[PATCH] D56365: [X86] Use funnel shift intrinsics for the VBMI2 vshld/vshrd intrinsics.

[Simon Pilgrim via Phabricator via cfe-commits]

RKSimon added inline comments.


================
Comment at: test/CodeGen/avx512vlvbmi2-builtins.c:415
   // CHECK-LABEL: @test_mm256_mask_shldv_epi64
-  // CHECK: @llvm.x86.avx512.mask.vpshldv.q.256
+  // CHECK: @llvm.fshl.v4i64(<4 x i64> %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> 
%{{.*}})
   return _mm256_mask_shldv_epi64(__S, __U, __A, __B);
----------------
Missing CHECK for select? Same for other tests.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D56365/new/

https://reviews.llvm.org/D56365



_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits