Home
last modified time | relevance | path

Searched refs:xmm0 (Results 1 – 25 of 1989) sorted by relevance

12345678910>>...80

/external/swiftshader/third_party/llvm-7.0/llvm/test/MC/X86/
Dx86_64-fma4-encoding.s6 vfmaddss (%rcx), %xmm1, %xmm0, %xmm0
10 vfmaddss %xmm1, (%rcx),%xmm0, %xmm0
14 vfmaddss %xmm2, %xmm1, %xmm0, %xmm0
18 vfmaddsd (%rcx), %xmm1, %xmm0, %xmm0
22 vfmaddsd %xmm1, (%rcx),%xmm0, %xmm0
26 vfmaddsd %xmm2, %xmm1, %xmm0, %xmm0
30 vfmaddsd %xmm10, %xmm1, %xmm0, %xmm0
34 vfmaddps (%rcx), %xmm1, %xmm0, %xmm0
38 vfmaddps %xmm1, (%rcx),%xmm0, %xmm0
42 vfmaddps %xmm2, %xmm1, %xmm0, %xmm0
[all …]
/external/llvm/test/MC/X86/
Dx86_64-fma4-encoding.s6 vfmaddss (%rcx), %xmm1, %xmm0, %xmm0
10 vfmaddss %xmm1, (%rcx),%xmm0, %xmm0
14 vfmaddss %xmm2, %xmm1, %xmm0, %xmm0
18 vfmaddsd (%rcx), %xmm1, %xmm0, %xmm0
22 vfmaddsd %xmm1, (%rcx),%xmm0, %xmm0
26 vfmaddsd %xmm2, %xmm1, %xmm0, %xmm0
30 vfmaddsd %xmm10, %xmm1, %xmm0, %xmm0
34 vfmaddps (%rcx), %xmm1, %xmm0, %xmm0
38 vfmaddps %xmm1, (%rcx),%xmm0, %xmm0
42 vfmaddps %xmm2, %xmm1, %xmm0, %xmm0
[all …]
/external/capstone/suite/MC/X86/
Dx86_64-fma4-encoding.s.cs2 0xc4,0xe3,0xf9,0x6a,0x01,0x10 = vfmaddss (%rcx), %xmm1, %xmm0, %xmm0
3 0xc4,0xe3,0x79,0x6a,0x01,0x10 = vfmaddss %xmm1, (%rcx), %xmm0, %xmm0
4 0xc4,0xe3,0xf9,0x6a,0xc2,0x10 = vfmaddss %xmm2, %xmm1, %xmm0, %xmm0
5 0xc4,0xe3,0xf9,0x6b,0x01,0x10 = vfmaddsd (%rcx), %xmm1, %xmm0, %xmm0
6 0xc4,0xe3,0x79,0x6b,0x01,0x10 = vfmaddsd %xmm1, (%rcx), %xmm0, %xmm0
7 0xc4,0xe3,0xf9,0x6b,0xc2,0x10 = vfmaddsd %xmm2, %xmm1, %xmm0, %xmm0
8 0xc4,0xc3,0xf9,0x6b,0xc2,0x10 = vfmaddsd %xmm10, %xmm1, %xmm0, %xmm0
9 0xc4,0xe3,0xf9,0x68,0x01,0x10 = vfmaddps (%rcx), %xmm1, %xmm0, %xmm0
10 0xc4,0xe3,0x79,0x68,0x01,0x10 = vfmaddps %xmm1, (%rcx), %xmm0, %xmm0
11 0xc4,0xe3,0xf9,0x68,0xc2,0x10 = vfmaddps %xmm2, %xmm1, %xmm0, %xmm0
[all …]
/external/swiftshader/third_party/llvm-7.0/llvm/test/CodeGen/X86/
Dbuild-vector-128.ll14 ; SSE-32-NEXT: movups {{[0-9]+}}(%esp), %xmm0
19 ; SSE-64-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
24 ; AVX-32-NEXT: vmovups {{[0-9]+}}(%esp), %xmm0
29 ; AVX-64-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
39 ; SSE-32-NEXT: movups {{[0-9]+}}(%esp), %xmm0
45 ; SSE2-64-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
46 ; SSE2-64-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
51 ; SSE41-64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
52 ; SSE41-64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
53 ; SSE41-64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[0]
[all …]
Dslow-pmulld.ll23 ; CHECK32-NEXT: pand {{\.LCPI.*}}, %xmm0
24 ; CHECK32-NEXT: pmaddwd {{\.LCPI.*}}, %xmm0
