Hi , Yes, I saw the thread. We have an internal discussion on this subject.
Regards, Michael Zuckerman From: tha...@google.com [mailto:tha...@google.com] On Behalf Of Nico Weber Sent: Monday, May 16, 2016 22:06 To: Zuckerman, Michael <michael.zucker...@intel.com> Cc: cfe-commits <cfe-commits@lists.llvm.org> Subject: Re: r269680 - [Clang][AVX512] completing missing intrinsics for [vpabs] instruction set Hi Michael, have you see then trhead "The intrinsics headers (especially avx512) are too big. What to do about it?"? Can you maybe comment on it? Thanks, Nico On Mon, May 16, 2016 at 2:57 PM, Michael Zuckerman via cfe-commits <cfe-commits@lists.llvm.org<mailto:cfe-commits@lists.llvm.org>> wrote: Author: mzuckerm Date: Mon May 16 13:57:24 2016 New Revision: 269680 URL: http://llvm.org/viewvc/llvm-project?rev=269680&view=rev Log: [Clang][AVX512] completing missing intrinsics for [vpabs] instruction set Differential Revision: http://reviews.llvm.org/D20069 Modified: cfe/trunk/lib/Headers/avx512fintrin.h cfe/trunk/test/CodeGen/avx512f-builtins.c Modified: cfe/trunk/lib/Headers/avx512fintrin.h URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Headers/avx512fintrin.h?rev=269680&r1=269679&r2=269680&view=diff ============================================================================== --- cfe/trunk/lib/Headers/avx512fintrin.h (original) +++ cfe/trunk/lib/Headers/avx512fintrin.h Mon May 16 13:57:24 2016 @@ -1631,6 +1631,23 @@ _mm512_abs_epi64(__m512i __A) (__mmask8) -1); } +static __inline__ __m512i __DEFAULT_FN_ATTRS +_mm512_mask_abs_epi64 (__m512i __W, __mmask8 __U, __m512i __A) +{ + return (__m512i) __builtin_ia32_pabsq512_mask ((__v8di) __A, + (__v8di) __W, + (__mmask8) __U); +} + +static __inline__ __m512i __DEFAULT_FN_ATTRS +_mm512_maskz_abs_epi64 (__mmask8 __U, __m512i __A) +{ + return (__m512i) __builtin_ia32_pabsq512_mask ((__v8di) __A, + (__v8di) + _mm512_setzero_si512 (), + (__mmask8) __U); +} + static __inline __m512i __DEFAULT_FN_ATTRS _mm512_abs_epi32(__m512i __A) { @@ -1640,6 +1657,23 @@ _mm512_abs_epi32(__m512i __A) (__mmask16) -1); } +static __inline__ __m512i __DEFAULT_FN_ATTRS +_mm512_mask_abs_epi32 (__m512i __W, __mmask16 __U, __m512i __A) +{ + return (__m512i) __builtin_ia32_pabsd512_mask ((__v16si) __A, + (__v16si) __W, + (__mmask16) __U); +} + +static __inline__ __m512i __DEFAULT_FN_ATTRS +_mm512_maskz_abs_epi32 (__mmask16 __U, __m512i __A) +{ + return (__m512i) __builtin_ia32_pabsd512_mask ((__v16si) __A, + (__v16si) + _mm512_setzero_si512 (), + (__mmask16) __U); +} + static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_mask_add_ss(__m128 __W, __mmask8 __U,__m128 __A, __m128 __B) { return (__m128) __builtin_ia32_addss_round_mask ((__v4sf) __A, Modified: cfe/trunk/test/CodeGen/avx512f-builtins.c URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGen/avx512f-builtins.c?rev=269680&r1=269679&r2=269680&view=diff ============================================================================== --- cfe/trunk/test/CodeGen/avx512f-builtins.c (original) +++ cfe/trunk/test/CodeGen/avx512f-builtins.c Mon May 16 13:57:24 2016 @@ -6574,3 +6574,30 @@ __m512 test_mm512_set_ps (float __A, flo __I, __J, __K, __L, __M, __N, __O, __P); } +__m512i test_mm512_mask_abs_epi64 (__m512i __W, __mmask8 __U, __m512i __A) +{ + // CHECK-LABEL: @test_mm512_mask_abs_epi64 + // CHECK: @llvm.x86.avx512.mask.pabs.q.512 + return _mm512_mask_abs_epi64 (__W,__U,__A); +} + +__m512i test_mm512_maskz_abs_epi64 (__mmask8 __U, __m512i __A) +{ + // CHECK-LABEL: @test_mm512_maskz_abs_epi64 + // CHECK: @llvm.x86.avx512.mask.pabs.q.512 + return _mm512_maskz_abs_epi64 (__U,__A); +} + +__m512i test_mm512_mask_abs_epi32 (__m512i __W, __mmask16 __U, __m512i __A) +{ + // CHECK-LABEL: @test_mm512_mask_abs_epi32 + // CHECK: @llvm.x86.avx512.mask.pabs.d.512 + return _mm512_mask_abs_epi32 (__W,__U,__A); +} + +__m512i test_mm512_maskz_abs_epi32 (__mmask16 __U, __m512i __A) +{ + // CHECK-LABEL: @test_mm512_maskz_abs_epi32 + // CHECK: @llvm.x86.avx512.mask.pabs.d.512 + return _mm512_maskz_abs_epi32 (__U,__A); +} _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org<mailto:cfe-commits@lists.llvm.org> http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits --------------------------------------------------------------------- Intel Israel (74) Limited This e-mail and any attachments may contain confidential material for the sole use of the intended recipient(s). Any review or distribution by others is strictly prohibited. If you are not the intended recipient, please contact the sender and delete all copies.
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
