| /external/llvm/test/CodeGen/X86/ |
| vec_cmp_uint-128.ll | 19 ; SSE2-NEXT: pcmpeqd %xmm1, %xmm0
20 ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
21 ; SSE2-NEXT: pand %xmm1, %xmm0
26 ; SSE41-NEXT: pcmpeqq %xmm1, %xmm0
31 ; SSE42-NEXT: pcmpeqq %xmm1, %xmm0
36 ; AVX-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
41 ; XOP-NEXT: vpcomeqq %xmm1, %xmm0, %xmm0
51 ; SSE-NEXT: pcmpeqd %xmm1, %xmm0
56 ; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
61 ; XOP-NEXT: vpcomeqd %xmm1, %xmm0, %xmm
[all...] |
| vec_setcc.ll | 10 ; SSE2: pmaxub %xmm0, %xmm1
11 ; SSE2: pcmpeqb %xmm1, %xmm0
14 ; SSE41: pmaxub %xmm0, %xmm1
15 ; SSE41: pcmpeqb %xmm1, %xmm0
18 ; AVX: vpmaxub %xmm1, %xmm0, %xmm1
19 ; AVX: vpcmpeqb %xmm1, %xmm0, %xmm0
27 ; SSE2: pminub %xmm0, %xmm1
28 ; SSE2: pcmpeqb %xmm1, %xmm0
31 ; SSE41: pminub %xmm0, %xmm1
[all...] |
| vector-popcnt-128.ll | 12 ; SSE2-NEXT: movdqa %xmm0, %xmm1
13 ; SSE2-NEXT: psrlq $1, %xmm1
14 ; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
15 ; SSE2-NEXT: psubq %xmm1, %xmm0
16 ; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [3689348814741910323,3689348814741910323]
18 ; SSE2-NEXT: pand %xmm1, %xmm2
20 ; SSE2-NEXT: pand %xmm1, %xmm0
22 ; SSE2-NEXT: movdqa %xmm0, %xmm1
23 ; SSE2-NEXT: psrlq $4, %xmm1
24 ; SSE2-NEXT: paddq %xmm0, %xmm1
[all...] |
| vector-tzcnt-128.ll | 16 ; SSE2-NEXT: movd %rax, %xmm1
22 ; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
23 ; SSE2-NEXT: movdqa %xmm1, %xmm0
32 ; SSE3-NEXT: movd %rax, %xmm1
38 ; SSE3-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
39 ; SSE3-NEXT: movdqa %xmm1, %xmm0
48 ; SSSE3-NEXT: movd %rax, %xmm1
54 ; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0
[all...] |
| powi.ll | 7 ; CHECK-NEXT: movapd %xmm0, %xmm1
8 ; CHECK-NEXT: mulsd %xmm1, %xmm1
9 ; CHECK-NEXT: mulsd %xmm1, %xmm0
10 ; CHECK-NEXT: mulsd %xmm1, %xmm1
11 ; CHECK-NEXT: mulsd %xmm1, %xmm0
12 ; CHECK-NEXT: mulsd %xmm1, %xmm1
13 ; CHECK-NEXT: mulsd %xmm0, %xmm1
[all...] |
| vector-rotate-128.ll | 20 ; SSE2-NEXT: psubq %xmm1, %xmm2
21 ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,0,1]
25 ; SSE2-NEXT: psllq %xmm1, %xmm3
28 ; SSE2-NEXT: movdqa %xmm0, %xmm1
29 ; SSE2-NEXT: psrlq %xmm3, %xmm1
31 ; SSE2-NEXT: movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
32 ; SSE2-NEXT: orpd %xmm4, %xmm1
33 ; SSE2-NEXT: movapd %xmm1, %xmm0
39 ; SSE41-NEXT: psubq %xmm1, %xmm
[all...] |
| vec_ctbits.ll | 13 ; CHECK-NEXT: movd %rax, %xmm1
18 ; CHECK-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
19 ; CHECK-NEXT: movdqa %xmm1, %xmm0
