| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp8/common/x86/ |
| variance_impl_sse2.asm | 40 movdqa xmm3, [rax+48]
44 pmaddwd xmm3, xmm3
47 paddd xmm2, xmm3
55 movdqa xmm3,xmm4
57 paddd xmm4,xmm3
58 movdqa xmm3,xmm4
60 paddd xmm4,xmm3
136 movdqa xmm3, xmm1
141 punpckhbw xmm3, xmm
[all...] |
| variance_impl_ssse3.asm | 94 movdqa xmm3, xmm1
97 punpckhbw xmm3, xmm2
99 pmaddubsw xmm3, [rax]
102 paddw xmm3, [GLOBAL(xmm_bi_rd)]
104 psraw xmm3, xmm_filter_shift
105 packuswb xmm1, xmm3
109 movdqa xmm3, xmm2
112 punpckhbw xmm3, xmm1
114 pmaddubsw xmm3, [rdx]
117 paddw xmm3, [GLOBAL(xmm_bi_rd)
[all...] |
| sad_sse4.asm | 18 movq xmm3, MMWORD PTR [rdi+8]
20 punpcklqdq xmm1, xmm3
21 punpcklqdq xmm3, xmm2
29 movdqa xmm4, xmm3
30 mpsadbw xmm3, xmm0, 0x0
34 paddw xmm1, xmm3
39 movq xmm3, MMWORD PTR [rdi+8]
41 punpcklqdq xmm5, xmm3
42 punpcklqdq xmm3, xmm2
50 movdqa xmm4, xmm3
[all...] |
| /external/llvm/test/CodeGen/X86/ |
| fmaxnum.ll | 21 ; SSE-NEXT: movaps %xmm2, %xmm3
22 ; SSE-NEXT: andps %xmm1, %xmm3
25 ; SSE-NEXT: orps %xmm3, %xmm2
64 ; SSE-NEXT: movaps %xmm2, %xmm3
65 ; SSE-NEXT: andps %xmm1, %xmm3
68 ; SSE-NEXT: orps %xmm3, %xmm2
103 ; SSE-NEXT: movaps %xmm0, %xmm3
104 ; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[3,1,2,3]
105 ; SSE-NEXT: movaps %xmm3, %xmm
[all...] |
| vector-rotate-128.ll | 21 ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,0,1]
23 ; SSE2-NEXT: psllq %xmm3, %xmm4
24 ; SSE2-NEXT: movdqa %xmm0, %xmm3
25 ; SSE2-NEXT: psllq %xmm1, %xmm3
26 ; SSE2-NEXT: movsd {{.*#+}} xmm4 = xmm3[0],xmm4[1]
27 ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[2,3,0,1]
29 ; SSE2-NEXT: psrlq %xmm3, %xmm1
40 ; SSE41-NEXT: movdqa %xmm0, %xmm3
41 ; SSE41-NEXT: psllq %xmm1, %xmm3
45 ; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm3[0,1,2,3],xmm4[4,5,6,7
[all...] |
| /external/libvpx/libvpx/vpx_dsp/x86/ |
| sad_sse4.asm | 18 movq xmm3, MMWORD PTR [rdi+8]
20 punpcklqdq xmm1, xmm3
21 punpcklqdq xmm3, xmm2
29 movdqa xmm4, xmm3
30 mpsadbw xmm3, xmm0, 0x0
34 paddw xmm1, xmm3
39 movq xmm3, MMWORD PTR [rdi+8]
41 punpcklqdq xmm5, xmm3
42 punpcklqdq xmm3, xmm2
50 movdqa xmm4, xmm3
[all...] |
| highbd_variance_impl_sse2.asm | 87 movdqu xmm3, XMMWORD PTR [rsi+16]
93 psubw xmm3, xmm2
95 paddw xmm5, xmm3
96 pmaddwd xmm3, xmm3
98 paddd xmm6, xmm3
101 movdqu xmm3, XMMWORD PTR [rsi+rax+16]
