diff options
| author | Kirill Yukhin <kirill.yukhin@intel.com> | 2014-01-14 06:21:06 +0000 |
|---|---|---|
| committer | Kirill Yukhin <kyukhin@gcc.gnu.org> | 2014-01-14 06:21:06 +0000 |
| commit | c56a42b9bedfbedef3fc1c1a86e7594d52ea2aa4 (patch) | |
| tree | 470c6de9ea5210430e48b4be6c4cf9b55623de2f /gcc/config/i386/avx512fintrin.h | |
| parent | e5e46f5ee53d9969b2d625b4d4e805a06584ca71 (diff) | |
| download | gcc-c56a42b9bedfbedef3fc1c1a86e7594d52ea2aa4.zip gcc-c56a42b9bedfbedef3fc1c1a86e7594d52ea2aa4.tar.gz gcc-c56a42b9bedfbedef3fc1c1a86e7594d52ea2aa4.tar.bz2 | |
avx512erintrin.h (_mm_rcp28_round_sd): New.
gcc/
* config/i386/avx512erintrin.h (_mm_rcp28_round_sd): New.
(_mm_rcp28_round_ss): Ditto.
(_mm_rsqrt28_round_sd): Ditto.
(_mm_rsqrt28_round_ss): Ditto.
(_mm_rcp28_sd): Ditto.
(_mm_rcp28_ss): Ditto.
(_mm_rsqrt28_sd): Ditto.
(_mm_rsqrt28_ss): Ditto.
* config/i386/avx512fintrin.h (_mm512_stream_load_si512): Ditto.
* config/i386/i386-builtin-types.def (V8DI_FTYPE_PV8DI): Ditto.
* config/i386/i386.c (IX86_BUILTIN_MOVNTDQA512): Ditto.
(IX86_BUILTIN_RCP28SD): Ditto.
(IX86_BUILTIN_RCP28SS): Ditto.
(IX86_BUILTIN_RSQRT28SD): Ditto.
(IX86_BUILTIN_RSQRT28SS): Ditto.
(bdesc_special_args): Define __builtin_ia32_movntdqa512,
__builtin_ia32_rcp28sd_round, __builtin_ia32_rcp28ss_round,
__builtin_ia32_rsqrt28sd_round, __builtin_ia32_rsqrt28ss_round.
(ix86_expand_special_args_builtin): Expand new FTYPE.
* config/i386/sse.md (define_mode_attr "sse4_1_avx2"): Expand to V8DI.
(srcp14<mode>): Make insn unary.
(avx512f_vmscalef<mode><round_name>): Use substed predicate.
(avx512f_sgetexp<mode><round_saeonly_name>): Ditto.
(avx512f_rndscale<mode><round_saeonly_name>): Ditto.
(<sse4_1_avx2>_movntdqa): Extend to 512 bits.
(avx512er_exp2<mode><mask_name><round_saeonly_name>):
Fix rounding: make it SAE only.
(<mask_codefor>avx512er_rcp28<mode><mask_name><round_saeonly_name>): Ditto.
(<mask_codefor>avx512er_rsqrt28<mode><mask_name><round_saeonly_name>): Ditto.
(avx512er_vmrcp28<mode><round_saeonly_name>): Ditto.
(avx512er_vmrsqrt28<mode><round_saeonly_name>): Ditto.
(avx512f_getmant<mode><mask_name><round_saeonly_name>): Ditto.
* config/i386/subst.md (round_saeonly_mask_scalar_operand3): Remove.
(round_saeonly_mask_scalar_operand4): Ditto.
(round_saeonly_mask_scalar_op3): Ditto.
(round_saeonly_mask_scalar_op4): Ditto.
gcc/testsuite/
* gcc.target/i386/avx-1.c: Fix __builtin_ia32_exp2ps_mask,
__builtin_ia32_exp2pd_mask, __builtin_ia32_rcp28ps_mask,
__builtin_ia32_rcp28pd_mask, __builtin_ia32_rsqrt28ps_mask,
__builtin_ia32_rsqrt28pd_mask. Add __builtin_ia32_rcp28ss_round,
__builtin_ia32_rcp28sd_round, __builtin_ia32_rsqrt28ss_round,
__builtin_ia32_rsqrt28sd_round.
* gcc.target/i386/avx512er-vexp2pd-1.c: Fix rounding mode.
* gcc.target/i386/avx512er-vexp2ps-1.c: Ditto.
* gcc.target/i386/avx512er-vrcp28pd-1.c: Ditto.
* gcc.target/i386/avx512er-vrcp28ps-1.c: Ditto.
* gcc.target/i386/avx512er-vrsqrt28pd-1.c: Ditto.
* gcc.target/i386/avx512er-vrsqrt28ps-1.c: Ditto.
* gcc.target/i386/avx512er-vrcp28sd-1.c: New.
* gcc.target/i386/avx512er-vrcp28sd-2.c: Ditto.
* gcc.target/i386/avx512er-vrcp28ss-1.c: Ditto.
* gcc.target/i386/avx512er-vrcp28ss-2.c: Ditto.
* gcc.target/i386/avx512er-vrsqrt28sd-1.c: Ditto.
* gcc.target/i386/avx512er-vrsqrt28sd-2.c: Ditto.
* gcc.target/i386/avx512er-vrsqrt28ss-1.c: Ditto.
* gcc.target/i386/avx512er-vrsqrt28ss-2.c: Ditto.
* gcc.target/i386/avx512f-vmovntdqa-1.c: Ditto.
* gcc.target/i386/avx512f-vmovntdqa-2.c: Ditto.
* gcc.target/i386/avx512f-vrcp14sd-2.c: Fix.
* gcc.target/i386/avx512f-vrcp14ss-2.c: Ditto.
* gcc.target/i386/sse-22.c: Extend with new built-ins,
fix wrong rounding mode (see above).
* gcc.target/i386/sse-23.c: Ditto.
From-SVN: r206596
Diffstat (limited to 'gcc/config/i386/avx512fintrin.h')
| -rw-r--r-- | gcc/config/i386/avx512fintrin.h | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h index a2ee88e..26f8cb6 100644 --- a/gcc/config/i386/avx512fintrin.h +++ b/gcc/config/i386/avx512fintrin.h @@ -7809,6 +7809,13 @@ _mm512_stream_pd (double *__P, __m512d __A) __builtin_ia32_movntpd512 (__P, (__v8df) __A); } +extern __inline __m512i +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm512_stream_load_si512 (void *__P) +{ + return __builtin_ia32_movntdqa512 ((__v8di *)__P); +} + #ifdef __OPTIMIZE__ extern __inline __m128 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) |