31 ; CHECK-NEXT: movd %rax, %xmm1
37 ; CHECK-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
38 ; CHECK-NEXT: movdqa %xmm1, %xmm0
48 ; CHECK-NEXT: movdqa %xmm0, %xmm1
49 ; CHECK-NEXT: psrlq $1, %xmm1
[all...] |
| vector-shift-shl-128.ll | 19 ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,0,1]
22 ; SSE2-NEXT: psllq %xmm1, %xmm0
30 ; SSE41-NEXT: psllq %xmm1, %xmm2
31 ; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
32 ; SSE41-NEXT: psllq %xmm1, %xmm0
38 ; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm2
39 ; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
40 ; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm
[all...] |
| uint_to_fp-2.ll | 9 ; CHECK-NEXT: movd {{[0-9]+}}(%esp), %xmm1
10 ; CHECK-NEXT: orpd %xmm0, %xmm1
11 ; CHECK-NEXT: subsd %xmm0, %xmm1
13 ; CHECK-NEXT: cvtsd2ss %xmm1, %xmm0
28 ; CHECK-NEXT: xorps %xmm1, %xmm1
29 ; CHECK-NEXT: movss %xmm0, %xmm1
31 ; CHECK-NEXT: orps %xmm0, %xmm1
32 ; CHECK-NEXT: subsd %xmm0, %xmm1
34 ; CHECK-NEXT: cvtsd2ss %xmm1, %xmm
[all...] |
| vmovq.ll | 9 ; SSE-NEXT: movd %rax, %xmm1
10 ; SSE-NEXT: por %xmm1, %xmm0
11 ; SSE-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
12 ; SSE-NEXT: paddq %xmm1, %xmm0
18 ; AVX-NEXT: vmovq %rax, %xmm1
19 ; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
20 ; AVX-NEXT: vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
21 ; AVX-NEXT: vpaddq %xmm1, %xmm0, %xmm
[all...] |
| vec_int_to_fp.ll | 18 ; SSE-NEXT: cvtsi2sdq %rax, %xmm1
23 ; SSE-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
24 ; SSE-NEXT: movapd %xmm1, %xmm0
30 ; AVX-NEXT: vcvtsi2sdq %rax, %xmm0, %xmm1
34 ; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
172 ; SSE-NEXT: movd %xmm1, %rax
174 ; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
180 ; SSE-NEXT: movapd %xmm3, %xmm1
185 ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
[all...] |
| /external/v8/test/cctest/ |
| test-disasm-ia32.cc | 390 __ movaps(xmm0, xmm1);
392 __ cvtsd2ss(xmm0, xmm1);
396 __ andps(xmm0, xmm1);
398 __ orps(xmm0, xmm1);
400 __ xorps(xmm0, xmm1);
404 __ addss(xmm1, xmm0);
405 __ addss(xmm1, Operand(ebx, ecx, times_4, 10000));
406 __ mulss(xmm1, xmm0);
407 __ mulss(xmm1, Operand(ebx, ecx, times_4, 10000));
408 __ subss(xmm1, xmm0)
436 __ movsd(Operand(ebx, ecx, times_4, 10000), xmm1); local
[all...] |
| test-disasm-x64.cc | 385 __ cvttss2si(rdx, xmm1);
386 __ cvtsd2ss(xmm0, xmm1);
388 __ movaps(xmm0, xmm1);
391 __ andps(xmm0, xmm1);
393 __ orps(xmm0, xmm1);
395 __ xorps(xmm0, xmm1);
399 __ addss(xmm1, xmm0);