107 psubw xmm3, xmm2
108 paddw xmm5, xmm3
109 pmaddwd xmm3, xmm
[all...] |
| halfpix_variance_impl_sse2.asm | 43 movdqu xmm3, XMMWORD PTR [rsi+1]
44 pavgb xmm5, xmm3 ; xmm5 = avg(xmm1,xmm3) horizontal line 1
51 pavgb xmm1, xmm2 ; xmm1 = avg(xmm1,xmm3) horizontal line i+1
59 movq xmm3, QWORD PTR [rdi] ; xmm3 = d0,d1,d2..d7
60 punpcklbw xmm3, xmm0 ; xmm3 = words of above
61 psubw xmm5, xmm3 ; xmm5 -= xmm3
[all...] |
| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp9/encoder/x86/ |
| vp9_sad_sse4.asm | 18 movq xmm3, MMWORD PTR [rdi+8]
20 punpcklqdq xmm1, xmm3
21 punpcklqdq xmm3, xmm2
29 movdqa xmm4, xmm3
30 mpsadbw xmm3, xmm0, 0x0
34 paddw xmm1, xmm3
39 movq xmm3, MMWORD PTR [rdi+8]
41 punpcklqdq xmm5, xmm3
42 punpcklqdq xmm3, xmm2
50 movdqa xmm4, xmm3
[all...] |
| vp9_variance_impl_sse2.asm | 38 movdqa xmm3, [rax+48]
42 pmaddwd xmm3, xmm3
45 paddd xmm2, xmm3
53 movdqa xmm3,xmm4
55 paddd xmm4,xmm3
56 movdqa xmm3,xmm4
58 paddd xmm4,xmm3
134 movdqa xmm3, xmm1
139 punpckhbw xmm3, xmm
[all...] |
| vp9_subpel_variance_impl_sse2.asm | 46 movdqu xmm3, XMMWORD PTR [rsi+1]
47 pavgb xmm5, xmm3 ; xmm5 = avg(xmm1,xmm3) horizontal line 1
54 pavgb xmm1, xmm2 ; xmm1 = avg(xmm1,xmm3) horizontal line i+1
62 movq xmm3, QWORD PTR [rdi] ; xmm3 = d0,d1,d2..d7
63 punpcklbw xmm3, xmm0 ; xmm3 = words of above
64 psubw xmm5, xmm3 ; xmm5 -= xmm3
[all...] |
| /toolchain/binutils/binutils-2.25/gas/testsuite/gas/i386/ |
| xop.s | 109 # Tests for op VPCMOV xmm4, xmm3/mem128, xmm2, xmm1 (at&t syntax)
112 VPCMOV %xmm1,(%esi),%xmm3,%xmm0
118 VPCMOV %xmm7,(%esi),%xmm3,%xmm7
119 VPCMOV %xmm7,%xmm6,%xmm3,%xmm7
120 VPCMOV %xmm7,%xmm7,%xmm3,%xmm0
121 VPCMOV %xmm0,(%edx),%xmm3,%xmm0
125 VPCMOV %xmm7,(%esi),%xmm3,%xmm5
143 # Tests for op VPCMOV xmm4/mem128, xmm3, xmm2, xmm1 (at&t syntax)
146 VPCMOV (%eax),%xmm7,%xmm3,%xmm0
152 VPCMOV (%ebx),%xmm7,%xmm3,%xmm
[all...] |
| sha.s | 8 sha1rnds4 $5, 0x12(%eax), %xmm3
43 sha1rnds4 xmm3, XMMWORD PTR [eax+0x12], 5
47 sha1nexte xmm3, XMMWORD PTR [eax+0x12]
51 sha1msg1 xmm3, XMMWORD PTR [eax+0x12]
55 sha1msg2 xmm3, XMMWORD PTR [eax+0x12]
59 sha256rnds2 xmm3, XMMWORD PTR [eax+0x12]
63 sha256rnds2 xmm3, XMMWORD PTR [eax+0x12], xmm0
67 sha256msg1 xmm3, XMMWORD PTR [eax+0x12]
71 sha256msg2 xmm3, XMMWORD PTR [eax+0x12]
|
| x86-64-sha.s | 8 sha1rnds4 $5, 0x12(%rax), %xmm3
43 sha1rnds4 xmm3, XMMWORD PTR [rax+0x12], 5
