x86 SIMD: Consistify capitalization of NASM types
byte, word, dword, qword, oword, and yword are all assembler keywords,
so it makes sense to use lowercase for these so as not to mistake them
for macros or constants.
diff --git a/simd/i386/jccolext-avx2.asm b/simd/i386/jccolext-avx2.asm
index 11674d5..c46d684 100644
--- a/simd/i386/jccolext-avx2.asm
+++ b/simd/i386/jccolext-avx2.asm
@@ -108,12 +108,12 @@
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:
diff --git a/simd/i386/jccolext-mmx.asm b/simd/i386/jccolext-mmx.asm
index c18dbc4..6357a42 100644
--- a/simd/i386/jccolext-mmx.asm
+++ b/simd/i386/jccolext-mmx.asm
@@ -109,13 +109,13 @@
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:
@@ -125,7 +125,7 @@
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:
@@ -195,7 +195,7 @@
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
diff --git a/simd/i386/jccolext-sse2.asm b/simd/i386/jccolext-sse2.asm
index 06b02d5..c6c8085 100644
--- a/simd/i386/jccolext-sse2.asm
+++ b/simd/i386/jccolext-sse2.asm
@@ -107,12 +107,12 @@
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:
diff --git a/simd/i386/jcgryext-avx2.asm b/simd/i386/jcgryext-avx2.asm
index 5601a6a..3fa7973 100644
--- a/simd/i386/jcgryext-avx2.asm
+++ b/simd/i386/jcgryext-avx2.asm
@@ -100,12 +100,12 @@
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:
diff --git a/simd/i386/jcgryext-mmx.asm b/simd/i386/jcgryext-mmx.asm
index 727894f..8af42e5 100644
--- a/simd/i386/jcgryext-mmx.asm
+++ b/simd/i386/jcgryext-mmx.asm
@@ -101,13 +101,13 @@
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:
@@ -117,7 +117,7 @@
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:
@@ -187,7 +187,7 @@
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
diff --git a/simd/i386/jcgryext-sse2.asm b/simd/i386/jcgryext-sse2.asm
index 5b4559f..c9d6ff1 100644
--- a/simd/i386/jcgryext-sse2.asm
+++ b/simd/i386/jcgryext-sse2.asm
@@ -99,12 +99,12 @@
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:
diff --git a/simd/i386/jchuff-sse2.asm b/simd/i386/jchuff-sse2.asm
index 2b0b469..79f0ca5 100644
--- a/simd/i386/jchuff-sse2.asm
+++ b/simd/i386/jchuff-sse2.asm
@@ -195,8 +195,8 @@
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
@@ -212,7 +212,7 @@
; 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
@@ -227,12 +227,12 @@
; 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
@@ -240,13 +240,13 @@
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.
@@ -289,22 +289,22 @@
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
@@ -314,13 +314,13 @@
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;
@@ -350,29 +350,29 @@
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
@@ -382,13 +382,13 @@
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;
@@ -405,8 +405,8 @@
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
diff --git a/simd/i386/jdcolext-avx2.asm b/simd/i386/jdcolext-avx2.asm
index 66e2683..015be04 100644
--- a/simd/i386/jdcolext-avx2.asm
+++ b/simd/i386/jdcolext-avx2.asm
@@ -346,7 +346,7 @@
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
@@ -355,7 +355,7 @@
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/i386/jdcolext-mmx.asm b/simd/i386/jdcolext-mmx.asm
index 29b6dd4..5813cfc 100644
--- a/simd/i386/jdcolext-mmx.asm
+++ b/simd/i386/jdcolext-mmx.asm
@@ -278,7 +278,7 @@
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
@@ -286,14 +286,14 @@
.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 ; -----------
@@ -365,7 +365,7 @@
.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 ; ---------------
diff --git a/simd/i386/jdcolext-sse2.asm b/simd/i386/jdcolext-sse2.asm
index 73b37de..d5572b3 100644
--- a/simd/i386/jdcolext-sse2.asm
+++ b/simd/i386/jdcolext-sse2.asm
@@ -318,7 +318,7 @@
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
@@ -327,7 +327,7 @@
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/i386/jdmrgext-avx2.asm b/simd/i386/jdmrgext-avx2.asm
index 3512c50..e35f728 100644
--- a/simd/i386/jdmrgext-avx2.asm
+++ b/simd/i386/jdmrgext-avx2.asm
@@ -352,7 +352,7 @@
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
@@ -361,7 +361,7 @@
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/i386/jdmrgext-mmx.asm b/simd/i386/jdmrgext-mmx.asm
index dab5c32..eb3e36b 100644
--- a/simd/i386/jdmrgext-mmx.asm
+++ b/simd/i386/jdmrgext-mmx.asm
@@ -281,7 +281,7 @@
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
@@ -289,14 +289,14 @@
.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 ; -----------
@@ -371,7 +371,7 @@
.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 ; ---------------
diff --git a/simd/i386/jdmrgext-sse2.asm b/simd/i386/jdmrgext-sse2.asm
index 91295ff..c113dc4 100644
--- a/simd/i386/jdmrgext-sse2.asm
+++ b/simd/i386/jdmrgext-sse2.asm
@@ -323,7 +323,7 @@
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
@@ -332,7 +332,7 @@
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/i386/jidctflt-3dn.asm b/simd/i386/jidctflt-3dn.asm
index 396f36a..8795191 100644
--- a/simd/i386/jidctflt-3dn.asm
+++ b/simd/i386/jidctflt-3dn.asm
@@ -90,23 +90,23 @@
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)
@@ -133,10 +133,10 @@
; -- 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
@@ -180,10 +180,10 @@
; -- 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
diff --git a/simd/i386/jidctflt-sse.asm b/simd/i386/jidctflt-sse.asm
index 6236fd5..b27ecfd 100644
--- a/simd/i386/jidctflt-sse.asm
+++ b/simd/i386/jidctflt-sse.asm
@@ -100,8 +100,8 @@
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)]
diff --git a/simd/i386/jidctflt-sse2.asm b/simd/i386/jidctflt-sse2.asm
index 0b38937..c646eae 100644
--- a/simd/i386/jidctflt-sse2.asm
+++ b/simd/i386/jidctflt-sse2.asm
@@ -100,8 +100,8 @@
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)]
diff --git a/simd/i386/jidctfst-mmx.asm b/simd/i386/jidctfst-mmx.asm
index c69bffa..24622d4 100644
--- a/simd/i386/jidctfst-mmx.asm
+++ b/simd/i386/jidctfst-mmx.asm
@@ -121,8 +121,8 @@
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)]
diff --git a/simd/i386/jidctfst-sse2.asm b/simd/i386/jidctfst-sse2.asm
index 03bac9d..19704ff 100644
--- a/simd/i386/jidctfst-sse2.asm
+++ b/simd/i386/jidctfst-sse2.asm
@@ -116,8 +116,8 @@
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)]
diff --git a/simd/i386/jidctint-avx2.asm b/simd/i386/jidctint-avx2.asm
index 1e94541..c371985 100644
--- a/simd/i386/jidctint-avx2.asm
+++ b/simd/i386/jidctint-avx2.asm
@@ -318,8 +318,8 @@
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)]
diff --git a/simd/i386/jidctint-mmx.asm b/simd/i386/jidctint-mmx.asm
index 281e5b3..4f07f56 100644
--- a/simd/i386/jidctint-mmx.asm
+++ b/simd/i386/jidctint-mmx.asm
@@ -134,8 +134,8 @@
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)]
diff --git a/simd/i386/jidctint-sse2.asm b/simd/i386/jidctint-sse2.asm
index acb1140..e442fdd 100644
--- a/simd/i386/jidctint-sse2.asm
+++ b/simd/i386/jidctint-sse2.asm
@@ -129,8 +129,8 @@
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)]
diff --git a/simd/i386/jidctred-mmx.asm b/simd/i386/jidctred-mmx.asm
index ad3fcb1..e2307e1 100644
--- a/simd/i386/jidctred-mmx.asm
+++ b/simd/i386/jidctred-mmx.asm
@@ -142,8 +142,8 @@
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)]
@@ -462,16 +462,16 @@
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
@@ -686,8 +686,8 @@
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
diff --git a/simd/i386/jidctred-sse2.asm b/simd/i386/jidctred-sse2.asm
index c00d0e4..6e56494 100644
--- a/simd/i386/jidctred-sse2.asm
+++ b/simd/i386/jidctred-sse2.asm
@@ -137,8 +137,8 @@
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)]
@@ -576,8 +576,8 @@
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
diff --git a/simd/nasm/jsimdext.inc b/simd/nasm/jsimdext.inc
index 383b709..11fe8ef 100644
--- a/simd/nasm/jsimdext.inc
+++ b/simd/nasm/jsimdext.inc
@@ -165,19 +165,19 @@
%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
