x86/dsputil: fix VECTOR_CLIP_INT32 macro
The inline loop was incrementing and using the value of %%i
the wrong way.
Disassembly of ff_vector_clip_int32_sse2 before and after
this patch:
movdqa (%rdx),%xmm0 | movdqa (%rdx),%xmm0
movdqa 0x10(%rdx),%xmm1 | movdqa 0x10(%rdx),%xmm1
movdqa 0x20(%rdx),%xmm2 | movdqa 0x20(%rdx),%xmm2
movdqa 0x30(%rdx),%xmm3 | movdqa 0x30(%rdx),%xmm3
[...] |
movdqa %xmm0,(%rcx) | movdqa %xmm0,(%rcx)
movdqa %xmm1,0x10(%rcx) | movdqa %xmm1,0x10(%rcx)
movdqa %xmm2,0x20(%rcx) | movdqa %xmm2,0x20(%rcx)
movdqa %xmm3,0x30(%rcx) | movdqa %xmm3,0x30(%rcx)
movdqa (%rdx),%xmm0 | movdqa 0x40(%rdx),%xmm0
movdqa 0x20(%rdx),%xmm1 | movdqa 0x50(%rdx),%xmm1
movdqa 0x40(%rdx),%xmm2 | movdqa 0x60(%rdx),%xmm2
movdqa 0x60(%rdx),%xmm3 | movdqa 0x70(%rdx),%xmm3
[...] |
movdqa %xmm0,(%rcx) | movdqa %xmm0,0x40(%rcx)
movdqa %xmm1,0x20(%rcx) | movdqa %xmm1,0x50(%rcx)
movdqa %xmm2,0x40(%rcx) | movdqa %xmm2,0x60(%rcx)
movdqa %xmm3,0x60(%rcx) | movdqa %xmm3,0x70(%rcx)
add $0x80,%rdx | add $0x80,%rdx
add $0x80,%rcx | add $0x80,%rcx
Other versions were unaffected.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
James Almer