29 ; CHECK64-NEXT: pand {{.*}}(%rip), %xmm0
30 ; CHECK64-NEXT: pmaddwd {{.*}}(%rip), %xmm0
35 ; SSE4-32-NEXT: pand {{\.LCPI.*}}, %xmm0
36 ; SSE4-32-NEXT: pmaddwd {{\.LCPI.*}}, %xmm0
41 ; SSE4-64-NEXT: pand {{.*}}(%rip), %xmm0
42 ; SSE4-64-NEXT: pmaddwd {{.*}}(%rip), %xmm0
47 ; AVX2-32-NEXT: vpand {{\.LCPI.*}}, %xmm0, %xmm0
48 ; AVX2-32-NEXT: vpmaddwd {{\.LCPI.*}}, %xmm0, %xmm0
[all …]
Dvector-tzcnt-128.ll23 ; SSE2-NEXT: psubq %xmm0, %xmm2
24 ; SSE2-NEXT: pand %xmm0, %xmm2
27 ; SSE2-NEXT: movdqa %xmm3, %xmm0
28 ; SSE2-NEXT: psrlq $1, %xmm0
29 ; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
30 ; SSE2-NEXT: psubq %xmm0, %xmm3
31 ; SSE2-NEXT: movdqa {{.*#+}} xmm0 = [3689348814741910323,3689348814741910323]
33 ; SSE2-NEXT: pand %xmm0, %xmm2
35 ; SSE2-NEXT: pand %xmm0, %xmm3
37 ; SSE2-NEXT: movdqa %xmm3, %xmm0
[all …]
Dvector-popcnt-128.ll16 ; SSE2-NEXT: movdqa %xmm0, %xmm1
19 ; SSE2-NEXT: psubq %xmm1, %xmm0
21 ; SSE2-NEXT: movdqa %xmm0, %xmm2
23 ; SSE2-NEXT: psrlq $2, %xmm0
24 ; SSE2-NEXT: pand %xmm1, %xmm0
25 ; SSE2-NEXT: paddq %xmm2, %xmm0
26 ; SSE2-NEXT: movdqa %xmm0, %xmm1
28 ; SSE2-NEXT: paddq %xmm0, %xmm1
30 ; SSE2-NEXT: pxor %xmm0, %xmm0
31 ; SSE2-NEXT: psadbw %xmm0, %xmm1
[all …]
Dvector-reduce-fmul.ll16 ; SSE2-NEXT: mulss %xmm1, %xmm0
18 ; SSE2-NEXT: mulss %xmm1, %xmm0
23 ; SSE41-NEXT: mulss %xmm1, %xmm0
25 ; SSE41-NEXT: mulss %xmm1, %xmm0
30 ; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0
32 ; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0
37 ; AVX512-NEXT: vmulss %xmm1, %xmm0, %xmm0
39 ; AVX512-NEXT: vmulss %xmm1, %xmm0, %xmm0
48 ; SSE2-NEXT: mulss %xmm1, %xmm0
51 ; SSE2-NEXT: mulss %xmm2, %xmm0
[all …]
Dshuffle-strided-with-offset-128.ll15 ; SSE2-NEXT: movdqa (%rdi), %xmm0
17 ; SSE2-NEXT: movdqa %xmm0, %xmm2
23 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1…
24 ; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
25 ; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,5,6,7]
26 ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
27 ; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,0,3,2,4,5,6,7]
28 ; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
29 ; SSE2-NEXT: packuswb %xmm0, %xmm0
30 ; SSE2-NEXT: movq %xmm0, (%rsi)
[all …]
Dvector-zext.ll15 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1…
21 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1…
26 …XT: pmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,x…
31 …T: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,x…
43 ; SSE2-NEXT: movdqa %xmm0, %xmm1
45 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2…
51 ; SSSE3-NEXT: movdqa %xmm0, %xmm1
53 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2…
59 … pmovzxbw {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0
60 ; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
[all …]
Dvector-reduce-fadd.ll16 ; SSE2-NEXT: addss %xmm1, %xmm0
18 ; SSE2-NEXT: addss %xmm1, %xmm0
23 ; SSE41-NEXT: addss %xmm1, %xmm0
25 ; SSE41-NEXT: addss %xmm1, %xmm0
30 ; AVX-NEXT: vaddss %xmm1, %xmm0, %xmm0
32 ; AVX-NEXT: vaddss %xmm1, %xmm0, %xmm0
37 ; AVX512-NEXT: vaddss %xmm1, %xmm0, %xmm0
39 ; AVX512-NEXT: vaddss %xmm1, %xmm0, %xmm0
48 ; SSE2-NEXT: addss %xmm1, %xmm0
51 ; SSE2-NEXT: addss %xmm2, %xmm0
[all …]
Dbitcast-int-to-vector-bool.ll12 ; SSE2-SSSE3-NEXT: movq %rdi, %xmm0
13 ; SSE2-SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
14 ; SSE2-SSSE3-NEXT: movdqa {{.*#+}} xmm0 = [1,2]
15 ; SSE2-SSSE3-NEXT: pand %xmm0, %xmm1
16 ; SSE2-SSSE3-NEXT: pcmpeqd %xmm0, %xmm1
17 ; SSE2-SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,0,3,2]
18 ; SSE2-SSSE3-NEXT: pand %xmm1, %xmm0
19 ; SSE2-SSSE3-NEXT: psrlq $63, %xmm0
25 ; AVX1-NEXT: vmovq %rdi, %xmm0
26 ; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
[all …]
Devex-to-vex-compress.mir652 ; CHECK: $ymm0 = VPMOVSXBDYrr $xmm0
653 $ymm0 = VPMOVSXBDZ256rr $xmm0
656 ; CHECK: $ymm0 = VPMOVSXBQYrr $xmm0
657 $ymm0 = VPMOVSXBQZ256rr $xmm0
660 ; CHECK: $ymm0 = VPMOVSXBWYrr $xmm0
661 $ymm0 = VPMOVSXBWZ256rr $xmm0
664 ; CHECK: $ymm0 = VPMOVSXDQYrr $xmm0
665 $ymm0 = VPMOVSXDQZ256rr $xmm0
668 ; CHECK: $ymm0 = VPMOVSXWDYrr $xmm0
669 $ymm0 = VPMOVSXWDZ256rr $xmm0
[all …]
Dknown-bits-vector.ll8 ; X32-NEXT: vpand {{\.LCPI.*}}, %xmm0, %xmm0
9 ; X32-NEXT: vpextrw $0, %xmm0, %eax
14 ; X64-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
15 ; X64-NEXT: vpextrw $0, %xmm0, %eax
27 ; X32-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
28 ; X32-NEXT: vmovd %xmm0, %eax
29 ; X32-NEXT: vcvtsi2ssl %eax, %xmm1, %xmm0
30 ; X32-NEXT: vmovss %xmm0, (%esp)
37 ; X64-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
38 ; X64-NEXT: vmovq %xmm0, %rax
[all …]
Dvector-shift-shl-128.ll23 ; SSE2-NEXT: movdqa %xmm0, %xmm2
26 ; SSE2-NEXT: psllq %xmm1, %xmm0
27 ; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
32 ; SSE41-NEXT: movdqa %xmm0, %xmm2
35 ; SSE41-NEXT: psllq %xmm1, %xmm0
36 ; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm2[0,1,2,3],xmm0[4,5,6,7]
41 ; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm2
43 ; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm0
44 ; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm2[0,1,2,3],xmm0[4,5,6,7]
49 ; AVX2-NEXT: vpsllvq %xmm1, %xmm0, %xmm0
[all …]
Dvector-reduce-mul.ll18 ; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
19 ; SSE-NEXT: movdqa %xmm0, %xmm2
24 ; SSE-NEXT: pmuludq %xmm0, %xmm3
27 ; SSE-NEXT: pmuludq %xmm1, %xmm0
28 ; SSE-NEXT: paddq %xmm3, %xmm0
29 ; SSE-NEXT: movq %xmm0, %rax
34 ; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
35 ; AVX-NEXT: vpsrlq $32, %xmm0, %xmm2
38 ; AVX-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
41 ; AVX-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
[all …]
Dvector-shuffle-128-v8.ll14 ; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
19 ; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,1]
27 ; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
32 ; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
40 ; SSE2-NEXT: shufpd {{.*#+}} xmm0 = xmm0[1],xmm1[0]
45 ; SSSE3-NEXT: palignr {{.*#+}} xmm1 = xmm0[8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7]
46 ; SSSE3-NEXT: movdqa %xmm1, %xmm0
51 ; SSE41-NEXT: palignr {{.*#+}} xmm1 = xmm0[8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7]
52 ; SSE41-NEXT: movdqa %xmm1, %xmm0
57 ; AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7]
[all …]
Dsse2-schedule.ll25 ; GENERIC-NEXT: addpd %xmm1, %xmm0 # sched: [3:1.00]
26 ; GENERIC-NEXT: addpd (%rdi), %xmm0 # sched: [9:1.00]
31 ; ATOM-NEXT: addpd %xmm1, %xmm0 # sched: [6:3.00]
32 ; ATOM-NEXT: addpd (%rdi), %xmm0 # sched: [7:3.50]
37 ; SLM-NEXT: addpd %xmm1, %xmm0 # sched: [3:1.00]
38 ; SLM-NEXT: addpd (%rdi), %xmm0 # sched: [6:1.00]
43 ; SANDY-SSE-NEXT: addpd %xmm1, %xmm0 # sched: [3:1.00]
44 ; SANDY-SSE-NEXT: addpd (%rdi), %xmm0 # sched: [9:1.00]
49 ; SANDY-NEXT: vaddpd %xmm1, %xmm0, %xmm0 # sched: [3:1.00]
50 ; SANDY-NEXT: vaddpd (%rdi), %xmm0, %xmm0 # sched: [9:1.00]
[all …]
Dfma-schedule.ll18 ; GENERIC-NEXT: vfmadd132pd {{.*#+}} xmm0 = (xmm0 * xmm2) + xmm1 sched: [5:0.50]
19 ; GENERIC-NEXT: vfmadd213pd {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2 sched: [5:0.50]
20 ; GENERIC-NEXT: vfmadd231pd {{.*#+}} xmm0 = (xmm1 * xmm2) + xmm0 sched: [5:0.50]
21 ; GENERIC-NEXT: vfmadd132pd {{.*#+}} xmm0 = (xmm0 * mem) + xmm1 sched: [10:0.50]
22 ; GENERIC-NEXT: vfmadd213pd {{.*#+}} xmm0 = (xmm1 * xmm0) + mem sched: [10:0.50]
23 ; GENERIC-NEXT: vfmadd231pd {{.*#+}} xmm0 = (xmm1 * mem) + xmm0 sched: [10:0.50]
30 ; HASWELL-NEXT: vfmadd132pd {{.*#+}} xmm0 = (xmm0 * xmm2) + xmm1 sched: [5:0.50]
31 ; HASWELL-NEXT: vfmadd213pd {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2 sched: [5:0.50]
32 ; HASWELL-NEXT: vfmadd231pd {{.*#+}} xmm0 = (xmm1 * xmm2) + xmm0 sched: [5:0.50]
33 ; HASWELL-NEXT: vfmadd132pd {{.*#+}} xmm0 = (xmm0 * mem) + xmm1 sched: [11:0.50]
[all …]
/external/boringssl/src/crypto/fipsmodule/aes/asm/
Dvpaes-armv8.pl176 ## AES-encrypt %xmm0.
