection of boost b5ac7b0f0 Merge branch 'dev' 05dd400e0 recover a removed line 94eff6246 v6.66 ec3fadeba update doc 00bfaaa7f add test of rao-int 0f2f1aaa6 support rio-int 6c047f480 detect rao-int f07c5c255 fix args of EmptyAllocator::alloc in test 04d3eb5f5 stop if a test script causes an error 1c1d2366f disable boost sample cfb1127c3 tweak 5fcbeb7c4 [sample] change the way of detection of boost bafc1ee60 CXX uses g++ as default value d8cabc6cb remove warning of blace bc73a0816 remove -fno-operator-names option 6989aea94 use CXX instead of g++ a7c5a1bd7 use English 1bfbd8c4d Fix incorrect format strings 0ecef5c28 Merge branch 'dev' 7556c20ba update doc a15709271 v6.65 3b83aab3e add detect_x32 to TARGET 8c64bbbc3 use gcc instead of dpkg for portability 5e9a9b96f test_avx512.sh runs on x32 8ae01b0c2 disable some tests on x32 83b3da217 x32 does not check large disp 693ab8c9d sizeof(void*) = 4 on x32, so disable the test 348e3e548 Merge branch 'dev' 11b9c4dc0 v6.64 459636196 add T_M_K flag to vpmov* 1d3722928 add include path 5e27eddae move CrearError from LabelManager::reset() to CodeGenerator::reset() f8ea5c28d Merge branch 'dev' 20b2b1eae v6.63 3706869f8 desc. of setDefaultEncoding d6f2d7577 add test of setDefaultEncoding 3b0a19c41 vpmadd52{h,l}uq for avx-ifma 95752ebd7 add tAVX_IFMA cd36e31ea [sample] show AMX_FP16/AVX_VNNI_INT8/AVX_NE_CONVERT e5858af27 add setDefaultEncoding 2f7fb0220 modify gen.cpp for AVX-NE-CONVERT/AVX-VNNI-INT8/AMX-FP16 1c5cb7efa add AVX-NE-CONVERT instructions 564fe9acd add AVX-VNNI-INT8 instructions cd14d07b1 add AMX-FP16 instruction 7811f593c Merge pull request #161 from scribam/patch-1 2218f6c08 Update changelog.md 7bccdbbb4 Merge pull request #160 from herumi/dev 5fcf87596 compile nasm-2.15 instead of apt install e31961ea8 v6.62 ff4f9e65c update doc 9c8fb81db disable wrong detection of gcc -Warray-bounds 6b7519659 add serialize e16582696 Merge branch 'JonLiu1993-vcpkg-installition' into dev edbb410fb Add vcpkg installation instructions 055d31242 Merge branch 'dev' 21ab98441 Merge branch 'akodanka-enable_CIV' into dev ed4d598e3 Changes to compile xbyak project for openvino b652430c4 mingw uses __cpuidex 48457bfa0 Merge branch 'dev' 29cb524d1 v6.61.2 1a9a0b0e1 avoid including algorithm header in xbyak_util.h 6fadefd04 Merge branch 'dev' fc1c18a9d update doc f7cae7f11 v6.61.1 6f5ec5cf3 Merge branch 'doyaGu-master' into dev 4554d6bb9 Fix error related to XBYAK_NOEXCEPT git-subtree-dir: externals/xbyak git-subtree-split: a1ac3750f9a639b5a6c6d6c7da4259b8d6790989
2022-12-30 23:05:02 +00:00
{ Cpu::tAMX_FP16, "amx_fp16" },
{ Cpu::tAVX_VNNI_INT8, "avx_vnni_int8" },
{ Cpu::tAVX_NE_CONVERT, "avx_ne_convert" },
{ Cpu::tAVX_IFMA, "avx_ifma" },
{ Cpu::tRAO_INT, "rao-int" },
{ Cpu::tCMPCCXADD, "cmpccxadd" },
{ Cpu::tPREFETCHITI, "prefetchiti" },
Squashed 'externals/xbyak/' changes from a1ac3750f..2ce465bbc 2ce465bbc Merge branch 'dev' 0b3f360eb v7.05 66f22b7a4 update doc 13ee4e19f use opSetCC for setCC 383866b42 use opMR with APX d6e6e6f85 tweak a7b02ac80 RAO_INT supports APX 26840492c use Address.immSize e2b40a33e refactor Address class e1b6896c2 Merge branch 'dev' c0888cc45 v7.04 7d9c82835 refactor rex b3e27734b apx supports 0x0f opecode with rex2 2e7b62d78 bswap supports apx 2e93baa6a Merge branch 'dev' e1864642c unify getMap and getMMM 0750873b7 T_MAP3 is not necessary ee4984222 T_MAP1 is not necessary 5c95842be tweak 8c44467af add no_flags sample 523cf1ed0 fix comment of sample/ccmp.cpp 5438fc69d Merge branch 'dev' ee26c094e v7.03 691ce361a [doc] update dfv 8d0e78146 set 0 for the default value of dfv 2255aea0d [doc] add ccmpSCC and ctestSCC b5e115284 add sample/ccmp.cpp bacd8d34b add sample/zero_upper.cpp f17cb9d6b Merge branch 'dev' c9ce3f8f6 v7.02 3427be298 unify opAESKL and opSHA bfd14244a update doc e690a2a47 sha* supports apx c9765588f Merge branch 'dev' 903f7c02e v7.01 54a1f07f9 update cpuid by sde 223ddfaf8 add detection of sse4a/clwb ba943b5b6 reorder cpu detection 30c362df5 Merge branch 'Sonicadvance1-missing_checks' into dev 02bc84ad8 renumber of tSSE4a, tCLWB 84fe3ab9d update doc 90fc0151c add encodekey{128,256} 440972b88 add detection of KEYLOCKER, KEYLOCKER_WIDE 68a30b91f add detection of