diff options
author | Andrew Senkevich <andrew.senkevich@intel.com> | 2015-06-17 15:53:00 +0300 |
---|---|---|
committer | Andrew Senkevich <andrew.senkevich@intel.com> | 2015-06-17 15:53:00 +0300 |
commit | 774488f88aeed6b838fe29c3c7561433c242a3c9 (patch) | |
tree | 25aaaa25ca25b0ce8855e23fd9b23f1c1f388820 /sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S | |
parent | 6af25acc7b6313fd8934c3b2f0eb3da5a1c6eb6b (diff) | |
download | glibc-774488f88aeed6b838fe29c3c7561433c242a3c9.tar.gz glibc-774488f88aeed6b838fe29c3c7561433c242a3c9.tar.xz glibc-774488f88aeed6b838fe29c3c7561433c242a3c9.zip |
Vector logf for x86_64 and tests.
Here is implementation of vectorized logf containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New symbols added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for logf. * sysdeps/x86_64/fpu/Makefile (libmvec-support): Added new files. * sysdeps/x86_64/fpu/Versions: New versions added. * sysdeps/x86_64/fpu/libm-test-ulps: Regenerated. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S: New file. * sysdeps/x86_64/fpu/svml_s_logf16_core.S: New file. * sysdeps/x86_64/fpu/svml_s_logf4_core.S: New file. * sysdeps/x86_64/fpu/svml_s_logf8_core.S: New file. * sysdeps/x86_64/fpu/svml_s_logf8_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_s_logf_data.S: New file. * sysdeps/x86_64/fpu/svml_s_logf_data.h: New file. * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Vector logf tests. * sysdeps/x86_64/fpu/test-float-vlen16.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen4-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen4.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-avx2-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-avx2.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8.c: Likewise. * NEWS: Mention addition of x86_64 vector logf.
Diffstat (limited to 'sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S')
-rw-r--r-- | sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S | 184 |
1 files changed, 184 insertions, 0 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S new file mode 100644 index 0000000000..1f08b4218a --- /dev/null +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S @@ -0,0 +1,184 @@ +/* Function logf vectorized with AVX2. + Copyright (C) 2014-2015 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + <http://www.gnu.org/licenses/>. */ + +#include <sysdep.h> +#include "svml_s_logf_data.h" + + .text +ENTRY(_ZGVdN8v_logf_avx2) +/* + ALGORITHM DESCRIPTION: + + log(x) = exponent_x*log(2) + log(mantissa_x), if mantissa_x<4/3 + log(x) = (exponent_x+1)*log(2) + log(0.5*mantissa_x), if mantissa_x>4/3 + + R = mantissa_x - 1, if mantissa_x<4/3 + R = 0.5*mantissa_x - 1, if mantissa_x>4/3 + |R|< 1/3 + + log(1+R) is approximated as a polynomial: degree 9 for 1-ulp, + degree 7 for 4-ulp, degree 3 for half-precision. */ + + pushq %rbp + cfi_adjust_cfa_offset (8) + cfi_rel_offset (%rbp, 0) + movq %rsp, %rbp + cfi_def_cfa_register (%rbp) + andq $-64, %rsp + subq $448, %rsp + movq __svml_slog_data@GOTPCREL(%rip), %rax + vmovaps %ymm0, %ymm2 + vmovups _iBrkValue(%rax), %ymm6 + vmovups _iLoRange(%rax), %ymm1 +/* check for working range, + set special argument mask (denormals/zero/Inf/NaN) */ + vpaddd _iHiDelta(%rax), %ymm2, %ymm7 + +/* reduction: compute r,n */ + vpsubd %ymm6, %ymm2, %ymm4 + +/* exponent_x (mantissa_x<4/3) or exponent_x+1 (mantissa_x>4/3) */ + vpsrad $23, %ymm4, %ymm3 + vpand _iOffExpoMask(%rax), %ymm4, %ymm5 + vmovups _sPoly_7(%rax), %ymm4 + vcvtdq2ps %ymm3, %ymm0 + +/* mantissa_x (mantissa_x<4/3), or 0.5*mantissa_x (mantissa_x>4/3) */ + vpaddd %ymm6, %ymm5, %ymm3 + +/* reduced argument R */ + vsubps _sOne(%rax), %ymm3, %ymm5 + +/* polynomial evaluation starts here */ + vfmadd213ps _sPoly_6(%rax), %ymm5, %ymm4 + vfmadd213ps _sPoly_5(%rax), %ymm5, %ymm4 + vfmadd213ps _sPoly_4(%rax), %ymm5, %ymm4 + vfmadd213ps _sPoly_3(%rax), %ymm5, %ymm4 + vfmadd213ps _sPoly_2(%rax), %ymm5, %ymm4 + vfmadd213ps _sPoly_1(%rax), %ymm5, %ymm4 + vmulps %ymm5, %ymm4, %ymm6 + +/* polynomial evaluation end */ + vfmadd213ps %ymm5, %ymm5, %ymm6 + vpcmpgtd %ymm7, %ymm1, %ymm1 + vmovmskps %ymm1, %ecx + +/* final reconstruction: + add exponent_value*log2 to polynomial result */ + vfmadd132ps _sLn2(%rax), %ymm6, %ymm0 + testl %ecx, %ecx + jne .LBL_1_3 + +.LBL_1_2: + cfi_remember_state + movq %rbp, %rsp + cfi_def_cfa_register (%rsp) + popq %rbp + cfi_adjust_cfa_offset (-8) + cfi_restore (%rbp) + ret + +.LBL_1_3: + cfi_restore_state + vmovups %ymm2, 320(%rsp) + vmovups %ymm0, 384(%rsp) + je .LBL_1_2 + + xorb %dl, %dl + xorl %eax, %eax + vmovups %ymm8, 224(%rsp) + vmovups %ymm9, 192(%rsp) + vmovups %ymm10, 160(%rsp) + vmovups %ymm11, 128(%rsp) + vmovups %ymm12, 96(%rsp) + vmovups %ymm13, 64(%rsp) + vmovups %ymm14, 32(%rsp) + vmovups %ymm15, (%rsp) + movq %rsi, 264(%rsp) + movq %rdi, 256(%rsp) + movq %r12, 296(%rsp) + cfi_offset_rel_rsp (12, 296) + movb %dl, %r12b + movq %r13, 288(%rsp) + cfi_offset_rel_rsp (13, 288) + movl %ecx, %r13d + movq %r14, 280(%rsp) + cfi_offset_rel_rsp (14, 280) + movl %eax, %r14d + movq %r15, 272(%rsp) + cfi_offset_rel_rsp (15, 272) + cfi_remember_state + +.LBL_1_6: + btl %r14d, %r13d + jc .LBL_1_12 + +.LBL_1_7: + lea 1(%r14), %esi + btl %esi, %r13d + jc .LBL_1_10 + +.LBL_1_8: + incb %r12b + addl $2, %r14d + cmpb $16, %r12b + jb .LBL_1_6 + + vmovups 224(%rsp), %ymm8 + vmovups 192(%rsp), %ymm9 + vmovups 160(%rsp), %ymm10 + vmovups 128(%rsp), %ymm11 + vmovups 96(%rsp), %ymm12 + vmovups 64(%rsp), %ymm13 + vmovups 32(%rsp), %ymm14 + vmovups (%rsp), %ymm15 + vmovups 384(%rsp), %ymm0 + movq 264(%rsp), %rsi + movq 256(%rsp), %rdi + movq 296(%rsp), %r12 + cfi_restore (%r12) + movq 288(%rsp), %r13 + cfi_restore (%r13) + movq 280(%rsp), %r14 + cfi_restore (%r14) + movq 272(%rsp), %r15 + cfi_restore (%r15) + jmp .LBL_1_2 + +.LBL_1_10: + cfi_restore_state + movzbl %r12b, %r15d + vmovss 324(%rsp,%r15,8), %xmm0 + vzeroupper + + call logf@PLT + + vmovss %xmm0, 388(%rsp,%r15,8) + jmp .LBL_1_8 + +.LBL_1_12: + movzbl %r12b, %r15d + vmovss 320(%rsp,%r15,8), %xmm0 + vzeroupper + + call logf@PLT + + vmovss %xmm0, 384(%rsp,%r15,8) + jmp .LBL_1_7 + +END(_ZGVdN8v_logf_avx2) |