about summary refs log tree commit diff
path: root/math/test-float-vlen4.h
diff options
context:
space:
mode:
authorAndrew Senkevich <andrew.senkevich@intel.com>2015-06-18 17:55:55 +0300
committerAndrew Senkevich <andrew.senkevich@intel.com>2015-06-18 17:55:55 +0300
commitc9a8c526acd185176e486bee4624039740f8c435 (patch)
tree1f199d8fb0bb0ce9b0bdb21c86c3c213a514c22a /math/test-float-vlen4.h
parent8aa92022e2e7cb5470b6e252020140c05b8013ed (diff)
downloadglibc-c9a8c526acd185176e486bee4624039740f8c435.tar.gz
glibc-c9a8c526acd185176e486bee4624039740f8c435.tar.xz
glibc-c9a8c526acd185176e486bee4624039740f8c435.zip
Vector sincos for x86_64 and tests.
Here is implementation of vectorized sincos containing SSE, AVX,
AVX2 and AVX512 versions according to Vector ABI
<https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>.

    * 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.
Diffstat (limited to 'math/test-float-vlen4.h')
-rw-r--r--math/test-float-vlen4.h6
1 files changed, 4 insertions, 2 deletions
diff --git a/math/test-float-vlen4.h b/math/test-float-vlen4.h
index eaf4b4b13e..f5e530b756 100644
--- a/math/test-float-vlen4.h
+++ b/math/test-float-vlen4.h
@@ -54,7 +54,8 @@ FLOAT scalar_func (FLOAT x)			\
   VEC_TYPE mx;					\
   INIT_VEC_LOOP (mx, x, 4);			\
   VEC_TYPE mr = vector_func (mx);		\
-  TEST_VEC_LOOP (4);				\
+  TEST_VEC_LOOP (mr, 4);			\
+  return ((FLOAT) mr[0]);			\
 }
 
 // Wrapper from scalar 2 argument function to vector one.
@@ -67,5 +68,6 @@ FLOAT scalar_func (FLOAT x, FLOAT y)		\
   INIT_VEC_LOOP (mx, x, 4);			\
   INIT_VEC_LOOP (my, y, 4);			\
   VEC_TYPE mr = vector_func (mx, my);		\
-  TEST_VEC_LOOP (4);				\
+  TEST_VEC_LOOP (mr, 4);			\
+  return ((FLOAT) mr[0]);			\
 }