INIT_MMX mmx
; void ff_h264_idct_add_8_mmx(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct_add_8, 3, 3, 0
+ movsxdifnidn r2, r2d
IDCT4_ADD r0, r1, r2
RET
INIT_MMX mmx
; void ff_h264_idct8_add_8_mmx(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_add_8, 3, 4, 0
+ movsxdifnidn r2, r2d
%assign pad 128+4-(stack_offset&7)
SUB rsp, pad
INIT_XMM sse2
; void ff_h264_idct8_add_8_sse2(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_add_8, 3, 4, 10
+ movsxdifnidn r2, r2d
IDCT8_ADD_SSE r0, r1, r2, r3
RET
; void ff_h264_idct_dc_add_8_mmxext(uint8_t *dst, int16_t *block, int stride)
%if ARCH_X86_64
cglobal h264_idct_dc_add_8, 3, 4, 0
+ movsxd r2, r2d
movsx r3, word [r1]
mov dword [r1], 0
DC_ADD_MMXEXT_INIT r3, r2
; void ff_h264_idct8_dc_add_8_mmxext(uint8_t *dst, int16_t *block, int stride)
cglobal h264_idct8_dc_add_8, 3, 4, 0
+ movsxd r2, r2d
movsx r3, word [r1]
mov dword [r1], 0
DC_ADD_MMXEXT_INIT r3, r2
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16_8, 5, 7 + npicregs, 0, dst, block_offset, block, stride, nnzc, cntr, coeff, picreg
+ movsxdifnidn r3, r3d
xor r5, r5
%ifdef PIC
lea picregq, [scan8_mem]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct8_add4_8, 5, 7 + npicregs, 0, dst, block_offset, block, stride, nnzc, cntr, coeff, picreg
+ movsxdifnidn r3, r3d
%assign pad 128+4-(stack_offset&7)
SUB rsp, pad
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
+ movsxdifnidn r3, r3d
xor r5, r5
%ifdef PIC
lea picregq, [scan8_mem]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16intra_8, 5, 7 + npicregs, 0, dst, block_offset, block, stride, nnzc, cntr, coeff, picreg
+ movsxdifnidn r3, r3d
xor r5, r5
%ifdef PIC
lea picregq, [scan8_mem]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16intra_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
+ movsxdifnidn r3, r3d
xor r5, r5
%ifdef PIC
lea picregq, [scan8_mem]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct8_add4_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
+ movsxdifnidn r3, r3d
%assign pad 128+4-(stack_offset&7)
SUB rsp, pad
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct8_add4_8, 5, 8 + npicregs, 10, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
+ movsxdifnidn r3, r3d
xor r5, r5
%ifdef PIC
lea picregq, [scan8_mem]
INIT_MMX mmx
h264_idct_add8_mmx_plane:
+ movsxdifnidn r3, r3d
.nextblock:
movzx r6, byte [scan8+r5]
movzx r6, byte [r4+r6]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add8_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
+ movsxdifnidn r3, r3d
mov r5, 16
add r2, 512
%ifdef PIC
RET
h264_idct_add8_mmxext_plane:
+ movsxdifnidn r3, r3d
.nextblock:
movzx r6, byte [scan8+r5]
movzx r6, byte [r4+r6]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add8_8, 5, 8 + npicregs, 0, dst1, block_offset, block, stride, nnzc, cntr, coeff, dst2, picreg
+ movsxdifnidn r3, r3d
mov r5, 16
add r2, 512
%if ARCH_X86_64
; r0 = uint8_t *dst, r2 = int16_t *block, r3 = int stride, r6=clobbered
h264_idct_dc_add8_mmxext:
+ movsxdifnidn r3, r3d
movd m0, [r2 ] ; 0 0 X D
mov word [r2+ 0], 0
punpcklwd m0, [r2+32] ; x X d D
INIT_XMM sse2
; r0 = uint8_t *dst (clobbered), r2 = int16_t *block, r3 = int stride
h264_add8x4_idct_sse2:
+ movsxdifnidn r3, r3d
movq m0, [r2+ 0]
movq m1, [r2+ 8]
movq m2, [r2+16]
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16_8, 5, 5 + ARCH_X86_64, 8
+ movsxdifnidn r3, r3d
%if ARCH_X86_64
mov r5, r0
%endif
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add16intra_8, 5, 7 + ARCH_X86_64, 8
+ movsxdifnidn r3, r3d
%if ARCH_X86_64
mov r7, r0
%endif
; int16_t *block, int stride,
; const uint8_t nnzc[6 * 8])
cglobal h264_idct_add8_8, 5, 7 + ARCH_X86_64, 8
+ movsxdifnidn r3, r3d
add r2, 512
%if ARCH_X86_64
mov r7, r0