diff --git a/simd/x86_64/jccolext-avx2.asm b/simd/x86_64/jccolext-avx2.asm
index 61f3b9e..10d2834 100644
--- a/simd/x86_64/jccolext-avx2.asm
+++ b/simd/x86_64/jccolext-avx2.asm
@@ -94,12 +94,12 @@
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:
diff --git a/simd/x86_64/jccolext-sse2.asm b/simd/x86_64/jccolext-sse2.asm
index 9df4f7f..2c914d3 100644
--- a/simd/x86_64/jccolext-sse2.asm
+++ b/simd/x86_64/jccolext-sse2.asm
@@ -93,12 +93,12 @@
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:
diff --git a/simd/x86_64/jcgryext-avx2.asm b/simd/x86_64/jcgryext-avx2.asm
index 20c48c1..175b60d 100644
--- a/simd/x86_64/jcgryext-avx2.asm
+++ b/simd/x86_64/jcgryext-avx2.asm
@@ -86,12 +86,12 @@
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:
diff --git a/simd/x86_64/jcgryext-sse2.asm b/simd/x86_64/jcgryext-sse2.asm
index 70e6891..873be80 100644
--- a/simd/x86_64/jcgryext-sse2.asm
+++ b/simd/x86_64/jcgryext-sse2.asm
@@ -85,12 +85,12 @@
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:
diff --git a/simd/x86_64/jchuff-sse2.asm b/simd/x86_64/jchuff-sse2.asm
index d49be5b..aa78fd5 100644
--- a/simd/x86_64/jchuff-sse2.asm
+++ b/simd/x86_64/jchuff-sse2.asm
@@ -198,7 +198,7 @@
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
@@ -331,7 +331,7 @@
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
diff --git a/simd/x86_64/jdcolext-avx2.asm b/simd/x86_64/jdcolext-avx2.asm
index 4b43baa..677b8ed 100644
--- a/simd/x86_64/jdcolext-avx2.asm
+++ b/simd/x86_64/jdcolext-avx2.asm
@@ -332,7 +332,7 @@
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
@@ -341,7 +341,7 @@
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/x86_64/jdcolext-sse2.asm b/simd/x86_64/jdcolext-sse2.asm
index e5bd0ee..071aa62 100644
--- a/simd/x86_64/jdcolext-sse2.asm
+++ b/simd/x86_64/jdcolext-sse2.asm
@@ -304,7 +304,7 @@
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
@@ -313,7 +313,7 @@
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/x86_64/jdmrgext-avx2.asm b/simd/x86_64/jdmrgext-avx2.asm
index 666d2ca..bb733c5 100644
--- a/simd/x86_64/jdmrgext-avx2.asm
+++ b/simd/x86_64/jdmrgext-avx2.asm
@@ -337,7 +337,7 @@
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
@@ -346,7 +346,7 @@
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/x86_64/jdmrgext-sse2.asm b/simd/x86_64/jdmrgext-sse2.asm
index 4fa69af..b176a4c 100644
--- a/simd/x86_64/jdmrgext-sse2.asm
+++ b/simd/x86_64/jdmrgext-sse2.asm
@@ -308,7 +308,7 @@
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
@@ -317,7 +317,7 @@
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
diff --git a/simd/x86_64/jidctflt-sse2.asm b/simd/x86_64/jidctflt-sse2.asm
index 95aff82..ab95e1a 100644
--- a/simd/x86_64/jidctflt-sse2.asm
+++ b/simd/x86_64/jidctflt-sse2.asm
@@ -93,8 +93,8 @@
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)]
diff --git a/simd/x86_64/jidctfst-sse2.asm b/simd/x86_64/jidctfst-sse2.asm
index 03ca13f..a66a681 100644
--- a/simd/x86_64/jidctfst-sse2.asm
+++ b/simd/x86_64/jidctfst-sse2.asm
@@ -109,8 +109,8 @@
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)]
diff --git a/simd/x86_64/jidctint-avx2.asm b/simd/x86_64/jidctint-avx2.asm
index b36cb31..50270f4 100644
--- a/simd/x86_64/jidctint-avx2.asm
+++ b/simd/x86_64/jidctint-avx2.asm
@@ -290,8 +290,8 @@
; ---- 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)]
diff --git a/simd/x86_64/jidctint-sse2.asm b/simd/x86_64/jidctint-sse2.asm
index 0f52a6e..034530c 100644
--- a/simd/x86_64/jidctint-sse2.asm
+++ b/simd/x86_64/jidctint-sse2.asm
@@ -122,8 +122,8 @@
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)]
diff --git a/simd/x86_64/jidctred-sse2.asm b/simd/x86_64/jidctred-sse2.asm
index 133a59a..7fbfcc5 100644
--- a/simd/x86_64/jidctred-sse2.asm
+++ b/simd/x86_64/jidctred-sse2.asm
@@ -130,8 +130,8 @@
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)]
@@ -560,8 +560,8 @@
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