Skip to content

R
riscv-gcc-1
Commit 8a6c8430 by Uros Bizjak Committed by Uros Bizjak
Options

re PR c++/35553 (-fkeep-inline-functions and -O errors out in SSE headers) 

	PR target/35553
	* config/i386/i386.h (TARGET_CPU_CPP_BUILTINS): Define
	__SSE_USE_INLINED_FUNC__ when using -flag-keep-inline-functions
	together with optimization.
	* config/i386/xmmintrin.h: Use __SSE_USE_INLINED_FUNC__ instead of
	__OPTIMIZE__ to choose between inlined intrinsic SSE function having
	immediate arguments and its equivalent macro definition.
	* config/i386/bmintrin.h: Ditto.
	* config/i386/smmintrin.h: Ditto.
	* config/i386/tmmintrin.h: Ditto.
	* config/i386/mmintrin-common.h: Ditto.
	* config/i386/ammintrin.h: Ditto.
	* config/i386/emmintrin.h: Ditto.

testsuite/ChangeLog:

	PR target/35553
	* g++.dg/other/i386-3.C: New test.

From-SVN: r133164
parent 22aee8c5
Showing with 60 additions and 26 deletions
gcc/ChangeLog
2008-03-13 Uros Bizjak <ubizjak@gmail.com>
PR target/35553
* config/i386/i386.h (TARGET_CPU_CPP_BUILTINS): Define
__SSE_USE_INLINED_FUNC__ when using -flag-keep-inline-functions
together with optimization.
* config/i386/xmmintrin.h: Use __SSE_USE_INLINED_FUNC__ instead of
__OPTIMIZE__ to choose between inlined intrinsic SSE function having
immediate arguments and its equivalent macro definition.
* config/i386/bmintrin.h: Ditto.
* config/i386/smmintrin.h: Ditto.
* config/i386/tmmintrin.h: Ditto.
* config/i386/mmintrin-common.h: Ditto.
* config/i386/ammintrin.h: Ditto.
* config/i386/emmintrin.h: Ditto.
2008-03-13 Jakub Jelinek <jakub@redhat.com>
PR middle-end/35185
......
gcc/config/i386/ammintrin.h
......@@ -55,7 +55,7 @@ _mm_extract_si64 (__m128i __X, __m128i __Y)
return (__m128i) __builtin_ia32_extrq ((__v2di) __X, (__v16qi) __Y);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_extracti_si64 (__m128i __X, unsigned const int __I, unsigned const int __L)
{
......@@ -73,7 +73,7 @@ _mm_insert_si64 (__m128i __X,__m128i __Y)
return (__m128i) __builtin_ia32_insertq ((__v2di)__X, (__v2di)__Y);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_inserti_si64(__m128i __X, __m128i __Y, unsigned const int __I, unsigned const int __L)
{
......
gcc/config/i386/bmmintrin.h
......@@ -350,7 +350,7 @@ _mm_rot_epi64(__m128i __A, __m128i __B)
/* Rotates - Immediate form */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_roti_epi8(__m128i __A, const int __B)
{
......
gcc/config/i386/emmintrin.h
......@@ -880,7 +880,7 @@ _mm_cvtss_sd (__m128d __A, __m128 __B)
return (__m128d)__builtin_ia32_cvtss2sd ((__v2df) __A, (__v4sf)__B);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128d __attribute__((__always_inline__, __artificial__))
_mm_shuffle_pd(__m128d __A, __m128d __B, const int __mask)
{
......@@ -1144,7 +1144,7 @@ _mm_srai_epi32 (__m128i __A, int __B)
return (__m128i)__builtin_ia32_psradi128 ((__v4si)__A, __B);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_srli_si128 (__m128i __A, const int __N)
{
......@@ -1307,7 +1307,7 @@ _mm_cmpgt_epi32 (__m128i __A, __m128i __B)
return (__m128i)__builtin_ia32_pcmpgtd128 ((__v4si)__A, (__v4si)__B);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline int __attribute__((__always_inline__, __artificial__))
_mm_extract_epi16 (__m128i const __A, int const __N)
{
......@@ -1363,7 +1363,7 @@ _mm_mulhi_epu16 (__m128i __A, __m128i __B)
return (__m128i)__builtin_ia32_pmulhuw128 ((__v8hi)__A, (__v8hi)__B);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_shufflehi_epi16 (__m128i __A, const int __mask)
{
......
gcc/config/i386/i386.h
......@@ -691,6 +691,11 @@ extern const char *host_detect_local_cpu (int argc, const char **argv);
builtin_define ("__SSE_MATH__"); \
if (TARGET_SSE_MATH && TARGET_SSE2) \
builtin_define ("__SSE2_MATH__"); \
\
/* Use inlined intrinsic SSE function having immediate \
arguments instead of a macro definition. */ \
if (optimize && !flag_keep_inline_functions) \
builtin_define ("__SSE_USE_INLINED_FUNC__"); \
} \
while (0)
......
gcc/config/i386/mmintrin-common.h
......@@ -92,7 +92,7 @@ _mm_testnzc_si128 (__m128i __M, __m128i __V)
/* Packed/scalar double precision floating point rounding. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128d __attribute__((__always_inline__, __artificial__))
_mm_round_pd (__m128d __V, const int __M)
{
......@@ -117,7 +117,7 @@ _mm_round_sd(__m128d __D, __m128d __V, const int __M)
/* Packed/scalar single precision floating point rounding. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128 __attribute__((__always_inline__, __artificial__))
_mm_round_ps (__m128 __V, const int __M)
{
......
gcc/config/i386/smmintrin.h
......@@ -44,7 +44,7 @@
/* Integer blend instructions - select data from 2 sources using
constant/variable mask. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
{
......@@ -69,7 +69,7 @@ _mm_blendv_epi8 (__m128i __X, __m128i __Y, __m128i __M)
/* Single precision floating point blend instructions - select data
from 2 sources using constant/variable mask. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128 __attribute__((__always_inline__, __artificial__))
_mm_blend_ps (__m128 __X, __m128 __Y, const int __M)
{
......@@ -94,7 +94,7 @@ _mm_blendv_ps (__m128 __X, __m128 __Y, __m128 __M)
