test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
xor eax, eax
- mov al, BYTE [esi+ecx]
+ mov al, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
xor edx, edx
- mov dx, WORD [esi+ecx]
+ mov dx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
test cl, SIZEOF_DWORD
jz short .column_ld8
sub ecx, byte SIZEOF_DWORD
- movd mmG, DWORD [esi+ecx]
+ movd mmG, dword [esi+ecx]
psllq mmA, DWORD_BIT
por mmA, mmG
.column_ld8:
test cl, SIZEOF_MMWORD/8
jz short .column_ld2
sub ecx, byte SIZEOF_MMWORD/8
- movd mmA, DWORD [esi+ecx*RGB_PIXELSIZE]
+ movd mmA, dword [esi+ecx*RGB_PIXELSIZE]
.column_ld2:
test cl, SIZEOF_MMWORD/4
jz short .column_ld4
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
xor eax, eax
- mov al, BYTE [esi+ecx]
+ mov al, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
xor edx, edx
- mov dx, WORD [esi+ecx]
+ mov dx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
test cl, SIZEOF_DWORD
jz short .column_ld8
sub ecx, byte SIZEOF_DWORD
- movd mmG, DWORD [esi+ecx]
+ movd mmG, dword [esi+ecx]
psllq mmA, DWORD_BIT
por mmA, mmG
.column_ld8:
test cl, SIZEOF_MMWORD/8
jz short .column_ld2
sub ecx, byte SIZEOF_MMWORD/8
- movd mmA, DWORD [esi+ecx*RGB_PIXELSIZE]
+ movd mmA, dword [esi+ecx*RGB_PIXELSIZE]
.column_ld2:
test cl, SIZEOF_MMWORD/4
jz short .column_ld4
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
push ebp
mov esi, POINTER [eax+8] ; (working_state *state)
- mov put_buffer, DWORD [esi+8] ; put_buffer = state->cur.put_buffer;
- mov put_bits, DWORD [esi+12] ; put_bits = state->cur.put_bits;
+ mov put_buffer, dword [esi+8] ; put_buffer = state->cur.put_buffer;
+ mov put_bits, dword [esi+12] ; put_bits = state->cur.put_bits;
push esi ; esi is now scratch
get_GOT edx ; get GOT address
; Encode the DC coefficient difference per section F.1.2.1
mov esi, POINTER [esp+block] ; block
movsx ecx, word [esi] ; temp = temp2 = block[0] - last_dc_val;
- sub ecx, DWORD [eax+20]
+ sub ecx, dword [eax+20]
mov esi, ecx
; This is a well-known technique for obtaining the absolute value
; For a negative input, want temp2 = bitwise complement of abs(input)
; This code assumes we are on a two's complement machine
add esi, edx ; temp2 += temp3;
- mov DWORD [esp+temp], esi ; backup temp2 in temp
+ mov dword [esp+temp], esi ; backup temp2 in temp
; Find the number of bits needed for the magnitude of the coefficient
movpic ebp, POINTER [esp+gotptr] ; load GOT address (ebp)
movzx edx, byte [GOTOFF(ebp, jpeg_nbits_table + ecx)] ; nbits = JPEG_NBITS(temp);
- mov DWORD [esp+temp2], edx ; backup nbits in temp2
+ mov dword [esp+temp2], edx ; backup nbits in temp2
; Emit the Huffman-coded symbol for the number of bits
mov ebp, POINTER [eax+24] ; After this point, arguments are not accessible anymore
movzx ecx, byte [ebp + edx + 1024] ; size = dctbl->ehufsi[nbits];
EMIT_BITS eax ; EMIT_BITS(code, size)
- mov ecx, DWORD [esp+temp2] ; restore nbits
+ mov ecx, dword [esp+temp2] ; restore nbits
; Mask off any extra bits in code
mov eax, 1
shl eax, cl
dec eax
- and eax, DWORD [esp+temp] ; temp2 &= (((JLONG)1)<<nbits) - 1;
+ and eax, dword [esp+temp] ; temp2 &= (((JLONG)1)<<nbits) - 1;
; Emit that number of bits of the value, if positive,
; or the complement of its magnitude, if negative.
jz near .ELOOP
lea esi, [esi+ecx*2] ; k += r;
shr edx, cl ; index >>= r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
.BRLOOP:
cmp ecx, 16 ; while (r > 15) {
jl near .ERLOOP
sub ecx, 16 ; r -= 16;
- mov DWORD [esp+temp], ecx
+ mov dword [esp+temp], ecx
mov eax, INT [ebp + 240 * 4] ; code_0xf0 = actbl->ehufco[0xf0];
movzx ecx, byte [ebp + 1024 + 240] ; size_0xf0 = actbl->ehufsi[0xf0];
EMIT_BITS eax ; EMIT_BITS(code_0xf0, size_0xf0)
- mov ecx, DWORD [esp+temp]
+ mov ecx, dword [esp+temp]
jmp .BRLOOP
.ERLOOP:
movsx eax, word [esi] ; temp = t1[k];
movpic edx, POINTER [esp+gotptr] ; load GOT address (edx)
movzx eax, byte [GOTOFF(edx, jpeg_nbits_table + eax)] ; nbits = JPEG_NBITS(temp);
- mov DWORD [esp+temp2], eax
+ mov dword [esp+temp2], eax
; Emit Huffman symbol for run length / number of bits
shl ecx, 4 ; temp3 = (r << 4) + nbits;
add ecx, eax
movsx edx, word [esi+DCTSIZE2*2] ; temp2 = t2[k];
; Mask off any extra bits in code
- mov ecx, DWORD [esp+temp2]
+ mov ecx, dword [esp+temp2]
mov eax, 1
shl eax, cl
dec eax
and eax, edx ; temp2 &= (((JLONG)1)<<nbits) - 1;
EMIT_BITS eax ; PUT_BITS(temp2, nbits)
- mov edx, DWORD [esp+temp3]
+ mov edx, dword [esp+temp3]
add esi, 2 ; ++k;
shr edx, 1 ; index >>= 1;
shr edx, cl ; index >>= r;
add ecx, eax
lea esi, [esi+ecx*2] ; k += r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
jmp .BRLOOP2
.BLOOP2:
bsf ecx, edx ; r = __builtin_ctzl(index);
jz near .ELOOP2
lea esi, [esi+ecx*2] ; k += r;
shr edx, cl ; index >>= r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
.BRLOOP2:
cmp ecx, 16 ; while (r > 15) {
jl near .ERLOOP2
sub ecx, 16 ; r -= 16;
- mov DWORD [esp+temp], ecx
+ mov dword [esp+temp], ecx
mov eax, INT [ebp + 240 * 4] ; code_0xf0 = actbl->ehufco[0xf0];
movzx ecx, byte [ebp + 1024 + 240] ; size_0xf0 = actbl->ehufsi[0xf0];
EMIT_BITS eax ; EMIT_BITS(code_0xf0, size_0xf0)
- mov ecx, DWORD [esp+temp]
+ mov ecx, dword [esp+temp]
jmp .BRLOOP2
.ERLOOP2:
movsx eax, word [esi] ; temp = t1[k];
bsr eax, eax ; nbits = 32 - __builtin_clz(temp);
inc eax
- mov DWORD [esp+temp2], eax
+ mov dword [esp+temp2], eax
; Emit Huffman symbol for run length / number of bits
shl ecx, 4 ; temp3 = (r << 4) + nbits;
add ecx, eax
movsx edx, word [esi+DCTSIZE2*2] ; temp2 = t2[k];
; Mask off any extra bits in code
- mov ecx, DWORD [esp+temp2]
+ mov ecx, dword [esp+temp2]
mov eax, 1
shl eax, cl
dec eax
and eax, edx ; temp2 &= (((JLONG)1)<<nbits) - 1;
EMIT_BITS eax ; PUT_BITS(temp2, nbits)
- mov edx, DWORD [esp+temp3]
+ mov edx, dword [esp+temp3]
add esi, 2 ; ++k;
shr edx, 1 ; index >>= 1;
mov eax, [esp+buffer]
pop esi
; Save put_buffer & put_bits
- mov DWORD [esi+8], put_buffer ; state->cur.put_buffer = put_buffer;
- mov DWORD [esi+12], put_bits ; state->cur.put_bits = put_bits;
+ mov dword [esi+8], put_buffer ; state->cur.put_buffer = put_buffer;
+ mov dword [esi+12], put_bits ; state->cur.put_bits = put_bits;
pop ebp
pop edi
vmovd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
movd eax, mmA
cmp ecx, byte SIZEOF_DWORD
jb short .column_st2
- mov DWORD [edi+0*SIZEOF_DWORD], eax
+ mov dword [edi+0*SIZEOF_DWORD], eax
psrlq mmA, DWORD_BIT
movd eax, mmA
sub ecx, byte SIZEOF_DWORD
.column_st2:
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi+0*SIZEOF_WORD], ax
+ mov word [edi+0*SIZEOF_WORD], ax
shr eax, WORD_BIT
sub ecx, byte SIZEOF_WORD
add edi, byte SIZEOF_WORD
.column_st1:
cmp ecx, byte SIZEOF_BYTE
jb short .nextrow
- mov BYTE [edi+0*SIZEOF_BYTE], al
+ mov byte [edi+0*SIZEOF_BYTE], al
%else ; RGB_PIXELSIZE == 4 ; -----------
.column_st4:
cmp ecx, byte SIZEOF_MMWORD/8
jb short .nextrow
- movd DWORD [edi+0*SIZEOF_DWORD], mmA
+ movd dword [edi+0*SIZEOF_DWORD], mmA
%endif ; RGB_PIXELSIZE ; ---------------
movd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
vmovd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
movd eax, mmA
cmp ecx, byte SIZEOF_DWORD
jb short .column_st2
- mov DWORD [edi+0*SIZEOF_DWORD], eax
+ mov dword [edi+0*SIZEOF_DWORD], eax
psrlq mmA, DWORD_BIT
movd eax, mmA
sub ecx, byte SIZEOF_DWORD
.column_st2:
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi+0*SIZEOF_WORD], ax
+ mov word [edi+0*SIZEOF_WORD], ax
shr eax, WORD_BIT
sub ecx, byte SIZEOF_WORD
add edi, byte SIZEOF_WORD
.column_st1:
cmp ecx, byte SIZEOF_BYTE
jb short .endcolumn
- mov BYTE [edi+0*SIZEOF_BYTE], al
+ mov byte [edi+0*SIZEOF_BYTE], al
%else ; RGB_PIXELSIZE == 4 ; -----------
.column_st4:
cmp ecx, byte SIZEOF_MMWORD/8
jb short .endcolumn
- movd DWORD [edi+0*SIZEOF_DWORD], mmA
+ movd dword [edi+0*SIZEOF_DWORD], mmA
%endif ; RGB_PIXELSIZE ; ---------------
movd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_3DNOW
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
pushpic ebx ; save GOT address
- mov ebx, DWORD [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
- mov eax, DWORD [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
- or ebx, DWORD [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
- or ebx, DWORD [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
+ mov ebx, dword [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
+ or ebx, dword [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
+ or ebx, dword [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
or eax, ebx
poppic ebx ; restore GOT address
jnz short .columnDCT
; -- AC terms all zero
- movd mm0, DWORD [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
+ movd mm0, dword [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
punpcklwd mm0, mm0
psrad mm0, (DWORD_BIT-WORD_BIT)
; -- Even part
- movd mm0, DWORD [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
- movd mm1, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
- movd mm2, DWORD [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
- movd mm3, DWORD [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
+ movd mm0, dword [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
+ movd mm1, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ movd mm2, dword [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
+ movd mm3, dword [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
punpcklwd mm0, mm0
punpcklwd mm1, mm1
; -- Odd part
- movd mm2, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- movd mm3, DWORD [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
- movd mm5, DWORD [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
- movd mm1, DWORD [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
+ movd mm2, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ movd mm3, dword [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
+ movd mm5, dword [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
+ movd mm1, dword [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
punpcklwd mm2, mm2
punpcklwd mm3, mm3
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq xmm1, XMM_MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_IFAST_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_IFAST_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_AVX2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_4X4_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+2*SIZEOF_JSAMPROW]
- movd DWORD [edx+eax*SIZEOF_JSAMPLE], mm1
- movd DWORD [esi+eax*SIZEOF_JSAMPLE], mm0
+ movd dword [edx+eax*SIZEOF_JSAMPLE], mm1
+ movd dword [esi+eax*SIZEOF_JSAMPLE], mm0
psrlq mm1, 4*BYTE_BIT
psrlq mm0, 4*BYTE_BIT
mov edx, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+3*SIZEOF_JSAMPROW]
- movd DWORD [edx+eax*SIZEOF_JSAMPLE], mm1
- movd DWORD [esi+eax*SIZEOF_JSAMPLE], mm0
+ movd dword [edx+eax*SIZEOF_JSAMPLE], mm1
+ movd dword [esi+eax*SIZEOF_JSAMPLE], mm0
emms ; empty MMX state
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
- mov WORD [edx+eax*SIZEOF_JSAMPLE], bx
- mov WORD [esi+eax*SIZEOF_JSAMPLE], cx
+ mov word [edx+eax*SIZEOF_JSAMPLE], bx
+ mov word [esi+eax*SIZEOF_JSAMPLE], cx
emms ; empty MMX state
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_4X4_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
- mov WORD [edx+eax*SIZEOF_JSAMPLE], bx
- mov WORD [esi+eax*SIZEOF_JSAMPLE], cx
+ mov word [edx+eax*SIZEOF_JSAMPLE], bx
+ mov word [esi+eax*SIZEOF_JSAMPLE], cx
pop edi
pop esi
%define XMM_DWORD
%define XMM_MMWORD
-%define SIZEOF_BYTE 1 ; sizeof(BYTE)
-%define SIZEOF_WORD 2 ; sizeof(WORD)
-%define SIZEOF_DWORD 4 ; sizeof(DWORD)
-%define SIZEOF_QWORD 8 ; sizeof(QWORD)
-%define SIZEOF_OWORD 16 ; sizeof(OWORD)
-%define SIZEOF_YWORD 32 ; sizeof(YWORD)
+%define SIZEOF_BYTE 1 ; sizeof(byte)
+%define SIZEOF_WORD 2 ; sizeof(word)
+%define SIZEOF_DWORD 4 ; sizeof(dword)
+%define SIZEOF_QWORD 8 ; sizeof(qword)
+%define SIZEOF_OWORD 16 ; sizeof(oword)
+%define SIZEOF_YWORD 32 ; sizeof(yword)
%define BYTE_BIT 8 ; CHAR_BIT in C
-%define WORD_BIT 16 ; sizeof(WORD)*BYTE_BIT
-%define DWORD_BIT 32 ; sizeof(DWORD)*BYTE_BIT
-%define QWORD_BIT 64 ; sizeof(QWORD)*BYTE_BIT
-%define OWORD_BIT 128 ; sizeof(OWORD)*BYTE_BIT
-%define YWORD_BIT 256 ; sizeof(YWORD)*BYTE_BIT
+%define WORD_BIT 16 ; sizeof(word)*BYTE_BIT
+%define DWORD_BIT 32 ; sizeof(dword)*BYTE_BIT
+%define QWORD_BIT 64 ; sizeof(qword)*BYTE_BIT
+%define OWORD_BIT 128 ; sizeof(oword)*BYTE_BIT
+%define YWORD_BIT 256 ; sizeof(yword)*BYTE_BIT
; --------------------------------------------------------------------------
; External Symbol Name
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
mov buffer, r11 ; r11 is now sratch
mov put_buffer, MMWORD [r10+16] ; put_buffer = state->cur.put_buffer;
- mov put_bits, DWORD [r10+24] ; put_bits = state->cur.put_bits;
+ mov put_bits, dword [r10+24] ; put_bits = state->cur.put_bits;
push r10 ; r10 is now scratch
; Encode the DC coefficient difference per section F.1.2.1
pop r10
; Save put_buffer & put_bits
mov MMWORD [r10+16], put_buffer ; state->cur.put_buffer = put_buffer;
- mov DWORD [r10+24], put_bits ; state->cur.put_bits = put_bits;
+ mov dword [r10+24], put_bits ; state->cur.put_bits = put_bits;
pop rbx
uncollect_args 6
vmovd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
movd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
vmovd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
movd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
mov rcx, DCTSIZE/4 ; ctr
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq xmm1, XMM_MMWORD [MMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_IFAST_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
; ---- Pass 1: process columns.
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_AVX2
- mov eax, DWORD [DWBLOCK(1,0,r11,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,r11,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,r11,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,r11,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,r11,SIZEOF_JCOEF)]
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_4X4_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz short .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
mov rdx, JSAMPROW [rdi+0*SIZEOF_JSAMPROW]
mov rsi, JSAMPROW [rdi+1*SIZEOF_JSAMPROW]
- mov WORD [rdx+rax*SIZEOF_JSAMPLE], bx
- mov WORD [rsi+rax*SIZEOF_JSAMPLE], cx
+ mov word [rdx+rax*SIZEOF_JSAMPLE], bx
+ mov word [rsi+rax*SIZEOF_JSAMPLE], cx
pop rbx
uncollect_args 4