[PATCH] D71956: [X86] Improve v2i64->v2f32 and v4i64->v4f32 uint_to_fp on avx and avx2 targets.

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:29103
+      }
+      IsNeg = DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, IsNeg);
+      IsNeg =
----------------
DAG.getBitcast


================
Comment at: llvm/test/CodeGen/X86/vec-strict-inttofp-256.ll:649
+; AVX1-64-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-64-NEXT:    vpcmpgtq %ymm0, %ymm1, %ymm1
+; AVX1-64-NEXT:    vpbroadcastq {{.*#+}} ymm2 = [1,1,1,1]
----------------
AVX1 is using vpcmpgtq for ymm ?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D71956/new/

https://reviews.llvm.org/D71956