/* Double precision floating point blend instructions - select data
from 2 sources using constant/variable mask. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128d __attribute__((__always_inline__, __artificial__))
_mm_blend_pd (__m128d __X, __m128d __Y, const int __M)
{
......@@ -119,7 +119,7 @@ _mm_blendv_pd (__m128d __X, __m128d __Y, __m128d __M)
/* Dot product instructions with mask-defined summing and zeroing parts
of result. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128 __attribute__((__always_inline__, __artificial__))
_mm_dp_ps (__m128 __X, __m128 __Y, const int __M)
{
......@@ -224,7 +224,7 @@ _mm_mul_epi32 (__m128i __X, __m128i __Y)
index, the bits [5-4] define D index, and bits [3-0] define
zeroing mask for D. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128 __attribute__((__always_inline__, __artificial__))
_mm_insert_ps (__m128 __D, __m128 __S, const int __N)
{
......@@ -244,7 +244,7 @@ _mm_insert_ps (__m128 __D, __m128 __S, const int __N)
/* Extract binary representation of single precision float from packed
single precision array element of X selected by index N. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline int __attribute__((__always_inline__, __artificial__))
_mm_extract_ps (__m128 __X, const int __N)
{
......@@ -277,7 +277,7 @@ _mm_extract_ps (__m128 __X, const int __N)
/* Insert integer, S, into packed integer array element of D
selected by index N. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_insert_epi8 (__m128i __D, int __S, const int __N)
{
......@@ -319,7 +319,7 @@ _mm_insert_epi64 (__m128i __D, long long __S, const int __N)
/* Extract integer from packed integer array element of X selected by
index N. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline int __attribute__((__always_inline__, __artificial__))
_mm_extract_epi8 (__m128i __X, const int __N)
{
......@@ -447,7 +447,7 @@ _mm_packus_epi32 (__m128i __X, __m128i __Y)
byte integers in the first 2 operands. Starting offsets within
operands are determined by the 3rd mask operand. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_mpsadbw_epu8 (__m128i __X, __m128i __Y, const int __M)
{
......@@ -497,7 +497,7 @@ _mm_stream_load_si128 (__m128i *__X)
/* Intrinsics for text/string processing. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_cmpistrm (__m128i __X, __m128i __Y, const int __M)
{
......@@ -550,7 +550,7 @@ _mm_cmpestri (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
/* Intrinsics for text/string processing and reading values of
EFlags. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline int __attribute__((__always_inline__, __artificial__))
_mm_cmpistra (__m128i __X, __m128i __Y, const int __M)
{
......
gcc/config/i386/tmmintrin.h
......@@ -181,7 +181,7 @@ _mm_sign_pi32 (__m64 __X, __m64 __Y)
return (__m64) __builtin_ia32_psignd ((__v2si)__X, (__v2si)__Y);
}
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128i __attribute__((__always_inline__, __artificial__))
_mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
{
......
gcc/config/i386/xmmintrin.h
......@@ -716,7 +716,7 @@ _mm_cvtps_pi8(__m128 __A)
}
/* Selects four specific SPFP values from A and B based on MASK. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m128 __attribute__((__always_inline__, __artificial__))
_mm_shuffle_ps (__m128 __A, __m128 __B, int const __mask)
{
......@@ -992,7 +992,7 @@ _mm_move_ss (__m128 __A, __m128 __B)
}
/* Extracts one of the four words of A. The selector N must be immediate. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline int __attribute__((__always_inline__, __artificial__))
_mm_extract_pi16 (__m64 const __A, int const __N)
{
......@@ -1013,7 +1013,7 @@ _m_pextrw (__m64 const __A, int const __N)
/* Inserts word D into one of four words of A. The selector N must be
immediate. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m64 __attribute__((__always_inline__, __artificial__))
_mm_insert_pi16 (__m64 const __A, int const __D, int const __N)
{
......@@ -1114,7 +1114,7 @@ _m_pmulhuw (__m64 __A, __m64 __B)
/* Return a combination of the four 16-bit values in A. The selector
must be an immediate. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline __m64 __attribute__((__always_inline__, __artificial__))
_mm_shuffle_pi16 (__m64 __A, int const __N)
{
......@@ -1191,7 +1191,7 @@ _m_psadbw (__m64 __A, __m64 __B)
/* Loads one cache line from address P to a location "closer" to the
processor. The selector I specifies the type of prefetch operation. */
#ifdef __OPTIMIZE__
#ifdef __SSE_USE_INLINED_FUNC__
static __inline void __attribute__((__always_inline__, __artificial__))
_mm_prefetch (const void *__P, enum _mm_hint __I)
{
......
gcc/testsuite/ChangeLog
2008-03-13 Uros Bizjak <ubizjak@gmail.com>
PR target/35553
* g++.dg/other/i386-3.C: New test.
2008-03-13 Paolo Bonzini <bonzini@gnu.org>
PR tree-opt/35422
gcc/testsuite/g++.dg/other/i386-3.C 0 → 100644
/* Test that {,x,e,p,t,s,a,b}mmintrin.h, mm3dnow.h and mm_malloc.h are
usable with -O -fkeep-inline-functions. */
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -msse4 -msse5" } */
#include <bmmintrin.h>
#include <smmintrin.h>
#include <mm3dnow.h>
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment