diff --git a/src/backend/x64/emit_x64_vector.cpp b/src/backend/x64/emit_x64_vector.cpp index 9ca8f0d2..f5fc6ee0 100644 --- a/src/backend/x64/emit_x64_vector.cpp +++ b/src/backend/x64/emit_x64_vector.cpp @@ -439,6 +439,14 @@ void EmitX64::EmitVectorAnd(EmitContext& ctx, IR::Inst* inst) { } static void ArithmeticShiftRightByte(EmitContext& ctx, BlockOfCode& code, const Xbyak::Xmm& result, u8 shift_amount) { + if (code.HasAVX512_Icelake()) { + // Do a logical shift right upon the 8x8 bit-matrix, but shift in + // `0x80` bytes into the matrix to repeat the most significant bit. + const u64 zero_extend = ~(~0ull << (shift_amount)) & 0x8080808080808080; + const u64 shift_matrix = (0x0102040810204080 >> (shift_amount * 8)) | zero_extend; + code.vgf2p8affineqb(result, result, code.MConst(xword_b, shift_matrix), 0); + return; + } const Xbyak::Xmm tmp = ctx.reg_alloc.ScratchXmm(); code.punpckhbw(tmp, result);