47 sha1nexte xmm3, XMMWORD PTR [rax+0x12]
51 sha1msg1 xmm3, XMMWORD PTR [rax+0x12]
55 sha1msg2 xmm3, XMMWORD PTR [rax+0x12]
59 sha256rnds2 xmm3, XMMWORD PTR [rax+0x12]
63 sha256rnds2 xmm3, XMMWORD PTR [rax+0x12], xmm0
67 sha256msg1 xmm3, XMMWORD PTR [rax+0x12]
71 sha256msg2 xmm3, XMMWORD PTR [rax+0x12]
|
| arch-10.s | 12 addss %xmm4,%xmm3
14 addsd %xmm4,%xmm3
16 addsubpd %xmm4,%xmm3
18 phaddw %xmm4,%xmm3
20 phminposuw %xmm1,%xmm3
|
| x86-64-arch-2.s | 12 addss %xmm4,%xmm3
14 addsd %xmm4,%xmm3
16 addsubpd %xmm4,%xmm3
18 phaddw %xmm4,%xmm3
20 phminposuw %xmm1,%xmm3
|
| /external/libjpeg-turbo/simd/ |
| jidctflt-sse2-64.asm | 104 movq xmm3, XMM_MMWORD [MMBLOCK(3,0,rsi,SIZEOF_JCOEF)]
110 por xmm3,xmm4
112 por xmm1,xmm3
132 movaps xmm3,xmm0
137 shufps xmm3,xmm3,0xFF ; xmm3=(03 03 03 03)
145 movaps XMMWORD [XMMBLOCK(3,0,rdi,SIZEOF_FAST_FLOAT)], xmm3
146 movaps XMMWORD [XMMBLOCK(3,1,rdi,SIZEOF_FAST_FLOAT)], xmm3
156 movq xmm3, XMM_MMWORD [MMBLOCK(6,0,rsi,SIZEOF_JCOEF)
[all...] |
| jidctflt-sse2.asm | 110 movq xmm3, XMM_MMWORD [MMBLOCK(3,0,esi,SIZEOF_JCOEF)]
116 por xmm3,xmm4
118 por xmm1,xmm3
138 movaps xmm3,xmm0
143 shufps xmm3,xmm3,0xFF ; xmm3=(03 03 03 03)
151 movaps XMMWORD [XMMBLOCK(3,0,edi,SIZEOF_FAST_FLOAT)], xmm3
152 movaps XMMWORD [XMMBLOCK(3,1,edi,SIZEOF_FAST_FLOAT)], xmm3
163 movq xmm3, XMM_MMWORD [MMBLOCK(6,0,esi,SIZEOF_JCOEF)
[all...] |
| jidctint-sse2-64.asm | 161 pshufd xmm3,xmm4,0x55 ; xmm3=col5=(05 05 05 05 05 05 05 05)
167 movdqa XMMWORD [wk(10)], xmm3 ; wk(10)=col5
180 movdqa xmm3, XMMWORD [XMMBLOCK(6,0,rsi,SIZEOF_JCOEF)]
182 pmullw xmm3, XMMWORD [XMMBLOCK(6,0,rdx,SIZEOF_ISLOW_MULT_TYPE)]
195 punpcklwd xmm4,xmm3 ; xmm3=in6=z3
196 punpckhwd xmm5,xmm3
198 movdqa xmm3,xmm5
202 pmaddwd xmm3,[rel PW_F054_MF130] ; xmm3=tmp2
[all...] |
| jfdctflt-sse-64.asm | 89 movaps xmm3, XMMWORD [XMMBLOCK(3,1,rdx,SIZEOF_FAST_FLOAT)]
92 ; xmm1=(30 31 32 33), xmm3=(34 35 36 37)
98 unpcklps xmm2,xmm3 ; xmm2=(24 34 25 35)
99 unpckhps xmm5,xmm3 ; xmm5=(26 36 27 37)
104 movaps xmm3, XMMWORD [XMMBLOCK(1,1,rdx,SIZEOF_FAST_FLOAT)]
107 ; xmm7=(10 11 12 13), xmm3=(14 15 16 17)
116 unpcklps xmm1,xmm3 ; xmm1=(04 14 05 15)
117 unpckhps xmm2,xmm3 ; xmm2=(06 16 07 17)
122 movaps xmm3,xmm2 ; transpose coefficients(phase 2)
124 unpckhps2 xmm3,xmm5 ; xmm3=(07 17 27 37)=data
[all...] |
