aboutsummaryrefslogtreecommitdiff
path: root/math
diff options
context:
space:
mode:
authorAndrew Senkevich <andrew.senkevich@intel.com>2015-06-18 17:04:07 +0300
committerAndrew Senkevich <andrew.senkevich@intel.com>2015-06-18 17:04:07 +0300
commit8aa92022e2e7cb5470b6e252020140c05b8013ed (patch)
treedfedc663faa6a67fee4bd9a65ec2227fc0e4c534 /math
parent2f3184451dc9daf8c15be10f190071409d93232e (diff)
downloadglibc-8aa92022e2e7cb5470b6e252020140c05b8013ed.tar
glibc-8aa92022e2e7cb5470b6e252020140c05b8013ed.tar.gz
glibc-8aa92022e2e7cb5470b6e252020140c05b8013ed.tar.bz2
glibc-8aa92022e2e7cb5470b6e252020140c05b8013ed.zip
Vector powf for x86_64 and tests.
Here is implementation of vectorized powf 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 powf. * 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/svml_s_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S: New file. * sysdeps/x86_64/fpu/svml_s_powf16_core.S: New file. * sysdeps/x86_64/fpu/svml_s_powf4_core.S: New file. * sysdeps/x86_64/fpu/svml_s_powf8_core.S: New file. * sysdeps/x86_64/fpu/svml_s_powf8_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_s_powf_data.S: New file. * sysdeps/x86_64/fpu/svml_s_powf_data.h: New file. * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Vector powf 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. * math/test-float-vlen16.h: Fixed 2 argument macro. * math/test-float-vlen4.h: Likewise. * math/test-float-vlen8.h: Likewise. * NEWS: Mention addition of x86_64 vector powf.
Diffstat (limited to 'math')
-rw-r--r--math/test-float-vlen16.h4
-rw-r--r--math/test-float-vlen4.h4
-rw-r--r--math/test-float-vlen8.h4
3 files changed, 6 insertions, 6 deletions
diff --git a/math/test-float-vlen16.h b/math/test-float-vlen16.h
index 5c0a7a484f..008e15ea13 100644
--- a/math/test-float-vlen16.h
+++ b/math/test-float-vlen16.h
@@ -58,8 +58,8 @@ FLOAT scalar_func (FLOAT x) \
}
// Wrapper from scalar 2 argument function to vector one.
-#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
-extern VEC_TYPE vector_func (VEC_TYPE); \
+#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
+extern VEC_TYPE vector_func (VEC_TYPE, VEC_TYPE); \
FLOAT scalar_func (FLOAT x, FLOAT y) \
{ \
int i; \
diff --git a/math/test-float-vlen4.h b/math/test-float-vlen4.h
index 09485bccca..eaf4b4b13e 100644
--- a/math/test-float-vlen4.h
+++ b/math/test-float-vlen4.h
@@ -58,8 +58,8 @@ FLOAT scalar_func (FLOAT x) \
}
// Wrapper from scalar 2 argument function to vector one.
-#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
-extern VEC_TYPE vector_func (VEC_TYPE); \
+#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
+extern VEC_TYPE vector_func (VEC_TYPE, VEC_TYPE); \
FLOAT scalar_func (FLOAT x, FLOAT y) \
{ \
int i; \
diff --git a/math/test-float-vlen8.h b/math/test-float-vlen8.h
index d309931c4c..1a2eb52318 100644
--- a/math/test-float-vlen8.h
+++ b/math/test-float-vlen8.h
@@ -58,8 +58,8 @@ FLOAT scalar_func (FLOAT x) \
}
// Wrapper from scalar 2 argument function to vector one.
-#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
-extern VEC_TYPE vector_func (VEC_TYPE); \
+#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
+extern VEC_TYPE vector_func (VEC_TYPE, VEC_TYPE); \
FLOAT scalar_func (FLOAT x, FLOAT y) \
{ \
int i; \