400 __ addss(xmm1, Operand(rbx, rcx, times_4, 10000));
401 __ mulss(xmm1, xmm0);
402 __ mulss(xmm1, Operand(rbx, rcx, times_4, 10000))
432 __ movsd(Operand(rbx, rcx, times_4, 10000), xmm1); local
516 __ vmovss(Operand(rbx, r9, times_4, 10000), xmm1); local
[all...] |
| /external/libvpx/libvpx/vp8/common/x86/ |
| postproc_sse2.asm | 18 movdqa xmm5, xmm1
22 psubusb xmm4, xmm1
23 psubusb xmm1, xmm0
26 paddusb xmm4, xmm1
31 pxor xmm1, xmm1
37 pcmpeqb xmm2, xmm1
38 pcmpeqb xmm7, xmm1
45 movdqa xmm2, xmm1
46 pavgb xmm1, xmm
[all...] |
| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp8/common/x86/ |
| postproc_sse2.asm | 18 movdqa xmm5, xmm1
22 psubusb xmm4, xmm1
23 psubusb xmm1, xmm0
26 paddusb xmm4, xmm1
31 pxor xmm1, xmm1
37 pcmpeqb xmm2, xmm1
38 pcmpeqb xmm7, xmm1
45 movdqa xmm2, xmm1
46 pavgb xmm1, xmm
[all...] |
| /external/llvm/test/MC/X86/ |
| x86-32-fma3.s | 3 // CHECK: vfmadd132pd %xmm2, %xmm5, %xmm1
5 vfmadd132pd %xmm2, %xmm5, %xmm1
7 // CHECK: vfmadd132pd (%eax), %xmm5, %xmm1
9 vfmadd132pd (%eax), %xmm5, %xmm1
11 // CHECK: vfmadd132ps %xmm2, %xmm5, %xmm1
13 vfmadd132ps %xmm2, %xmm5, %xmm1
15 // CHECK: vfmadd132ps (%eax), %xmm5, %xmm1
17 vfmadd132ps (%eax), %xmm5, %xmm1
19 // CHECK: vfmadd213pd %xmm2, %xmm5, %xmm1
21 vfmadd213pd %xmm2, %xmm5, %xmm1
[all...] |
| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp8/encoder/x86/ |
| quantize_ssse3.asm | 62 movdqa xmm1, xmm0
69 pabsw xmm1, xmm1
72 paddw xmm1, xmm2
76 pmulhw xmm1, [rdx]
83 movdqa xmm2, xmm1 ;store y for getting eob
86 pxor xmm1, xmm0
88 psubw xmm1, xmm0
91 movdqa [rax], xmm1
97 pmullw xmm0, xmm1
[all...] |
| /toolchain/binutils/binutils-2.25/gas/testsuite/gas/i386/ |
| arch-2.d | 9 [ ]*[a-f0-9]+: 66 0f 38 17 c1 ptest %xmm1,%xmm0
10 [ ]*[a-f0-9]+: 66 0f 3a 09 c1 00 roundpd \$0x0,%xmm1,%xmm0
11 [ ]*[a-f0-9]+: 66 0f 3a 08 c1 00 roundps \$0x0,%xmm1,%xmm0
12 [ ]*[a-f0-9]+: 66 0f 3a 0b c1 00 roundsd \$0x0,%xmm1,%xmm0
13 [ ]*[a-f0-9]+: 66 0f 3a 0a c1 00 roundss \$0x0,%xmm1,%xmm0
|
| arch-3.d | 9 [ ]*[a-f0-9]+: 66 0f 38 17 c1 ptest %xmm1,%xmm0
10 [ ]*[a-f0-9]+: 66 0f 3a 09 c1 00 roundpd \$0x0,%xmm1,%xmm0
11 [ ]*[a-f0-9]+: 66 0f 3a 08 c1 00 roundps \$0x0,%xmm1,%xmm0
12 [ ]*[a-f0-9]+: 66 0f 3a 0b c1 00 roundsd \$0x0,%xmm1,%xmm0
13 [ ]*[a-f0-9]+: 66 0f 3a 0a c1 00 roundss \$0x0,%xmm1,%xmm0
|
| sse4_2.s | 15 pcmpgtq %xmm1,%xmm0
17 pcmpestri $0x0,%xmm1,%xmm0
19 pcmpestrm $0x1,%xmm1,%xmm0
21 pcmpistri $0x2,%xmm1,%xmm0
23 pcmpistrm $0x3,%xmm1,%xmm0
45 pcmpgtq xmm0,xmm1
47 pcmpestri xmm0,xmm1,0x0
49 pcmpestrm xmm0,xmm1,0x1
