4a6fac8a update version to 5.77
801cf3fd cosmetic change of getNumCores
d397e824 fix number of cores that share LLC cache
a669e092 support non-intel-cpu visual studio
af5f422e Merge branch 'fenghaitao-guard_x86' into develop
9b98dc17 Guard x86 specific codes with "#if defined(__i386__) || defined(__x86_64__)"
dd4173e1 move some member variables input private
f72646a7 update version
4612528f format change
4b95e862 Merge branch 'shelleygoel-master'
4c262fa6 add functionality to get num of cores using x2APIC ID
bc70e7e1 recover Xbyak::CastTo
d09a230f unlink Label when LabelManager is destroyed
973e8597 update version
afdb9fe9 Xbyak::CastTo is removed
b011aca4 add RegRip +/- int
acae93cd increase max temp regs for StackFrame
ea4e3562 util::StackFrame uses push/pop instead of mov
42462ef9 use evex encoding for vpslld/vpslldq/vpsraw/...(reg, mem, imm);
da9117a9 update version of readme.md
d35f4fb7 fix the encoding of vinsertps for disp8N
1de435ed bf uses Label class
613922bd add Label L() for convenience
43e15583 fix typo
93579ee6 add protect-re.cpp
60004b5c fix url of protect-re.cpp
348b2709 fix typo of doc
f34f6ed5 update manual
232110be update test
82b78bf0 add setProtectMode
dd8b290f put warning message if pageSize != 4096
64775ca2 a little refactoring
7c3e7b85 fix wrong VSIB encoding with idx >= 16
git-subtree-dir: externals/xbyak
git-subtree-split: 4a6fac8ade404f667b94170f713367fe7da2a852
Like FCVTN, now that we have half-precision floating point conversion
functions available, we can go ahead and use those to eliminate the
interpreter fallback.
This is supposed to call FPUnpackBase instead of FPUnpack. This would
result in alternate half-precision representations being misinterpreted
when it comes to dealing with NaNs.
Avoids potentially clobbering the intended sign bit value during
conversions to double-precision values. The other conversion types are
already properly handled, so those don't need to be addressed.
This just transfers values between vector registers and general-purpose
registers with no conversions performed, so this is trivial to add
support for half-precision to.
Corresponds to the equivalent pseudocode within the ARMv8 reference
manual. This will be necessary for supporting half-precision
floating-point.
This also makes use of it within FPConvert
This function is defined as always disabling the AHP bit in the fpcr
before performing any operations.
At the same time, rename the original FPUnpack function to FPUnpackBase
to match the pseudocode in the ARM reference manual.
This corrects one case where floating-point exceptions could be set when
they're not supposed to be.
This also corrects a case where values were being treated as NaNs when
they weren't supposed to be.
