/sysdeps/x86_64/fpu/multiarch/ |
A D | svml_s_acosf4_core_sse4.S | 65 movaps %xmm5, %xmm6 71 addps %xmm6, %xmm5 74 rsqrtps %xmm5, %xmm8 75 minps %xmm5, %xmm13 76 movaps %xmm5, %xmm2 79 cmpnltps %xmm5, %xmm1 81 addps %xmm5, %xmm5 88 mulps %xmm5, %xmm2 90 mulps %xmm9, %xmm5 101 mulps %xmm2, %xmm5 [all …]
|
A D | svml_s_logf4_core_sse4.S | 77 mulps %xmm1, %xmm5 78 addps _sPoly_6(%rax), %xmm5 79 mulps %xmm1, %xmm5 80 addps _sPoly_5(%rax), %xmm5 81 mulps %xmm1, %xmm5 83 mulps %xmm1, %xmm5 85 mulps %xmm1, %xmm5 87 mulps %xmm1, %xmm5 89 mulps %xmm1, %xmm5 92 mulps %xmm1, %xmm5 [all …]
|
A D | svml_d_sincos2_core_sse4.S | 61 mulpd %xmm4, %xmm5 65 movaps %xmm5, %xmm12 76 mulpd %xmm5, %xmm1 81 mulpd %xmm5, %xmm2 102 addpd %xmm5, %xmm3 120 mulpd %xmm5, %xmm6 129 mulpd %xmm6, %xmm5 133 subpd %xmm5, %xmm13 146 movaps %xmm5, %xmm3 148 mulpd %xmm10, %xmm5 [all …]
|
A D | svml_d_log2_core_sse4.S | 55 andps %xmm6, %xmm5 56 orps _Two10(%r8), %xmm5 59 cvtpd2ps %xmm5, %xmm7 71 andps %xmm5, %xmm2 73 subpd %xmm2, %xmm5 78 mulpd %xmm4, %xmm5 80 addpd %xmm2, %xmm5 95 mulpd %xmm5, %xmm4 108 movaps %xmm5, %xmm2 109 mulpd %xmm5, %xmm2 [all …]
|
A D | svml_d_exp2_core_sse4.S | 60 movq __iAbsMask(%r8), %xmm5 64 pand %xmm5, %xmm7 74 movups __dbLn2hi(%r8), %xmm5 79 mulpd %xmm7, %xmm5 88 subpd %xmm5, %xmm0 90 movups __dPC2(%r8), %xmm5 93 mulpd %xmm0, %xmm5 94 addpd __dPC1(%r8), %xmm5 95 mulpd %xmm0, %xmm5 97 addpd %xmm6, %xmm5 [all …]
|
A D | svml_d_pow4_core_avx2.S | 100 vextracti128 $1, %ymm0, %xmm5 101 vshufps $221, %xmm5, %xmm0, %xmm5 104 vandps _iIndexMask(%rax), %xmm5, %xmm3 121 vpsubd _i3fe7fe00(%rax), %xmm5, %xmm3 122 vpaddd _HIDELTA(%rax), %xmm5, %xmm5 225 vpcmpgtd %xmm5, %xmm7, %xmm13 229 vpor %xmm7, %xmm13, %xmm5 236 vpor %xmm3, %xmm5, %xmm13 266 vpslld $4, %xmm3, %xmm5 276 vgatherdpd %ymm10, 36416(%rax,%xmm5), %ymm1
|
A D | svml_s_cosf4_core_sse4.S | 56 movups __sRShifter(%rax), %xmm5 68 addps %xmm5, %xmm1 77 subps %xmm5, %xmm1 80 movups __sPI3(%rax), %xmm5 96 mulps %xmm1, %xmm5 102 subps %xmm5, %xmm0
|
A D | svml_s_expf4_core_sse4.S | 52 movaps %xmm0, %xmm5 57 mulps %xmm5, %xmm0 71 pand %xmm5, %xmm7 79 movaps %xmm5, %xmm7 128 movups %xmm5, 192(%rsp)
|
A D | svml_d_cos2_core_sse4.S | 51 movups __dInvPI(%rax), %xmm5 58 mulpd %xmm5, %xmm2 84 movups __dPI3(%rax), %xmm5 87 mulpd %xmm1, %xmm5 93 subpd %xmm5, %xmm0
|
