[llvm] [AMDGPU] Enable amdgpu-sw-lower-lds pass to lower LDS accesses to use device global memory (PR #87265)

[via llvm-commits]

================
@@ -0,0 +1,61 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes=amdgpu-sw-lower-lds -S -mtriple=amdgcn-- | FileCheck %s
+
+; Test to check if LDS accesses are lowered correctly when LDS is passed as function
+; argument to non-kernel.
+
+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-p9:192:256:256:32-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"
+target triple = "amdgcn-unknown-unknown"
+
+ at lds_var = internal addrspace(3) global [1024 x i32] poison, align 4
+
+define void @my_function(ptr addrspace(3) %lds_arg) {
+; CHECK-LABEL: define void @my_function(
+; CHECK-SAME: ptr addrspace(3) [[LDS_ARG:%.*]]) {
+; CHECK-NEXT:    [[LDS_VAL:%.*]] = load i32, ptr addrspace(3) [[LDS_ARG]], align 4
+; CHECK-NEXT:    [[NEW_LDS_VAL:%.*]] = add i32 [[LDS_VAL]], 1
+; CHECK-NEXT:    store i32 [[NEW_LDS_VAL]], ptr addrspace(3) [[LDS_ARG]], align 4
+; CHECK-NEXT:    ret void
+;
+  %lds_val = load i32, ptr addrspace(3) %lds_arg, align 4
+  %new_lds_val = add i32 %lds_val, 1
+  store i32 %new_lds_val, ptr addrspace(3) %lds_arg, align 4
+  ret void
+}
+
+define amdgpu_kernel void @my_kernel() {
+; CHECK-LABEL: define amdgpu_kernel void @my_kernel() {
+; CHECK-NEXT:  WId:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[TMP3:%.*]] = or i32 [[TMP0]], [[TMP1]]
----------------
skc7 wrote:

Added utility method from amdgpu-lower-module-lds pass to AMDGPUMemoryUtils and removed amdgpu-no-workitem-id-* attributes from kernels which access LDS.

https://github.com/llvm/llvm-project/pull/87265