1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
|
cf. <https://github.com/libjpeg-turbo/libjpeg-turbo/commit/
8b2c04f774d18e05e321ee67a9a38b4d7e84f168> "Fix x86-64 ABI conformance issue in
SIMD code":
--- simd/jcclrss2-64.asm
+++ simd/jcclrss2-64.asm
@@ -50,14 +50,14 @@
collect_args
push rbx
- mov rcx, r10
+ mov ecx, r10d
test rcx,rcx
jz near .return
push rcx
mov rsi, r12
- mov rcx, r13
+ mov ecx, r13d
mov rdi, JSAMPARRAY [rsi+0*SIZEOF_JSAMPARRAY]
mov rbx, JSAMPARRAY [rsi+1*SIZEOF_JSAMPARRAY]
mov rdx, JSAMPARRAY [rsi+2*SIZEOF_JSAMPARRAY]
--- simd/jcgryss2-64.asm
+++ simd/jcgryss2-64.asm
@@ -50,14 +50,14 @@
collect_args
push rbx
- mov rcx, r10
+ mov ecx, r10d
test rcx,rcx
jz near .return
push rcx
mov rsi, r12
- mov rcx, r13
+ mov ecx, r13d
mov rdi, JSAMPARRAY [rsi+0*SIZEOF_JSAMPARRAY]
lea rdi, [rdi+rcx*SIZEOF_JSAMPROW]
--- simd/jcqnts2f-64.asm
+++ simd/jcqnts2f-64.asm
@@ -50,7 +50,7 @@
packsswb xmm7,xmm7 ; xmm7 = PB_CENTERJSAMPLE (0x808080..)
mov rsi, r10
- mov rax, r11
+ mov eax, r11d
mov rdi, r12
mov rcx, DCTSIZE/2
.convloop:
--- simd/jcqnts2i-64.asm
+++ simd/jcqnts2i-64.asm
@@ -50,7 +50,7 @@
psllw xmm7,7 ; xmm7={0xFF80 0xFF80 0xFF80 0xFF80 ..}
mov rsi, r10
- mov rax, r11
+ mov eax, r11d
mov rdi, r12
mov rcx, DCTSIZE/4
.convloop:
--- simd/jcsamss2-64.asm
+++ simd/jcsamss2-64.asm
@@ -49,11 +49,11 @@
mov rbp,rsp
collect_args
- mov rcx, r13
+ mov ecx, r13d
shl rcx,3 ; imul rcx,DCTSIZE (rcx = output_cols)
jz near .return
- mov rdx, r10
+ mov edx, r10d
; -- expand_right_edge
@@ -90,7 +90,7 @@
; -- h2v1_downsample
- mov rax, r12 ; rowctr
+ mov eax, r12d ; rowctr
test eax,eax
jle near .return
@@ -193,11 +193,11 @@
mov rbp,rsp
collect_args
- mov rcx, r13
+ mov rcx, r13
shl rcx,3 ; imul rcx,DCTSIZE (rcx = output_cols)
jz near .return
- mov rdx, r10
+ mov edx, r10d
; -- expand_right_edge
@@ -234,7 +234,7 @@
; -- h2v2_downsample
- mov rax, r12 ; rowctr
+ mov eax, r12d ; rowctr
test rax,rax
jle near .return
--- simd/jdclrss2-64.asm
+++ simd/jdclrss2-64.asm
@@ -52,14 +52,14 @@
collect_args
push rbx
- mov rcx, r10 ; num_cols
+ mov ecx, r10d ; num_cols
test rcx,rcx
jz near .return
push rcx
mov rdi, r11
- mov rcx, r12
+ mov ecx, r12d
mov rsi, JSAMPARRAY [rdi+0*SIZEOF_JSAMPARRAY]
mov rbx, JSAMPARRAY [rdi+1*SIZEOF_JSAMPARRAY]
mov rdx, JSAMPARRAY [rdi+2*SIZEOF_JSAMPARRAY]
--- simd/jdmrgss2-64.asm
+++ simd/jdmrgss2-64.asm
@@ -52,14 +52,14 @@
collect_args
push rbx
- mov rcx, r10 ; col
+ mov ecx, r10d ; col
test rcx,rcx
jz near .return
push rcx
mov rdi, r11
- mov rcx, r12
+ mov ecx, r12d
mov rsi, JSAMPARRAY [rdi+0*SIZEOF_JSAMPARRAY]
mov rbx, JSAMPARRAY [rdi+1*SIZEOF_JSAMPARRAY]
mov rdx, JSAMPARRAY [rdi+2*SIZEOF_JSAMPARRAY]
@@ -455,10 +455,10 @@
collect_args
push rbx
- mov rax, r10
+ mov eax, r10d
mov rdi, r11
- mov rcx, r12
+ mov ecx, r12d
mov rsi, JSAMPARRAY [rdi+0*SIZEOF_JSAMPARRAY]
mov rbx, JSAMPARRAY [rdi+1*SIZEOF_JSAMPARRAY]
mov rdx, JSAMPARRAY [rdi+2*SIZEOF_JSAMPARRAY]
--- simd/jdsamss2-64.asm
+++ simd/jdsamss2-64.asm
@@ -67,7 +67,7 @@
mov rbp,rsp
collect_args
- mov rax, r11 ; colctr
+ mov eax, r11d ; colctr
test rax,rax
jz near .return
@@ -214,7 +214,7 @@
collect_args
push rbx
- mov rax, r11 ; colctr
+ mov eax, r11d ; colctr
test rax,rax
jz near .return
@@ -506,7 +506,7 @@
mov rbp,rsp
collect_args
- mov rdx, r11
+ mov edx, r11d
add rdx, byte (2*SIZEOF_XMMWORD)-1
and rdx, byte -(2*SIZEOF_XMMWORD)
jz near .return
@@ -596,7 +596,7 @@
collect_args
push rbx
- mov rdx, r11
+ mov edx, r11d
add rdx, byte (2*SIZEOF_XMMWORD)-1
and rdx, byte -(2*SIZEOF_XMMWORD)
jz near .return
--- simd/jiss2flt-64.asm
+++ simd/jiss2flt-64.asm
@@ -326,7 +326,7 @@
mov rax, [original_rbp]
lea rsi, [workspace] ; FAST_FLOAT * wsptr
mov rdi, r12 ; (JSAMPROW *)
- mov rax, r13
+ mov eax, r13d
mov rcx, DCTSIZE/4 ; ctr
.rowloop:
--- simd/jiss2fst-64.asm
+++ simd/jiss2fst-64.asm
@@ -323,7 +323,7 @@
mov rax, [original_rbp]
mov rdi, r12 ; (JSAMPROW *)
- mov rax, r13
+ mov eax, r13d
; -- Even part
--- simd/jiss2int-64.asm
+++ simd/jiss2int-64.asm
@@ -515,7 +515,7 @@
mov rax, [original_rbp]
mov rdi, r12 ; (JSAMPROW *)
- mov rax, r13
+ mov eax, r13d
; -- Even part
--- simd/jiss2red-64.asm
+++ simd/jiss2red-64.asm
@@ -312,7 +312,7 @@
mov rax, [original_rbp]
mov rdi, r12 ; (JSAMPROW *)
- mov rax, r13
+ mov eax, r13d
; -- Even part
@@ -521,7 +521,7 @@
; ---- Pass 2: process rows, store into output array.
mov rdi, r12 ; (JSAMPROW *)
- mov rax, r13
+ mov eax, r13d
; | input:| result:|
; | A0 B0 | |
|
