On the day of Saturday 23 February 2008 Uros Bizjak hast written: > Hello! > > > f7: 0f 7f 5c 24 f0 movq %mm3,-0x10(%rsp) > > fc: 0f 7f 54 24 f8 movq %mm2,-0x8(%rsp) > > 101: 48 8b 5c 24 f8 mov -0x8(%rsp),%rbx > > 106: 48 89 5c 38 40 mov %rbx,0x40(%rax,%rdi,1) > > 10b: 48 8b 5c 24 f0 mov -0x10(%rsp),%rbx > > 110: 48 89 5c 38 48 mov %rbx,0x48(%rax,%rdi,1) > > > > As you see in the intrinsic version gcc moves to mmx register to the > > stack, reloads from the stack and writes to the destination. Why? > > > > I don't know whether earlier gcc 4.2 versions produced such stupid code. > > Compiling as 32 does similar stupidity, though gcc reloads into a mmx > > register... > > This is a variant of "Strange code for MMX register moves" [1] or its > dupe "mmx and movd/movq on x86_64" [2]. Since touching %mm register > switches x87 register stack to MMX mode, we penalize mmx moves severely > in order to prevent gcc to ever allocate %mm for DImode moves, unless > really necessary.
[...]
Just as a side note. The equivalent SSE2 code looks fine, but I have question
regarding the used store instruction:
#include <emmintrin.h>
void diff_pixels_mmx4(char *block, const uint8_t *s1, const uint8_t *s2, long
stride)
{
long offset = -128;
block+=64;
__m128i mm7 = _mm_setzero_si128();
do {
__m128i mm0 = *(__m128i*)s1;
__m128i mm2 = *(__m128i*)s2;
__m128i mm1 = mm0;
__m128i mm3 = mm2;
mm0 = _mm_unpacklo_epi8(mm0, mm7);
mm1 = _mm_unpackhi_epi8(mm1, mm7);
mm2 = _mm_unpacklo_epi8(mm2, mm7);
mm3 = _mm_unpackhi_epi8(mm3, mm7);
mm0 = _mm_sub_epi16(mm0, mm2);
mm1 = _mm_sub_epi16(mm1, mm3);
*(__m128i*)(block+offset) = mm0;
*(__m128i*)(block+offset+16) = mm1;
s1 += stride;
s2 += stride;
offset +=32;
} while (offset < 0);
}
generated assembly (-O2 -march=k8):
0000000000000050 <diff_pixels_mmx4>:
50: 66 0f ef e4 pxor %xmm4,%xmm4
54: 48 c7 c0 80 ff ff ff mov $0xffffffffffffff80,%rax
5b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
60: 66 0f 6f 0e movdqa (%rsi),%xmm1
64: 48 01 ce add %rcx,%rsi
67: 66 0f 6f 02 movdqa (%rdx),%xmm0
6b: 48 01 ca add %rcx,%rdx
6e: 66 0f 6f d1 movdqa %xmm1,%xmm2
72: 66 0f 6f d8 movdqa %xmm0,%xmm3
76: 66 0f 68 cc punpckhbw %xmm4,%xmm1
7a: 66 0f 60 d4 punpcklbw %xmm4,%xmm2
7e: 66 0f 60 dc punpcklbw %xmm4,%xmm3
82: 66 0f 68 c4 punpckhbw %xmm4,%xmm0
86: 66 0f f9 d3 psubw %xmm3,%xmm2
8a: 0f 29 54 38 40 movaps %xmm2,0x40(%rax,%rdi,1)
8f: 66 0f f9 c8 psubw %xmm0,%xmm1
93: 0f 29 4c 38 50 movaps %xmm1,0x50(%rax,%rdi,1)
98: 48 83 c0 20 add $0x20,%rax
9c: 75 c2 jne 60 <diff_pixels_mmx4+0x10>
9e: f3 c3 repz retq
Why is movaps (SSE, floating point data) instead of movdqa (SSE2. integer
data) used as store? Bug or feature? Even with -O0 compiled it is used.
Regards,
--
(°= =°)
//\ Prakash Punnoor /\\
V_/ \_V
signature.asc
Description: This is a digitally signed message part.
