From d497b855a65198edb6435bccdc20094d2fa4fc79 Mon Sep 17 00:00:00 2001
From: Jakub Kuderski <jakub@nod-labs.com>
Date: Tue, 5 Dec 2023 19:24:41 -0500
Subject: [PATCH] [LLVMGPU] Add multi-row vector reduction configuration (#73)

This is to speed up matvec. The new configuration is experimental and
only applied on ROCm targets.
---
 .../iree/compiler/Codegen/Common/GPU/VectorReductionToGPU.cpp   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/compiler/src/iree/compiler/Codegen/Common/GPU/VectorReductionToGPU.cpp b/compiler/src/iree/compiler/Codegen/Common/GPU/VectorReductionToGPU.cpp
index 9c7a3d7b55dd2..dfcba93867b1b 100644
--- a/compiler/src/iree/compiler/Codegen/Common/GPU/VectorReductionToGPU.cpp
+++ b/compiler/src/iree/compiler/Codegen/Common/GPU/VectorReductionToGPU.cpp
@@ -196,7 +196,7 @@ class VectorReductionToGPUPass
       bool expandSubgroupReduction,
       std::function<int(func::FuncOp)> getWarpSize)
       : expandSubgroupReduction(expandSubgroupReduction),
-        getWarpSize(getWarpSize) {}
+        getWarpSize(std::move(getWarpSize)) {}
 
   void getDependentDialects(DialectRegistry &registry) const override {
     registry.insert<scf::SCFDialect, memref::MemRefDialect, gpu::GPUDialect,