A D | svml_d_acos2_core_sse4.S | 48 movaps %xmm0, %xmm5 54 orps %xmm5, %xmm4 79 andps %xmm5, %xmm3 112 movaps %xmm5, %xmm12 156 # LOE rbx rbp r12 r13 r14 r15 edx xmm0 xmm5 173 movups %xmm5, 32(%rsp)
|
/sysdeps/x86_64/multiarch/ |
A D | strstr-sse2-unaligned.S | 41 pxor %xmm5, %xmm5 47 pcmpeqb %xmm5, %xmm6 51 pcmpeqb %xmm0, %xmm5 56 por %xmm5, %xmm0 104 pxor %xmm5, %xmm5 110 pcmpeqb %xmm5, %xmm6 114 pcmpeqb %xmm0, %xmm5 119 por %xmm5, %xmm0 196 pxor %xmm1, %xmm5 197 por %xmm8, %xmm5 [all …]
|
A D | strcmp-sse2-unaligned.S | 51 movdqu 32(%rdi), %xmm5 57 pcmpeqb %xmm5, %xmm2 60 pminub %xmm5, %xmm2 111 pcmpeqb %xmm2, %xmm5 113 pminub %xmm2, %xmm5 115 pminub %xmm5, %xmm0 121 pcmpeqb %xmm7, %xmm5 130 pmovmskb %xmm5, %r8d 164 pcmpeqb %xmm2, %xmm5 166 pminub %xmm2, %xmm5 [all …]
|
A D | memcpy-ssse3.S | 458 movdqa %xmm5, %xmm6 508 movaps %xmm5, %xmm1 543 movdqa %xmm5, %xmm6 593 movaps %xmm5, %xmm1 628 movdqa %xmm5, %xmm6 678 movaps %xmm5, %xmm1 713 movdqa %xmm5, %xmm6 763 movaps %xmm5, %xmm1 798 movdqa %xmm5, %xmm6 848 movaps %xmm5, %xmm1 [all …]
|
A D | memcpy-ssse3-back.S | 244 movaps 0x3f(%rsi), %xmm5 256 palignr $1, %xmm5, %xmm6 258 palignr $1, %xmm4, %xmm5 259 movaps %xmm5, 0x30(%rdi) 291 palignr $1, %xmm5, %xmm4 295 palignr $1, %xmm6, %xmm5 327 movaps 0x3e(%rsi), %xmm5 339 palignr $2, %xmm5, %xmm6 341 palignr $2, %xmm4, %xmm5 342 movaps %xmm5, 0x30(%rdi) [all …]
|
A D | wcscpy-ssse3.S | 142 movaps 16(%rcx), %xmm5 146 pminub %xmm5, %xmm2 156 movaps %xmm5, -48(%rdx) 167 pcmpeqd %xmm5, %xmm0 265 movaps 60(%rcx), %xmm5 267 pminub %xmm5, %xmm7 271 movaps %xmm5, %xmm7 366 pminub %xmm5, %xmm7 370 movaps %xmm5, %xmm7 465 pminub %xmm5, %xmm7 [all …]
|
A D | strcpy-ssse3.S | 263 pminub %xmm5, %xmm2 291 pcmpeqb %xmm5, %xmm0 407 pminub %xmm5, %xmm7 411 movaps %xmm5, %xmm7 524 pminub %xmm5, %xmm7 528 movaps %xmm5, %xmm7 641 pminub %xmm5, %xmm7 645 movaps %xmm5, %xmm7 758 pminub %xmm5, %xmm7 762 movaps %xmm5, %xmm7 [all …]
|
/sysdeps/x86_64/ |
A D | strchr.S | 87 movdqa (%rdi), %xmm5 90 pxor %xmm1, %xmm5 94 pminub (%rdi), %xmm5 98 pminub %xmm2, %xmm5 100 pminub %xmm3, %xmm5 101 pminub %xmm4, %xmm5 102 pcmpeqb %xmm6, %xmm5 103 pmovmskb %xmm5, %eax 108 movdqa (%rdi), %xmm5 109 movdqa %xmm5, %xmm0 [all …]
|
A D | strrchr.S | 52 movdqa %xmm4, %xmm5 55 pcmpeqb %xmm2, %xmm5 57 pmovmskb %xmm5, %edx 58 movdqa %xmm3, %xmm5 60 pcmpeqb %xmm2, %xmm5 64 pmovmskb %xmm5, %eax 113 movdqa (%rdi), %xmm5 115 pminub %xmm5, %xmm0 118 movdqa %xmm5, %xmm0 140 pcmpeqb %xmm6, %xmm5 [all …]
|
