From 8dd3ee9dddcaf1d538252d77dd2af3ea139f4f96 Mon Sep 17 00:00:00 2001 From: Henrik Gramner Date: Fri, 4 Mar 2016 17:51:41 +0100 Subject: x86inc: Fix AVX emulation of scalar float instructions Those instructions are not commutative since they only change the first element in the vector and leave the rest unmodified. --- libavutil/x86/x86inc.asm | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'libavutil') diff --git a/libavutil/x86/x86inc.asm b/libavutil/x86/x86inc.asm index 3a0a2612ba..22608eae69 100644 --- a/libavutil/x86/x86inc.asm +++ b/libavutil/x86/x86inc.asm @@ -1194,8 +1194,8 @@ INIT_XMM ; Non-destructive instructions are written without parameters AVX_INSTR addpd, sse2, 1, 0, 1 AVX_INSTR addps, sse, 1, 0, 1 -AVX_INSTR addsd, sse2, 1, 0, 1 -AVX_INSTR addss, sse, 1, 0, 1 +AVX_INSTR addsd, sse2, 1, 0, 0 +AVX_INSTR addss, sse, 1, 0, 0 AVX_INSTR addsubpd, sse3, 1, 0, 0 AVX_INSTR addsubps, sse3, 1, 0, 0 AVX_INSTR aesdec, aesni, 0, 0, 0 @@ -1225,10 +1225,10 @@ AVX_INSTR cvtpd2ps, sse2 AVX_INSTR cvtps2dq, sse2 AVX_INSTR cvtps2pd, sse2 AVX_INSTR cvtsd2si, sse2 -AVX_INSTR cvtsd2ss, sse2 -AVX_INSTR cvtsi2sd, sse2 -AVX_INSTR cvtsi2ss, sse -AVX_INSTR cvtss2sd, sse2 +AVX_INSTR cvtsd2ss, sse2, 1, 0, 0 +AVX_INSTR cvtsi2sd, sse2, 1, 0, 0 +AVX_INSTR cvtsi2ss, sse, 1, 0, 0 +AVX_INSTR cvtss2sd, sse2, 1, 0, 0 AVX_INSTR cvtss2si, sse AVX_INSTR cvttpd2dq, sse2 AVX_INSTR cvttps2dq, sse2 @@ -1251,12 +1251,12 @@ AVX_INSTR ldmxcsr, sse AVX_INSTR maskmovdqu, sse2 AVX_INSTR maxpd, sse2, 1, 0, 1 AVX_INSTR maxps, sse, 1, 0, 1 -AVX_INSTR maxsd, sse2, 1, 0, 1 -AVX_INSTR maxss, sse, 1, 0, 1 +AVX_INSTR maxsd, sse2, 1, 0, 0 +AVX_INSTR maxss, sse, 1, 0, 0 AVX_INSTR minpd, sse2, 1, 0, 1 AVX_INSTR minps, sse, 1, 0, 1 -AVX_INSTR minsd, sse2, 1, 0, 1 -AVX_INSTR minss, sse, 1, 0, 1 +AVX_INSTR minsd, sse2, 1, 0, 0 +AVX_INSTR minss, sse, 1, 0, 0 AVX_INSTR movapd, sse2 AVX_INSTR movaps, sse AVX_INSTR movd, mmx @@ -1285,8 +1285,8 @@ AVX_INSTR movups, sse AVX_INSTR mpsadbw, sse4 AVX_INSTR mulpd, sse2, 1, 0, 1 AVX_INSTR mulps, sse, 1, 0, 1 -AVX_INSTR mulsd, sse2, 1, 0, 1 -AVX_INSTR mulss, sse, 1, 0, 1 +AVX_INSTR mulsd, sse2, 1, 0, 0 +AVX_INSTR mulss, sse, 1, 0, 0 AVX_INSTR orpd, sse2, 1, 0, 1 AVX_INSTR orps, sse, 1, 0, 1 AVX_INSTR pabsb, ssse3 @@ -1414,8 +1414,8 @@ AVX_INSTR rcpps, sse, 1, 0, 0 AVX_INSTR rcpss, sse, 1, 0, 0 AVX_INSTR roundpd, sse4 AVX_INSTR roundps, sse4 -AVX_INSTR roundsd, sse4 -AVX_INSTR roundss, sse4 +AVX_INSTR roundsd, sse4, 1, 1, 0 +AVX_INSTR roundss, sse4, 1, 1, 0 AVX_INSTR rsqrtps, sse, 1, 0, 0 AVX_INSTR rsqrtss, sse, 1, 0, 0 AVX_INSTR shufpd, sse2, 1, 1, 0 -- cgit v1.2.3