[PATCH] D129863: [PowerPC] Improve LowerVECTOR_SHUFFLE load-and-splat multi-use

ChenZheng via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Sun Jul 17 21:14:26 PDT 2022


shchenz added inline comments.


================
Comment at: llvm/test/CodeGen/PowerPC/load-and-splat.ll:1405
+
+define <8 x float> @test_splat_multiuseW(<8 x float>* %vp) {
+; P9-LABEL: test_splat_multiuseW:
----------------
Since you already post D129861, you can show diff based on D129861 and make this patch be a child of that patch.


================
Comment at: llvm/test/CodeGen/PowerPC/load-and-splat.ll:1475
+  %vec = load <8 x float>, <8 x float>* %vp
+  %res = shufflevector <8 x float> %vec, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 5, i32 0, i32 0, i32 0>
+  ret <8 x float> %res
----------------
Can we also get improvement for a normal vector type, like <4 x float> or <2 x double>?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D129863/new/

https://reviews.llvm.org/D129863



More information about the llvm-commits mailing list