A D | tst-sse.c | 34 __m128i xmm5 = _mm_set1_epi32 (5); in do_test() local 38 xmm4, xmm5, xmm6, xmm7); in do_test()
|
/sysdeps/i386/i686/multiarch/ |
A D | wcscpy-ssse3.S | 157 movaps 16(%ecx), %xmm5 160 pminub %xmm5, %xmm2 182 pcmpeqd %xmm5, %xmm0 276 movaps 60(%ecx), %xmm5 278 pminub %xmm5, %xmm7 282 movaps %xmm5, %xmm7 292 movaps %xmm5, 48(%edx) 389 pminub %xmm5, %xmm7 393 movaps %xmm5, %xmm7 498 pminub %xmm5, %xmm7 [all …]
|
A D | memcpy-sse2-unaligned.S | 118 movdqu -48(%eax, %ecx), %xmm5 126 movdqu %xmm5, -48(%edx, %ecx) 142 movdqu 16(%eax), %xmm5 193 movdqu %xmm5, 16(%edx) 262 movdqu %xmm5, 16(%edx) 314 movdqu -48(%eax, %ecx), %xmm5 387 movdqu %xmm5, -32(%esi) 458 movdqu %xmm5, -32(%esi) 549 movdqu 80(%ebx, %eax), %xmm5 557 movaps %xmm5, 80(%ebx) [all …]
|
A D | strcpy-ssse3.S | 305 pminub %xmm5, %xmm2 333 pcmpeqb %xmm5, %xmm0 449 pminub %xmm5, %xmm7 453 movaps %xmm5, %xmm7 568 pminub %xmm5, %xmm7 572 movaps %xmm5, %xmm7 687 pminub %xmm5, %xmm7 691 movaps %xmm5, %xmm7 806 pminub %xmm5, %xmm7 810 movaps %xmm5, %xmm7 [all …]
|
/sysdeps/i386/i686/fpu/multiarch/ |
A D | s_sinf-sse2.S | 236 movapd %xmm0, %xmm5 /* |x| */ 252 movapd %xmm5, %xmm2 /* tmp2 copy */ 253 addsd %xmm3, %xmm5 /* tmp5 = tmp3 + tmp2 */ 255 addsd %xmm5, %xmm6 /* tmp6 = tmp5 + 2^52 */ 260 comisd %xmm5, %xmm4 /* tmp4 > tmp5? */ 293 movsd MO1(DP_S3), %xmm5 /* S3 */ 294 mulsd %xmm0, %xmm5 /* z*S3 */ 297 addsd MO1(DP_S1), %xmm5 /* S1+z*S3 */ 298 mulsd %xmm0, %xmm5 /* z*(S1+z*S3) */ 301 mulsd %xmm3, %xmm5 /* x*z*(S1+z*S3) */ [all …]
|
A D | s_sincosf-sse2.S | 236 movapd %xmm0, %xmm5 /* |x| */ 252 movapd %xmm5, %xmm2 /* tmp2 copy */ 253 addsd %xmm3, %xmm5 /* tmp5 = tmp3 + tmp2 */ 255 addsd %xmm5, %xmm6 /* tmp6 = tmp5 + 2^52 */ 260 comisd %xmm5, %xmm4 /* tmp4 > tmp5 ? */ 296 movapd MO1(DP_SC3), %xmm5 /* S3 */ 297 mulpd %xmm0, %xmm5 /* z*S3 */ 300 addpd MO1(DP_SC1), %xmm5 /* S1+z*S3 */ 301 mulpd %xmm0, %xmm5 /* z*(S1+z*S3) */ 304 mulpd %xmm3, %xmm5 /* x*z*(S1+z*S3) */ [all …]
|
A D | s_cosf-sse2.S | 232 movapd %xmm0, %xmm5 /* |x| */ 235 mulsd -1*8+MO2(_FPI,%eax,8), %xmm5 /* tmp2 = FPI[j-1]*|x| */ 248 movapd %xmm5, %xmm2 /* tmp2 copy */ 249 addsd %xmm3, %xmm5 /* tmp5 = tmp3 + tmp2 */ 251 addsd %xmm5, %xmm6 /* tmp6 = tmp5 + 2^52 */ 255 comisd %xmm5, %xmm4 /* tmp4 > tmp5? */ 286 movsd MO1(DP_C3), %xmm5 /* C3 */ 287 mulsd %xmm0, %xmm5 /* z*C3 */ 290 addsd MO1(DP_C1), %xmm5 /* C1+z*C3 */ 291 mulsd %xmm0, %xmm5 /* z*(C1+z*C3) */ [all …]
|