AESKLE, WIDE_KL e2d36c662 fix detection of AVX10 48551f5cc add aesenc{128,256}kl, aesencwide{128,256}kl d9c7c992f add aesdecwide{128,256}kl cd5231de0 add aesdec256kl fcb3d0dbb add aesdec128kl 85709ace7 mvoe opKmov in private 406199e7a Support cpuid CLWB 1214aad95 Adds back missing SSE4a check 5315658ad add detection of avx10/apx_f 835f6d2e6 Merge pull request #180 from Tachi107/fix-32bit-tests 650b241e3 test: only run apx test when BIT=64 016ce86b6 [doc] add a blank line df0ebc740 v7.00 1ec2adbbb Merge branch 'apx' da1818592 update doc bec145ba9 amx supports apx 944438195 add tests of kmov* bd85d108c kmov* supports apx 93bd6a0b7 rename T_VEX to T_APX b063d276f add misc tests 6d21c7389 add evex tests 05a66d2c0 support V4 in evex 33017d4fb support V4 in evex e228e737d prepare evex extension of evex 45eca7987 update doc 98ce73bb2 add cfcmov tests e2d9685af add cfcmov a4ec97ca9 add tests of ctestscc 45711c502 add ctestscc a1f6c14cc add alias of dfv facb052a1 avoid r15 on 32-bit mode c1c15848c remove warnings be319626b add ccmpscc with imm c4d05037e add ccmpscc 17f7d279c testing ccmpb ff01b1e20 setcc supports apx 25ceea2ef add 3-op cmovcc 2f8cfb9a8 CMPccXADD supports APX a9310deac add tests of push/pop ec2881bfd push/pop support rex2 114152fed add push2/pop2 1aefdb649 support jmpabs 77eca6d0d add tests of 3-op shift 5e54ffdfa add 3-op shift 426814c50 check v instead of r 3f3d6095c disable rol/ror to support NF ee572b7eb add tests of ror/rol 186d63ad9 add tests of shr/sar 26be71a12 2-op shl supports apx 83f5bd25e remove some warnings e43d99762 add crc32 tests 92153b6f8 crc32 supports apx d7ca6a2dd split T_F2 from T_66|T_F3 fb1fc738f tweak 389d73347 movbe supports apx and append test 3636cde22 tests of 1-byte opcode with rex2 1dd020126 check whether or not it is a 1-byte opcode 083822b52 movdiri supports apx 6703d4344 movdir64b supports apx ed5dc3516 add tests of shld/shrd b01c0ed40 shld/shrd support apx c51c4a6f7 add tests of lzcnt and tzcnt 2cc22ea1b lzcnt and tzcnt support apx baddec288 tweak 1d3a19a50 update doc of apx 273d8d5b6 add 3-op imul with T_zu 50875294c add tests of 2-op imul d20142d01 add T_zu eb9de1392 2-op imul supports apx dba2c174f add 2op neg/not_ 95ad5927f add tests of imul/mul/neg/not_ with 1-op 790afb745 add tests o idiv 045ef31a3 add tests of div 1d7e2a6bb div supports apx e5fe58231 remove warning on 32-bit 66b3a3042 check all regs of NF c7dba88df add dec test f55f596ad add inc test 6f6423899 2-op inc/dec 95c0c4e6f tweak inc/dec f5fda7ace change detection of pp with type a18e5aeb5 rorx supports apx 5bb8461b4 blsmsk, blsr support apx a493dc7b4 blsi supports apx 7c1accedc sarx/shlx/shrx support apx and add tests 125d8e740 test bzhi with apx 78be5afd1 add tests of bextr with apx e9603b79d bextr supports apx 3a85aadc6 pdep, pext support apx 16f1a5d8a mulx supports apx 82529af93 andn supports APX 637ad7a4a add test of NF e23f5ad75 fix type for adc 1bcc83303 3-op add supports T_nf 5d46b950b the type of all type is uint64_t 0a8ea9edf fix type b1f0fef4d add test of 3op apx 9b21727ba remove space 6fa1b4a90 reorder of opRO 2d1f229a0 simplify condR b220be972 simplify opRO 24b71a1ce use Reg instead of Operand if possible de1353448 rename opGen with opSSE 4cd8e8eac refactor opGpr as opRRO 01d756917 rename 5037120f7 replace old rex with rexA 45fe94fdd rename opLoadSeg2 with opLoadSeg 253f800bc tweak 4f3939d92 rename opModM2 with opModM fa731a27c rename opModR2 with opModR e5db7d0e4 rename opModRM2 to opModRM dc20fd09b use opModRM2 d4da1561b rename opR_ModM2 with opR_ModM ef3665274 use opR_ModM2 e5b20e5a5 use opModM2 104941db2 use opModM2 6ae769f21 rename opROO2 with opROO 1521cb7ce rename opGen2 to opGen f9c6cb5dc all opGen are replaced with opGen2 249d6978a use opGen2 81ae48922 use opGen2 b9e4bb2fc always put prefix as byte code 3374a158f use opGen2 719f81f45 use opGen2 8d037ebd6 use opGen2 6f8bc28e2 use opGen2 303876cac use opGen2 f0b49752a rewrite opMovXMM 5d4c48ffd rewrite opMMX 189c3488b use opMMX2 1361d0946 use opMMX2 32cafcc61 tweak cf1cfd6c4 add temporary converting code 433bf29e3 replacing opModR with opModR2 ba1d07ed1 senduipi uses opModR2 646da9750 use opModR2 for rdrand, rdseed, movq ccad6cecd use opModR2 for movdq2q, movq2dq 3c21754b9 use opModR2 for movd, movmskps 4718643ef use opModR2 for bswap, maskmovq, pmovmskb e1a148707 try to use opModR2 220a5def7 split avx_type_def.h in gen/ 87b8c8ed2 adox passes the test bd8477292 fix detection of adox without apx 6b19515eb add adcx, adox with APX 77d6acea6 increase the room of type 710e39bfe add test of r, r/m ea9cd9ade tweak 057f09c5b rename T_NF to T_nf 57a0c1935 support NF=1 8f49739da remove cmp of 3-op e3310344c [doc] about APX cdc2533c1 add test of adc/3op 9c6b81c4d return value on nothrow mode 8d524b4a4 add op(r, r/m, imm) and op(r, r/m, r/m) 4c62d1fdc test adc2(r, op, mem) and adc2(r, mem, op) 6f593a1cb test of adc2 (3op APX) 61addb9d9 simplify opMIB 575c447f1 remove rex2p a95bd9cc5 add test of adc/add/and_/cmp/or_/sbb/sub/xor_ f7d3c17e8 tweak d7a7ea912 refactoring rex acd797139 use opModM instead of opMIB ad3334ba6 add modRM with rex2 059d115b5 add test of apx.cpp 873c93a51 add test of regs of apx e25b1cd62 [not tested] add(r1, r2) with rex2 eb118504d remove warning of VC 6c580b1f7 fix cvt test for extended r16-r31 981fa6f05 add r16 - r31 244623812 Merge branch 'dev' aafe3cb62 build(cmake): bump minimum required to version 3.5 76d7477d7 Merge branch 'dev' 151c8ab04 v6.73 dd66cfb76 add tests of avx-vnni-int{8,16} 4a6132d66 update cpuid list bea25541a add detection of AVX_VNNI_INT16 d9e76b1c6 add tests of SM4 e1c4c360b add SM4 d79717dbe add tests of SM3 48f8dbeb6 add SM3 5473d3933 vsha512* check regs 9b3687a68 add detection of SHA512, SM3, SM4 ecdd01ee5 mov crypt test in 64-bit mode c4550b6a9 sde 9.24.0 5762819de add vsha512{msg1, msg2, rnds2} 3255d606a Merge branch 'dev' 322665e72 v6.72 ad178a219 add xabort/xbegin/xend 0924ff4aa Merge branch 'dev' 8980934c1 v6.71 76292b310 add SystemInfo class for win 3e42709ab ignore space and cr 66b2768a6 disable wrong detection of gcc 1855985e1 remove / for mingw64 5bdccc0b8 64bit only for mingw64 33882d0a0 use sysconf(_SC_PAGESIZE) instead of const value 4096 on linux 33075c2bd add link to other projects 60e71402e reorder 79854aa08 add new cpus 5921e270c update cpuid ce083a0dc Merge branch 'dev' b538485f3 v6.70 461dd34ee udpate doc 2149c79e3 add test of alias of vpclmulqdq 2c59c5c91 add alias of vpclmulqdq 729ae4aa3 fix alias of pclmulqdq 3c248d68a define XBYAK_CONSTEXPR if XBYAK_ONLY_CLASS_CPU is defined c0a932d7b Merge remote-tracking branch 'origin/dev' ef502b5b4 update doc ba3db4730 update version c0d7a704f v6.69.2 c535f4737 update cpuid test list 683249232 change the order of args of diff e81b95583 Merge branch 'Wunkolo-constexpr-typet' into dev ab3f40587 Allow constexpr TypeT `operator|` ad5276fa4 Merge pull request #172 from orz--/patch-1 b4d54f6e1 Update changelog.md 58642e0cd Merge branch 'dev' 3b13d068b v6.69.1 d700f6c35 add detection of xsave 740dff2e8 Merge branch 'dev' dc048a04c v6.69 ad0dfffd2 add senduipi/stui/testui/uiret e78f1121b add clui 23b40331a add detection of uintr 98a0f1924 remove warning of sign/unsigned 0afd71a27 add detection of SERIALIZE 363bbaa57 sample shows cpu cache info for AMD edce72709 Cpu supports AMD git-subtree-dir: externals/xbyak git-subtree-split: 2ce465bbca46e92dde9c44bbe7940fd7f70e3b97
2024-01-30 00:36:49 +00:00
{ Cpu::tSHA512, "sha512" },
{ Cpu::tSM3, "sm3" },
{ Cpu::tSM4, "sm4" },
{ Cpu::tAVX_VNNI_INT16, "avx_vnni_int16" },
{ Cpu::tAPX_F, "apx_f" },
{ Cpu::tAVX10, "avx10" },
{ Cpu::tAESKLE, "aeskle" },
{ Cpu::tWIDE_KL, "wide_kl" },
{ Cpu::tKEYLOCKER, "keylocker" },
{ Cpu::tKEYLOCKER_WIDE, "keylocker_wide" },
};
for (size_t i = 0; i < NUM_OF_ARRAY(tbl); i++) {
if (cpu.has(tbl[i].type)) printf(" %s", tbl[i].str);
}
printf("\n");
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
if (onlyCpuidFeature) return;