179 ## %xmm0 = input
183 ## Output in %xmm0
197 and v1.16b, v7.16b, v17.16b // vpand %xmm9, %xmm0, %xmm1
198 ushr v0.16b, v7.16b, #4 // vpsrlb \$4, %xmm0, %xmm0
201 tbl v2.16b, {$ipthi}, v0.16b // vpshufb %xmm0, %xmm3, %xmm2
202 eor v0.16b, v1.16b, v16.16b // vpxor %xmm5, %xmm1, %xmm0
203 eor v0.16b, v0.16b, v2.16b // vpxor %xmm2, %xmm0, %xmm0
212 tbl v0.16b, {$sb1u}, v3.16b // vpshufb %xmm3, %xmm12, %xmm0 # 0 = sb1t
215 eor v0.16b, v0.16b, v4.16b // vpxor %xmm4, %xmm0, %xmm0 # 0 = A
[all …]
/external/swiftshader/third_party/llvm-7.0/llvm/test/tools/llvm-mca/X86/Generic/
Dresources-xop.s4 vfrczpd %xmm0, %xmm3
10 vfrczps %xmm0, %xmm3
16 vfrczsd %xmm0, %xmm3
19 vfrczss %xmm0, %xmm3
22 vpcmov %xmm0, %xmm1, %xmm2, %xmm3
23 vpcmov (%rax), %xmm0, %xmm1, %xmm3
24 vpcmov %xmm0, (%rax), %xmm1, %xmm3
30 vpcomb $0, %xmm0, %xmm1, %xmm3
31 vpcomb $0, (%rax), %xmm0, %xmm3
33 vpcomd $0, %xmm0, %xmm1, %xmm3
[all …]
/external/llvm/test/CodeGen/X86/
Dvector-tzcnt-128.ll17 ; SSE2-NEXT: movd %xmm0, %rax
22 ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
23 ; SSE2-NEXT: movd %xmm0, %rax
26 ; SSE2-NEXT: movd %rax, %xmm0
27 ; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
28 ; SSE2-NEXT: movdqa %xmm1, %xmm0
33 ; SSE3-NEXT: movd %xmm0, %rax
38 ; SSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
39 ; SSE3-NEXT: movd %xmm0, %rax
42 ; SSE3-NEXT: movd %rax, %xmm0
[all …]
Dvector-zext.ll13 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1…
19 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1…
24 …XT: pmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,x…
29 …T: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,x…
41 ; SSE2-NEXT: movdqa %xmm0, %xmm1
43 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2…
49 ; SSSE3-NEXT: movdqa %xmm0, %xmm1
51 …cklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2…
57 ; SSE41-NEXT: movdqa %xmm0, %xmm1
59 ; SSE41-NEXT: pmovzxbw {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[…
[all …]
Dwiden_conv-4.ll14 ; X86-SSE2-NEXT: movdqa %xmm0, %xmm2
17 ; X86-SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[…
18 ; X86-SSE2-NEXT: cvtdq2ps %xmm0, %xmm0
19 ; X86-SSE2-NEXT: movups %xmm0, (%eax)
21 ; X86-SSE2-NEXT: movaps %xmm2, %xmm0
22 ; X86-SSE2-NEXT: shufpd {{.*#+}} xmm0 = xmm0[1,0]
23 ; X86-SSE2-NEXT: movss %xmm0, 24(%eax)
32 ; X86-SSE42-NEXT: pmovzxwd {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
33 ; X86-SSE42-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0
34 ; X86-SSE42-NEXT: cvtdq2ps %xmm0, %xmm0
[all …]
Dvec_int_to_fp.ll17 ; SSE-NEXT: movd %xmm0, %rax
19 ; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
20 ; SSE-NEXT: movd %xmm0, %rax
21 ; SSE-NEXT: xorps %xmm0, %xmm0
22 ; SSE-NEXT: cvtsi2sdq %rax, %xmm0
23 ; SSE-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
24 ; SSE-NEXT: movapd %xmm1, %xmm0
29 ; AVX-NEXT: vpextrq $1, %xmm0, %rax
30 ; AVX-NEXT: vcvtsi2sdq %rax, %xmm0, %xmm1
31 ; AVX-NEXT: vmovq %xmm0, %rax
[all …]

12345678910>>...80