[llvm] [MachineLICM] Hoist COPY instruction only when user can be hoisted (PR #81735)

[via llvm-commits]

================
@@ -0,0 +1,94 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 -O2 -vectorize-loops -vectorize-slp -amdgpu-early-inline-all=true -amdgpu-function-calls=false < %s | FileCheck %s
+target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-G1-ni:7:8:9-p9:192:256:256:32"
+target triple = "amdgcn-amd-amdhsa"
+
+define amdgpu_kernel void @_ZN6Kokkos4ImplL32hip_parallel_launch_local_memoryINS0_11ParallelForIN4Test7HexGradINS_3HIPEdfEENS_11RangePolicyIJS5_EEES5_EELj1024ELj1EEEvT_(ptr %.sroa.1.0.copyload, ptr %0, ptr %1, ptr %2, ptr %3, ptr %4, ptr %5, ptr %6, ptr %7, ptr %8, ptr %9, ptr %10, ptr %11, ptr %12, ptr %13, ptr %14, ptr %15, ptr %16, ptr %17, ptr %18, ptr %19, ptr %20, ptr %21, ptr %22, ptr %23, ptr %24, ptr %25, ptr %26, ptr %27, ptr %28, ptr %29, ptr %30, ptr %31, ptr %32, ptr %33, double %34, double %35, double %36, float %37, float %38, float %39, float %40, ptr %41) {
----------------
michaelselehov wrote:

Good point.

https://github.com/llvm/llvm-project/pull/81735