Squashed 'externals/xbyak/' changes from a1ac3750f..2ce465bbc 2ce465bbc Merge branch 'dev' 0b3f360eb v7.05 66f22b7a4 update doc 13ee4e19f use opSetCC for setCC 383866b42 use opMR with APX d6e6e6f85 tweak a7b02ac80 RAO_INT supports APX 26840492c use Address.immSize e2b40a33e refactor Address class e1b6896c2 Merge branch 'dev' c0888cc45 v7.04 7d9c82835 refactor rex b3e27734b apx supports 0x0f opecode with rex2 2e7b62d78 bswap supports apx 2e93baa6a Merge branch 'dev' e1864642c unify getMap and getMMM 0750873b7 T_MAP3 is not necessary ee4984222 T_MAP1 is not necessary 5c95842be tweak 8c44467af add no_flags sample 523cf1ed0 fix comment of sample/ccmp.cpp 5438fc69d Merge branch 'dev' ee26c094e v7.03 691ce361a [doc] update dfv 8d0e78146 set 0 for the default value of dfv 2255aea0d [doc] add ccmpSCC and ctestSCC b5e115284 add sample/ccmp.cpp bacd8d34b add sample/zero_upper.cpp f17cb9d6b Merge branch 'dev' c9ce3f8f6 v7.02 3427be298 unify opAESKL and opSHA bfd14244a update doc e690a2a47 sha* supports apx c9765588f Merge branch 'dev' 903f7c02e v7.01 54a1f07f9 update cpuid by sde 223ddfaf8 add detection of sse4a/clwb ba943b5b6 reorder cpu detection 30c362df5 Merge branch 'Sonicadvance1-missing_checks' into dev 02bc84ad8 renumber of tSSE4a, tCLWB 84fe3ab9d update doc 90fc0151c add encodekey{128,256} 440972b88 add detection of KEYLOCKER, KEYLOCKER_WIDE 68a30b91f add detection of AESKLE, WIDE_KL e2d36c662 fix detection of AVX10 48551f5cc add aesenc{128,256}kl, aesencwide{128,256}kl d9c7c992f add aesdecwide{128,256}kl cd5231de0 add aesdec256kl fcb3d0dbb add aesdec128kl 85709ace7 mvoe opKmov in private 406199e7a Support cpuid CLWB 1214aad95 Adds back missing SSE4a check 5315658ad add detection of avx10/apx_f 835f6d2e6 Merge pull request #180 from Tachi107/fix-32bit-tests 650b241e3 test: only run apx test when BIT=64 016ce86b6 [doc] add a blank line df0ebc740 v7.00 1ec2adbbb Merge branch 'apx' da1818592 update doc bec145ba9 amx supports apx 944438195 add tests of kmov* bd85d108c kmov* supports apx 93bd6a0b7 rename T_VEX to T_APX b063d276f add misc tests 6d21c7389 add evex tests 05a66d2c0 support V4 in evex 33017d4fb support V4 in evex e228e737d prepare evex extension of evex 45eca7987 update doc 98ce73bb2 add cfcmov tests e2d9685af add cfcmov a4ec97ca9 add tests of ctestscc 45711c502 add ctestscc a1f6c14cc add alias of dfv facb052a1 avoid r15 on 32-bit mode c1c15848c remove warnings be319626b add ccmpscc with imm c4d05037e add ccmpscc 17f7d279c testing ccmpb ff01b1e20 setcc supports apx 25ceea2ef add 3-op cmovcc 2f8cfb9a8 CMPccXADD supports APX a9310deac add tests of push/pop ec2881bfd push/pop support rex2 114152fed add push2/pop2 1aefdb649 support jmpabs 77eca6d0d add tests of 3-op shift 5e54ffdfa add 3-op shift 426814c50 check v instead of r 3f3d6095c disable rol/ror to support NF ee572b7eb add tests of ror/rol 186d63ad9 add tests of shr/sar 26be71a12 2-op shl supports apx 83f5bd25e remove some warnings e43d99762 add crc32 tests 92153b6f8 crc32 supports apx d7ca6a2dd split T_F2 from T_66|T_F3 fb1fc738f tweak 389d73347 movbe supports apx and append test 3636cde22 tests of 1-byte opcode with rex2 1dd020126 check whether or not it is a 1-byte opcode 083822b52 movdiri supports apx 6703d4344 movdir64b supports apx ed5dc3516 add tests of shld/shrd b01c0ed40 shld/shrd support apx c51c4a6f7 add tests of lzcnt and tzcnt 2cc22ea1b lzcnt and tzcnt support apx baddec288 tweak 1d3a19a50 update doc of apx 273d8d5b6 add 3-op imul with T_zu 50875294c add tests of 2-op imul d20142d01 add T_zu eb9de1392 2-op imul supports apx dba2c174f add 2op neg/not_ 95ad5927f add tests of imul/mul/neg/not_ with 1-op 790afb745 add tests o idiv 045ef31a3 add tests of div 1d7e2a6bb div supports apx e5fe58231 remove warning on 32-bit 66b3a3042 check all regs of NF c7dba88df add dec test f55f596ad add inc test 6f6423899 2-op inc/dec 95c0c4e6f tweak inc/dec f5fda7ace change detection of pp with type a18e5aeb5 rorx supports apx 5bb8461b4 blsmsk, blsr support apx a493dc7b4 blsi supports apx 7c1accedc sarx/shlx/shrx support apx and add tests 125d8e740 test bzhi with apx 78be5afd1 add tests of bextr with apx e9603b79d bextr supports apx 3a85aadc6 pdep, pext support apx 16f1a5d8a mulx supports apx 82529af93 andn supports APX 637ad7a4a add test of NF e23f5ad75 fix type for adc 1bcc83303 3-op add supports T_nf 5d46b950b the type of all type is uint64_t 0a8ea9edf fix type b1f0fef4d add test of 3op apx 9b21727ba remove space 6fa1b4a90 reorder of opRO 2d1f229a0 simplify condR b220be972 simplify opRO 24b71a1ce use Reg instead of Operand if possible de1353448 rename opGen with opSSE 4cd8e8eac refactor opGpr as opRRO 01d756917 rename 5037120f7 replace old rex with rexA 45fe94fdd rename opLoadSeg2 with opLoadSeg 253f800bc tweak 4f3939d92 rename opModM2 with opModM fa731a27c rename opModR2 with opModR e5db7d0e4 rename opModRM2 to opModRM dc20fd09b use opModRM2 d4da1561b rename opR_ModM2 with opR_ModM ef3665274 use opR_ModM2 e5b20e5a5 use opModM2 104941db2 use opModM2 6ae769f21 rename opROO2 with opROO 1521cb7ce rename opGen2 to opGen f9c6cb5dc all opGen are replaced with opGen2 249d6978a use opGen2 81ae48922 use opGen2 b9e4bb2fc always put prefix as byte code 3374a158f use opGen2 719f81f45 use opGen2 8d037ebd6 use opGen2 6f8bc28e2 use opGen2 303876cac use opGen2 f0b49752a rewrite opMovXMM 5d4c48ffd rewrite opMMX 189c3488b use opMMX2 1361d0946 use opMMX2 32cafcc61 tweak cf1cfd6c4 add temporary converting code 433bf29e3 replacing opModR with opModR2 ba1d07ed1 senduipi uses opModR2 646da9750 use opModR2 for rdrand, rdseed, movq ccad6cecd use opModR2 for movdq2q, movq2dq 3c21754b9 use opModR2 for movd, movmskps 4718643ef use opModR2 for bswap, maskmovq, pmovmskb e1a148707 try to use opModR2 220a5def7 split avx_type_def.h in gen/ 87b8c8ed2 adox passes the test bd8477292 fix detection of adox without apx 6b19515eb add adcx, adox with APX 77d6acea6 increase the room of type 710e39bfe add test of r, r/m ea9cd9ade tweak 057f09c5b rename T_NF to T_nf 57a0c1935 support NF=1 8f49739da remove cmp of 3-op e3310344c [doc] about APX cdc2533c1 add test of adc/3op 9c6b81c4d return value on nothrow mode 8d524b4a4 add op(r, r/m, imm) and op(r, r/m, r/m) 4c62d1fdc test adc2(r, op, mem) and adc2(r, mem, op) 6f593a1cb test of adc2 (3op APX) 61addb9d9 simplify opMIB 575c447f1 remove rex2p a95bd9cc5 add test of adc/add/and_/cmp/or_/sbb/sub/xor_ f7d3c17e8 tweak d7a7ea912 refactoring rex acd797139 use opModM instead of opMIB ad3334ba6 add modRM with rex2 059d115b5 add test of apx.cpp 873c93a51 add test of regs of apx e25b1cd62 [not tested] add(r1, r2) with rex2 eb118504d remove warning of VC 6c580b1f7 fix cvt test for extended r16-r31 981fa6f05 add r16 - r31 244623812 Merge branch 'dev' aafe3cb62 build(cmake): bump minimum required to version 3.5 76d7477d7 Merge branch 'dev' 151c8ab04 v6.73 dd66cfb76 add tests of avx-vnni-int{8,16} 4a6132d66 update cpuid list bea25541a add detection of AVX_VNNI_INT16 d9e76b1c6 add tests of SM4 e1c4c360b add SM4 d79717dbe add tests of SM3 48f8dbeb6 add SM3 5473d3933 vsha512* check regs 9b3687a68 add detection of SHA512, SM3, SM4 ecdd01ee5 mov crypt test in 64-bit mode c4550b6a9 sde 9.24.0 5762819de add vsha512{msg1, msg2, rnds2} 3255d606a Merge branch 'dev' 322665e72 v6.72 ad178a219 add xabort/xbegin/xend 0924ff4aa Merge branch 'dev' 8980934c1 v6.71 76292b310 add SystemInfo class for win 3e42709ab ignore space and cr 66b2768a6 disable wrong detection of gcc 1855985e1 remove / for mingw64 5bdccc0b8 64bit only for mingw64 33882d0a0 use sysconf(_SC_PAGESIZE) instead of const value 4096 on linux 33075c2bd add link to other projects 60e71402e reorder 79854aa08 add new cpus 5921e270c update cpuid ce083a0dc Merge branch 'dev' b538485f3 v6.70 461dd34ee udpate doc 2149c79e3 add test of alias of vpclmulqdq 2c59c5c91 add alias of vpclmulqdq 729ae4aa3 fix alias of pclmulqdq 3c248d68a define XBYAK_CONSTEXPR if XBYAK_ONLY_CLASS_CPU is defined c0a932d7b Merge remote-tracking branch 'origin/dev' ef502b5b4 update doc ba3db4730 update version c0d7a704f v6.69.2 c535f4737 update cpuid test list 683249232 change the order of args of diff e81b95583 Merge branch 'Wunkolo-constexpr-typet' into dev ab3f40587 Allow constexpr TypeT `operator|` ad5276fa4 Merge pull request #172 from orz--/patch-1 b4d54f6e1 Update changelog.md 58642e0cd Merge branch 'dev' 3b13d068b v6.69.1 d700f6c35 add detection of xsave 740dff2e8 Merge branch 'dev' dc048a04c v6.69 ad0dfffd2 add senduipi/stui/testui/uiret e78f1121b add clui 23b40331a add detection of uintr 98a0f1924 remove warning of sign/unsigned 0afd71a27 add detection of SERIALIZE 363bbaa57 sample shows cpu cache info for AMD edce72709 Cpu supports AMD git-subtree-dir: externals/xbyak git-subtree-split: 2ce465bbca46e92dde9c44bbe7940fd7f70e3b97
2024-01-30 00:36:49 +00:00
if (cpu.has(Cpu::tAVX10)) {
printf("AVX10 version %d\n", cpu.getAVX10version());
}
if (cpu.has(Cpu::tPOPCNT)) {
const int n = 0x12345678; // bitcount = 13
const int ok = 13;
Squashed 'externals/xbyak/' changes from 0140eeff1..590c10e37 590c10e37 fix typo 396715a89 use github action 69a25fd92 change build status to travis-ci.com a6a9dac91 meanings of the name 8d1e41b65 test_util.cpp supports OpenBSD 77ffe7173 Merge pull request #115 from Ryan-rsm-McKenzie/master a1da3403a fix build interface include directory e0136d4ef fix add_library call with INTERFACE 3071eee0c support slightly more modern cmake e626d6209 v5.991 a49c4bc11 disable XBYAK_CONSTEXPR for g++-5 -std=c++-14 70777a699 Merge branch 'atafra-old_mac_fix' into dev 6b81678d0 fixed compile error on some older macOS versions 2c3b43f15 refactor util 91784e2b8 test_util checks AMX and AVX_VNNI 70b70c557 update to v5.99 284cc5bed refactor 6b3eb9c1e default encoding is always evex f85b1100b refactor vnni 276d09bae Merge branch 'akharito-akharito/adl_support' into dev 50df86ce3 v5.98 97ce92d58 Merge branch 'akharito/adl_support' of https://github.com/akharito/xbyak into akharito-akharito/adl_support 1f119a04a support [scale * reg] 9ee1bef9a cpuid - check that GRT CPUID leaf 7 subleaf 0 should return EAX=1 be93adb2c add AVX VNNI instruction support 0c277240a add ADL CPUID a9a5cc2e2 Add option to choose VEX or EVEX encoding 29bfd25ba fix indent a0c49fa2e Merge branch 'atafra-mac_avx512_fix' into dev ea388b3c6 fixed incorrect detection of AVX-512 on macOS ed1b8186f Merge branch 'FEX-Emu-extended_features' into dev 3dacddfec Merge branch 'extended_features' of https://github.com/FEX-Emu/xbyak into FEX-Emu-extended_features 898f78ca3 Merge branch 'kariya-mitsuru-use-sh' 0b7f1411c Merge branch 'use-sh' of https://github.com/kariya-mitsuru/xbyak into kariya-mitsuru-use-sh 99e2b13b2 Fixes extended feature support checking b0a43c7e5 Use sh instead of tcsh for test scripts 87e8f41ae remove warning of _MSC_VER git-subtree-dir: externals/xbyak git-subtree-split: 590c10e3746978dbfcf102d6da933ac2659e4544
2021-03-27 21:08:22 +00:00
PopCountTest code(n);
code.setProtectModeRE();
int (*f)() = code.getCode<int (*)()>();
int r = f();
if (r == ok) {
puts("popcnt ok");
} else {
printf("popcnt ng %d %d\n", r, ok);
}
Squashed 'externals/xbyak/' changes from 0140eeff1..590c10e37 590c10e37 fix typo 396715a89 use github action 69a25fd92 change build status to travis-ci.com a6a9dac91 meanings of the name 8d1e41b65 test_util.cpp supports OpenBSD 77ffe7173 Merge pull request #115 from Ryan-rsm-McKenzie/master a1da3403a fix build interface include directory e0136d4ef fix add_library call with INTERFACE 3071eee0c support slightly more modern cmake e626d6209 v5.991 a49c4bc11 disable XBYAK_CONSTEXPR for g++-5 -std=c++-14 70777a699 Merge branch 'atafra-old_mac_fix' into dev 6b81678d0 fixed compile error on some older macOS versions 2c3b43f15 refactor util 91784e2b8 test_util checks AMX and AVX_VNNI 70b70c557 update to v5.99 284cc5bed refactor 6b3eb9c1e default encoding is always evex f85b1100b refactor vnni 276d09bae Merge branch 'akharito-akharito/adl_support' into dev 50df86ce3 v5.98 97ce92d58 Merge branch 'akharito/adl_support' of https://github.com/akharito/xbyak into akharito-akharito/adl_support 1f119a04a support [scale * reg] 9ee1bef9a cpuid - check that GRT CPUID leaf 7 subleaf 0 should return EAX=1 be93adb2c add AVX VNNI instruction support 0c277240a add ADL CPUID a9a5cc2e2 Add option to choose VEX or EVEX encoding 29bfd25ba fix indent a0c49fa2e Merge branch 'atafra-mac_avx512_fix' into dev ea388b3c6 fixed incorrect detection of AVX-512 on macOS ed1b8186f Merge branch 'FEX-Emu-extended_features' into dev 3dacddfec Merge branch 'extended_features' of https://github.com/FEX-Emu/xbyak into FEX-Emu-extended_features 898f78ca3 Merge branch 'kariya-mitsuru-use-sh' 0b7f1411c Merge branch 'use-sh' of https://github.com/kariya-mitsuru/xbyak into kariya-mitsuru-use-sh 99e2b13b2 Fixes extended feature support checking b0a43c7e5 Use sh instead of tcsh for test scripts 87e8f41ae remove warning of _MSC_VER git-subtree-dir: externals/xbyak git-subtree-split: 590c10e3746978dbfcf102d6da933ac2659e4544
2021-03-27 21:08:22 +00:00
code.setProtectModeRW();
}
/*
displayFamily displayModel
Opteron 2376 10 4
Core2 Duo T7100 6 F
