From c9a8c526acd185176e486bee4624039740f8c435 Mon Sep 17 00:00:00 2001 From: Andrew Senkevich Date: Thu, 18 Jun 2015 17:55:55 +0300 Subject: Vector sincos for x86_64 and tests. Here is implementation of vectorized sincos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI . * NEWS: Mention addition of x86_64 vector sincos. * bits/libm-simd-decl-stubs.h: Added stubs for sincos. * math/math.h (__MATHDECL_VEC): New macro. * math/bits/mathcalls.h: Added sincos declaration with __MATHDECL_VEC. * math/gen-libm-have-vector-test.sh: Added generation of sincos wrapper declaration under condition. * math/test-vec-loop.h (TEST_VEC_LOOP): Refactored. * math/test-double-vlen2.h: Added wrapper for sincos tests, reflected TEST_VEC_LOOP change. * math/test-double-vlen4.h: Likewise. * math/test-double-vlen8.h: Likewise. * math/test-float-vlen16.h: Reflected TEST_VEC_LOOP change. * math/test-float-vlen4.h: Likewise. * math/test-float-vlen8.h: Likewise. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New symbols added. * sysdeps/x86/fpu/bits/math-vector.h: Added sincos SIMD declaration. * 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_d_sincos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: Added wrappers for sincos. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Vector sincos tests. * sysdeps/x86_64/fpu/test-double-vlen2.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4-avx2-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4-avx2.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen8-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen8.c: Likewise. --- math/test-double-vlen2.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'math/test-double-vlen2.h') diff --git a/math/test-double-vlen2.h b/math/test-double-vlen2.h index 2e8415b16a..3f117e510f 100644 --- a/math/test-double-vlen2.h +++ b/math/test-double-vlen2.h @@ -44,6 +44,7 @@ #define WRAPPER_DECL(function) extern FLOAT function (FLOAT); #define WRAPPER_DECL_ff(function) extern FLOAT function (FLOAT, FLOAT); +#define WRAPPER_DECL_fFF(function) extern void function (FLOAT, FLOAT *, FLOAT *); // Wrapper from scalar to vector function with vector length 2. #define VECTOR_WRAPPER(scalar_func, vector_func) \ @@ -54,7 +55,8 @@ FLOAT scalar_func (FLOAT x) \ VEC_TYPE mx; \ INIT_VEC_LOOP (mx, x, 2); \ VEC_TYPE mr = vector_func (mx); \ - TEST_VEC_LOOP (2); \ + TEST_VEC_LOOP (mr, 2); \ + return ((FLOAT) mr[0]); \ } // Wrapper from scalar 2 argument function to vector one. @@ -67,5 +69,22 @@ FLOAT scalar_func (FLOAT x, FLOAT y) \ INIT_VEC_LOOP (mx, x, 2); \ INIT_VEC_LOOP (my, y, 2); \ VEC_TYPE mr = vector_func (mx, my); \ - TEST_VEC_LOOP (2); \ + TEST_VEC_LOOP (mr, 2); \ + return ((FLOAT) mr[0]); \ +} + +// Wrapper from scalar 3 argument function to vector one. +#define VECTOR_WRAPPER_fFF(scalar_func, vector_func) \ +extern void vector_func (VEC_TYPE, VEC_TYPE *, VEC_TYPE *); \ +void scalar_func (FLOAT x, FLOAT * r, FLOAT * r1) \ +{ \ + int i; \ + VEC_TYPE mx, mr, mr1; \ + INIT_VEC_LOOP (mx, x, 2); \ + vector_func (mx, &mr, &mr1); \ + TEST_VEC_LOOP (mr, 2); \ + TEST_VEC_LOOP (mr1, 2); \ + *r = (FLOAT) mr[0]; \ + *r1 = (FLOAT) mr1[0]; \ + return; \ } -- cgit 1.4.1