From a6336cc446a7ed682cb9dbc47cc56ebf9f9a4229 Mon Sep 17 00:00:00 2001
From: Andrew Senkevich <andrew.senkevich@intel.com>
Date: Thu, 18 Jun 2015 20:11:27 +0300
Subject: Vector sincosf for x86_64 and tests.

Here is implementation of vectorized sincosf 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 sincosf.
    * math/test-float-vlen16.h: Added wrapper for sincosf tests.
    * 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 sincosf 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_s_sincosf16_core.S
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core.S
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core.S
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S
    * sysdeps/x86_64/fpu/svml_s_sincosf16_core.S
    * sysdeps/x86_64/fpu/svml_s_sincosf4_core.S
    * sysdeps/x86_64/fpu/svml_s_sincosf8_core.S
    * sysdeps/x86_64/fpu/svml_s_sincosf8_core_avx.S
    * sysdeps/x86_64/fpu/svml_s_sincosf_data.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sincosf_data.h: New file.
    * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h: Added 3 argument wrappers.
    * sysdeps/x86_64/fpu/test-float-vlen16.c: : Vector sincosf tests.
    * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.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 | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'math/test-float-vlen16.h')

diff --git a/math/test-float-vlen16.h b/math/test-float-vlen16.h
index 802ae7bda2..b1890f3740 100644
--- a/math/test-float-vlen16.h
+++ b/math/test-float-vlen16.h
@@ -44,6 +44,7 @@
 
 #define WRAPPER_DECL(func) extern FLOAT func (FLOAT x);
 #define WRAPPER_DECL_ff(func) extern FLOAT func (FLOAT x, FLOAT y);
+#define WRAPPER_DECL_fFF(function) extern void function (FLOAT, FLOAT *, FLOAT *);
 
 // Wrapper from scalar to vector function with vector length 16.
 #define VECTOR_WRAPPER(scalar_func, vector_func) \
@@ -71,3 +72,19 @@ FLOAT scalar_func (FLOAT x, FLOAT y)		\
   TEST_VEC_LOOP (mr, 16);			\
   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, 16);			\
+  vector_func (mx, &mr, &mr1);			\
+  TEST_VEC_LOOP (mr, 16);			\
+  TEST_VEC_LOOP (mr1, 16);			\
+  *r = (FLOAT) mr[0];				\
+  *r1 = (FLOAT) mr1[0];				\
+  return;					\
+}
-- 
cgit v1.2.3