Core i3-2120T 6 2A
Core i7-2600 6 2A
Xeon X5650 6 2C
Core i7-3517 6 3A
Core i7-3930K 6 2D
*/
cpu.putFamily();
for (unsigned int i = 0; i < cpu.getDataCacheLevels(); i++) {
printf("cache level=%u data cache size=%u cores sharing data cache=%u\n", i, cpu.getDataCacheSize(i), cpu.getCoresSharingDataCache(i));
}
printf("SmtLevel =%u\n", cpu.getNumCores(Xbyak::util::SmtLevel));
printf("CoreLevel=%u\n", cpu.getNumCores(Xbyak::util::CoreLevel));
}
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
int main(int argc, char *argv[])
{
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
bool onlyCpuidFeature = argc == 2 && strcmp(argv[1], "-cpuid") == 0;
if (!onlyCpuidFeature) {
#ifdef XBYAK32
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
puts("32bit");
#else
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
puts("64bit");
#endif
Squashed 'externals/xbyak/' changes from 590c10e37..9357732aa 9357732aa v6.06 b161a3eb7 update changelog e5453b064 Merge branch 'dev' 2a265d9d9 memfd: keep file descriptor open during allocation lifetime 31ff018ed replace unsigned int with uint32_t in xbyak_util.h e427b2231 move Type into Cpu 8cf41063b refactoring Cpu 66d62968d add -cpuid to test_util cf7cb744c add comments 028112949 add detection of clzero c88007b03 update doc 4cb2e77a9 v6.052 015c27cf6 Merge branch 'dev' d808f9ecb add test of Cpu::has b48a7bb1b add operator== to Type 1a90f456c v6.051 96cb1d660 update changelog 1f5a77f56 Merge branch 'dev' 87e14f02a add test with noexception 30144f809 fix error when XBYAK_NO_EXCEPTION is defined ec15751df Merge branch 'dev' 4831b3fb3 v6.05 9ddf251f3 remove debug code 905b31bab fix typo 72d1ac118 add movdir64b a6665996b add detection of movdir64b 92ddc6dfd remove Type::operator<<() because it's ambiguous 9cdd40f5e add detection of movdiri 379f8bf37 add movdiri 0ad6db138 fix cldemote test for 32-bit 84ab46bb3 add cldemote to Cpu a84ddc12d support cldemote 3a6cc626e add clwb 38c40c02e detection of clflushopt c061ac839 avoid unnecessary replacement in readme.md 095ebbff1 extend Cpu::Type to 128 bit 3ea8e45d3 Merge branch 'dev' f7bfc2634 v6.041 ab4e52d67 update doc 2bef54399 include intrin.h on mingw 621ed0775 Merge branch 'dev' 4f5893e1e memfd_create: disable for ANDROID_API < 30 684d69db0 Merge branch 'dev' ea88b6d85 disable warning on mingw 7e8923fa5 add colon 9914216bd Merge branch 'dev' b335602ff [skip ci] tweak doc 25fbb3996 tweak doc 122054dc4 Formatted Supported OS Section d4fa7e46b Reworked Authors Section 9e4b64a74 Adjusted Spacing ff9fdb45f Use Github Sponsor Widget 893b31d46 Added Quicklinks 2d2adf78b Added License Badge 335b5941b Formatted Header 70603addf Moved Install / Usage Into Dedicated Files 1659d28fe Moved History Into Dedicated File fb953284b Merge branch 'dev' dbd96b277 add news 898c354e6 v6.04 f8e2ad1e9 add waitpkg detection to Cpu a220fd69a add umwait 64ec053e6 add umonitor 764d54f6f add tpause c68646e8d remove warning of vc 4e8214ca2 Merge branch 'dev' 360f4b673 test badSSE only for 32-bit mode a9fddc454 fix typo of readme 250b5dc39 fix typo of readme c46e92756 Merge branch 'dev' 31b7cd350 v6.03 a2f9ed085 rename isValidXMm to isValidSSE 2bc8fcbd3 add tests to badSSE 6de93fb88 add baseSSE test e2eda384c update doc 71a7b1773 fix condition to throw error for SSE instructions when using XMM16-XMM31 615b665cc sample/memfd shows /proc/self/maps 2861517f2 add memfd sample 507b0285e apt update at first 452c07f77 typedef for no-MmapAllocator 8af6e2026 minimize diff 0af3b5d07 Allocator: take optional name parameter and use it with memfd a67e24505 Merge branch 'dev' b3892c15e Merge pull request #138 from Tachi107/make-cxx-cpp-ld-flags b4eddaced build(make): honour CXXFLAGS, CPPFLAGS and LDFLAGS fbe60e590 test generates only a.asm 0a4a7571d Merge branch 'patch-1' of https://github.com/Tachi107/xbyak into Tachi107-patch-1 55b9f131b build(make): fix clean target in test/Makefile 7aef3ff54 Merge branch 'dev' 82e0deb8a v6.02 4d9906a94 fix condition to throw error for invalid displacements c79311a51 fix test_util.cpp 9b2c175b3 Merge branch 'dev' 06d797e33 Allow parallel feature checks 2a85bba3f Merge branch 'dev' 8d5af80a6 v6.01 df39606fe update doc 08f11817c supprt retf 1abfc3465 