51 pcmpistri xmm0,xmm1,0x2
53 pcmpistrm xmm0,xmm1,0x
[all...] |
| sha.d | 9 [ ]*[a-f0-9]+: 0f 3a cc ca 09 sha1rnds4 \$0x9,%xmm2,%xmm1
13 [ ]*[a-f0-9]+: 0f 38 c8 ca sha1nexte %xmm2,%xmm1
14 [ ]*[a-f0-9]+: 0f 38 c8 08 sha1nexte \(%eax\),%xmm1
15 [ ]*[a-f0-9]+: 0f 38 c8 48 12 sha1nexte 0x12\(%eax\),%xmm1
16 [ ]*[a-f0-9]+: 0f 38 c8 0c 58 sha1nexte \(%eax,%ebx,2\),%xmm1
17 [ ]*[a-f0-9]+: 0f 38 c9 ca sha1msg1 %xmm2,%xmm1
18 [ ]*[a-f0-9]+: 0f 38 c9 08 sha1msg1 \(%eax\),%xmm1
19 [ ]*[a-f0-9]+: 0f 38 c9 48 12 sha1msg1 0x12\(%eax\),%xmm1
20 [ ]*[a-f0-9]+: 0f 38 c9 0c 58 sha1msg1 \(%eax,%ebx,2\),%xmm1
21 [ ]*[a-f0-9]+: 0f 38 ca ca sha1msg2 %xmm2,%xmm1
[all...] |
| /external/libjpeg-turbo/simd/ |
| jfdctint-sse2-64.asm | 121 movdqa xmm1, XMMWORD [XMMBLOCK(1,0,rdx,SIZEOF_DCTELEM)]
126 ; xmm1=(10 11 12 13 14 15 16 17), xmm3=(30 31 32 33 34 35 36 37)
129 punpcklwd xmm0,xmm1 ; xmm0=(00 10 01 11 02 12 03 13)
130 punpckhwd xmm4,xmm1 ; xmm4=(04 14 05 15 06 16 07 17)
137 movdqa xmm1, XMMWORD [XMMBLOCK(6,0,rdx,SIZEOF_DCTELEM)]
140 ; xmm6=( 4 12 20 28 36 44 52 60), xmm1=( 6 14 22 30 38 46 54 62)
149 movdqa xmm5,xmm1 ; transpose coefficients(phase 1)
150 punpcklwd xmm1,xmm3 ; xmm1=(60 70 61 71 62 72 63 73)
154 punpckldq xmm6,xmm1 ; xmm6=(40 50 60 70 41 51 61 71
[all...] |
| jfdctint-sse2.asm | 127 movdqa xmm1, XMMWORD [XMMBLOCK(1,0,edx,SIZEOF_DCTELEM)]
132 ; xmm1=(10 11 12 13 14 15 16 17), xmm3=(30 31 32 33 34 35 36 37)
135 punpcklwd xmm0,xmm1 ; xmm0=(00 10 01 11 02 12 03 13)
136 punpckhwd xmm4,xmm1 ; xmm4=(04 14 05 15 06 16 07 17)
143 movdqa xmm1, XMMWORD [XMMBLOCK(6,0,edx,SIZEOF_DCTELEM)]
146 ; xmm6=( 4 12 20 28 36 44 52 60), xmm1=( 6 14 22 30 38 46 54 62)
155 movdqa xmm5,xmm1 ; transpose coefficients(phase 1)
156 punpcklwd xmm1,xmm3 ; xmm1=(60 70 61 71 62 72 63 73)
160 punpckldq xmm6,xmm1 ; xmm6=(40 50 60 70 41 51 61 71
[all...] |
| /external/libvpx/libvpx/third_party/libyuv/source/ |
| compare_gcc.cc | 28 "movdqu " MEMACCESS(0) ",%%xmm1 \n"
32 "movdqa %%xmm1,%%xmm3 \n"
33 "psubusb %%xmm2,%%xmm1 \n"
35 "por %%xmm2,%%xmm1 \n"
36 "movdqa %%xmm1,%%xmm2 \n"
37 "punpcklbw %%xmm5,%%xmm1 \n"
39 "pmaddwd %%xmm1,%%xmm1 \n"
41 "paddd %%xmm1,%%xmm0 \n"
46 "pshufd $0xee,%%xmm0,%%xmm1 \n
[all...] |
| /external/libyuv/files/source/ |
| compare_gcc.cc | 32 "movdqu " MEMACCESS(0) ",%%xmm1 \n"
36 "movdqa %%xmm1,%%xmm3 \n"
37 "psubusb %%xmm2,%%xmm1 \n"
39 "por %%xmm2,%%xmm1 \n"
40 "movdqa %%xmm1,%%xmm2 \n"
41 "punpcklbw %%xmm5,%%xmm1 \n"
43 "pmaddwd %%xmm1,%%xmm1 \n"
45 "paddd %%xmm1,%%xmm0 \n"
50 "pshufd $0xee,%%xmm0,%%xmm1 \n
[all...] |