| jfdctflt-sse.asm | 96 movaps xmm3, XMMWORD [XMMBLOCK(3,1,edx,SIZEOF_FAST_FLOAT)]
99 ; xmm1=(30 31 32 33), xmm3=(34 35 36 37)
105 unpcklps xmm2,xmm3 ; xmm2=(24 34 25 35)
106 unpckhps xmm5,xmm3 ; xmm5=(26 36 27 37)
111 movaps xmm3, XMMWORD [XMMBLOCK(1,1,edx,SIZEOF_FAST_FLOAT)]
114 ; xmm7=(10 11 12 13), xmm3=(14 15 16 17)
123 unpcklps xmm1,xmm3 ; xmm1=(04 14 05 15)
124 unpckhps xmm2,xmm3 ; xmm2=(06 16 07 17)
129 movaps xmm3,xmm2 ; transpose coefficients(phase 2)
131 unpckhps2 xmm3,xmm5 ; xmm3=(07 17 27 37)=data
[all...] |
| /external/libvpx/libvpx/vp8/encoder/x86/ |
| dct_sse2.asm | 73 movq xmm3, MMWORD PTR[input+ pitch] ;33 32 31 30
76 punpcklqdq xmm1, xmm3 ;33 32 31 30 23 22 21 20
87 movdqa xmm3, xmm0
89 psubw xmm3, xmm1 ;c1 d1 c1 d1 c1 d1 c1 d1
91 psllw xmm3, 3 ;c1 <<= 3 d1 <<= 3
96 movdqa xmm4, xmm3
97 pmaddwd xmm3, XMMWORD PTR[GLOBAL(_5352_2217)] ;c1*2217 + d1*5352
100 paddd xmm3, XMMWORD PTR[GLOBAL(_14500)]
102 psrad xmm3, 12 ;(c1 * 2217 + d1 * 5352 + 14500)>>12
106 packssdw xmm3, xmm4 ;op[3] op[1
[all...] |
| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp8/encoder/x86/ |
| dct_sse2.asm | 73 movq xmm3, MMWORD PTR[input+ pitch] ;33 32 31 30
76 punpcklqdq xmm1, xmm3 ;33 32 31 30 23 22 21 20
87 movdqa xmm3, xmm0
89 psubw xmm3, xmm1 ;c1 d1 c1 d1 c1 d1 c1 d1
91 psllw xmm3, 3 ;c1 <<= 3 d1 <<= 3
96 movdqa xmm4, xmm3
97 pmaddwd xmm3, XMMWORD PTR[GLOBAL(_5352_2217)] ;c1*2217 + d1*5352
100 paddd xmm3, XMMWORD PTR[GLOBAL(_14500)]
102 psrad xmm3, 12 ;(c1 * 2217 + d1 * 5352 + 14500)>>12
106 packssdw xmm3, xmm4 ;op[3] op[1
[all...] |
| /external/llvm/test/MC/X86/ |
| x86-32-avx.s | 330 // CHECK: vshufps $8, %xmm1, %xmm2, %xmm3
332 vshufps $8, %xmm1, %xmm2, %xmm3
334 // CHECK: vshufps $8, -4(%ebx,%ecx,8), %xmm2, %xmm3
336 vshufps $8, -4(%ebx,%ecx,8), %xmm2, %xmm3
338 // CHECK: vshufpd $8, %xmm1, %xmm2, %xmm3
340 vshufpd $8, %xmm1, %xmm2, %xmm3
342 // CHECK: vshufpd $8, -4(%ebx,%ecx,8), %xmm2, %xmm3
344 vshufpd $8, -4(%ebx,%ecx,8), %xmm2, %xmm3
346 // CHECK: vcmpeqps %xmm1, %xmm2, %xmm3
348 vcmpeqps %xmm1, %xmm2, %xmm3
[all...] |
| /art/runtime/arch/x86/ |
| memcmp16_x86.S | 74 movdqu (%eax), %xmm3
78 pcmpeqb %xmm0, %xmm3
79 pmovmskb %xmm3, %edx
194 movdqa 32(%esi), %xmm3
195 palignr $2,%xmm2, %xmm3
196 pcmpeqb 16(%edi), %xmm3
198 pand %xmm1, %xmm3
199 pmovmskb %xmm3, %edx
219 movdqa 32(%esi), %xmm3
220 palignr $2,16(%esi), %xmm3
[all...] |