support call(mem, T_FAR) fb158f901 support jmp(mem, T_FAR) 9be47ceb2 Merge branch 'lioncash-hlt' into dev 3162eb16f add test of hlt bb55725a9 xbyak: Add hlt opcode function 47cf85fdb fix conflict b29e471ea build(meson): fix CMake Config file include dir 2cc21925f delete the sentences translated into Japanese from COPYRIGHT dca3930de remove tabs cecd204a5 Merge pull request #129 from Tachi107/meson-cmake-config 345de8a54 build(meson): generate CMake package config files e831805cc revert change of the type of Pack::util::operator[] fc9d953e5 util::Pack has not pointer but instance of Reg64 0868c54a9 use _WIN32 instead of _MSC_VER for mingw64 894a1b14a use original uint8_t dfc079ca1 add cstrs of Xbyak::util::Pack for 11 or 12 args 06e8f531f Merge branch 'Tachi107-meson' into dev ef90b6bd2 Makefile updates the version of meson.build 0000938f5 build: add Meson support This allows Meson users to use xbyak more easly, while it also provides a pkg-config file generator, useful to Linux distributions 757e4063f v6.00 b3489f548 add vcvtusi2sh 16d9898ab add vcvtsi2sh cfc03cb8f unify T_66, T_F3, T_F2 flags 02fa7057d add vcvttph2qq 4e72a9dc4 add vcvttsh2usi 05d08e05b add vcvttsh2si 621e6548c add vcvtsh2usi 34abda5c5 extend vcvtps2ph facd622b2 add vcvtw2ph 270af1cb2 add vcvtuw2ph 17dc697cd add vcvttph2w 62f022aea vcvttph2uw 836346bfd add vcvtph2w 300edb37b add vcvtph2uw 737904b5a add vcvtuqq2ph 52b2ebf18 add vcvtqq2ph 6761f1e05 add vcvtpd2ph 03f95b7e3 add vcvtudq2ph 64430b2bb add vcvtps2phx 88e426aa4 add vcvtdq2ph bf28a94a5 add vcvttph2uqq 4c4e665d3 add vcvtph2uqq 2b0099b63 add vcvtph2qq 3ff69a474 add vcvtph2pd 678b52956 add vcvttph2udq 72a5717e4 add vcvttph2dq 524d52bf6 add vcvtph2udq d1cf4db97 add vcvtph2psx fccd2c49b add vcvtph2dq 6530f4099 refactor gen-cvt c51e16156 tweak ed9f6c72a add vcvtsh2si ac1407bd1 add vcvtss2sh 2958a19bb add vcvtsh2ss 10d683303 add vcvtsh2sd 3920c950c add vcvtsd2sh 9a1b73932 add vmovw d86e4882f vmovsh xmm, addr 61f85a204 add vmovsh 847166cef add tests of vgetmant{ph,sh} c11a21cf4 add vgetmantph 55ab361f0 add tests of vgetexp{ph,sh} 8653f4152 add vgetexpsh 697eeb627 add vgetexpph ee920a991 add vfpclasssh 7aed436e6 add vfpclassph 56dca14e4 v5.997 b3b1e4e3c fix vrndscale* to support {sae} 681077eb1 add vrndscalesh 2f14eae85 add vrndscaleph f96870a44 add vreducesh 043c94ae9 add vreduceph 37bf3bb49 add vscalefsh c16f91c59 add vscalefph 61ad45935 add vsqrtsh e00b508d5 add vsqrtph 52765d54f add vrsqrtsh 2ec6a7ab4 add vrsqrtph b1ff7891d add vrcpph, vrcpsh 4f543ca0e add vucomish 412b95f02 add vf{,c}mulcph 9fc53baed add vf{,c}maddcph 0098ce98d add vf{,n}m{sub,add}sh 849dffb10 add vfmadd, vfnmadd, vfnmsub for avx512-fp16 eadb93d0b add vfmsubaddcph 9b8802cba add vfmaddsub{132,213,231}ph ab9481b4c add vcomish cd036ea17 fix vcmpsh b494b321a vcmpsh supports ptr_b eb2d63c83 vcmpph uses T_B16 a480b3dd9 v5.996 16d18b1d4 fix v{add,sub,mul,...}{sd,ss} to support T_rd_sae etc. 66c6ca1ab support vaddsh with T_rd_sae 6333ec099 add m16bcst 84053c8e7 add vcmpph 5df23d263 move FP16 to AVX-512 d5c7336f8 fix disp scaling of v{add,sub,mul,div,max,min}sh ebf29542d add vaddsh test f29689d02 add test of vaddph 2c4b6ac16 add v{add,sub,mul,div,min,max}{ph,sh} edf3c2f6f remove mask for mmm 2c561aad6 add T_MAP5 and T_MAP6 acd360c38 add Cpu::tAVX512_FP16 1554f479c remove unused flags(tSSE4a and tSSE5) of Cpu c313a8758 update CMakeLists.txt version 740b39e24 Merge pull request #122 from abouvier/cmake 10a1e5759 v5.995 0a557a099 rename XBYAK_MEMFD_CREATE to XBYAK_USE_MEMFD 0ad9b9bbe Merge branch 'captain5050-master' into dev c7bb66383 fix for mac and enable it if XBYAK_MEMFD_CREATE is defined c1e6569f1 fix cmake config files ccd4130ec Name mmap pages on Linux with memfd_create 2fb843c32 v5.994 413a66b44 add alias of vcmpXX{ps,pd,ss,sd} for mask register 6f4f76890 v5.993 19043cb9a add test for gather/scatter b5acb1d1c gather test does not generate bad combination of regs 67ec1674a check restriction of gather/scatter regs ea9814f4f check bad reg combination of gather a34850b2d add endbr32 and endbr64 git-subtree-dir: externals/xbyak git-subtree-split: 9357732aa2aa3cf97809027596dfa5c61d1515b2
2022-06-05 13:31:49 +01:00
}
putCPUinfo(onlyCpuidFeature);
}