| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py |
| ; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=module | FileCheck -check-prefixes=CHECK,M_OR_HY %s |
| ; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=table | FileCheck -check-prefixes=CHECK,TABLE %s |
| ; RUN: not --crash opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=kernel 2>&1 | FileCheck -check-prefixes=KERNEL %s |
| ; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=hybrid | FileCheck -check-prefixes=CHECK,M_OR_HY %s |
| |
| ;; Two kernels access the same variable, specialisation gives them each their own copy of it |
| |
| @kernel.lds = addrspace(3) global i8 undef |
| define amdgpu_kernel void @k0() { |
| ; CHECK-LABEL: @k0( |
| ; CHECK-NEXT: [[LD:%.*]] = load i8, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 1 |
| ; CHECK-NEXT: [[MUL:%.*]] = mul i8 [[LD]], 2 |
| ; CHECK-NEXT: store i8 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 1 |
| ; CHECK-NEXT: ret void |
| ; |
| %ld = load i8, ptr addrspace(3) @kernel.lds |
| %mul = mul i8 %ld, 2 |
| store i8 %mul, ptr addrspace(3) @kernel.lds |
| ret void |
| } |
| |
| define amdgpu_kernel void @k1() { |
| ; CHECK-LABEL: @k1( |
| ; CHECK-NEXT: [[LD:%.*]] = load i8, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, align 1 |
| ; CHECK-NEXT: [[MUL:%.*]] = mul i8 [[LD]], 3 |
| ; CHECK-NEXT: store i8 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, align 1 |
| ; CHECK-NEXT: ret void |
| ; |
| %ld = load i8, ptr addrspace(3) @kernel.lds |
| %mul = mul i8 %ld, 3 |
| store i8 %mul, ptr addrspace(3) @kernel.lds |
| ret void |
| } |
| |
| ;; Function accesses variable, reachable from two kernels, can't use kernel lowering for either |
| ;; Hybrid can put it in module lds without cost as the first variable is free |
| |
| ; KERNEL: LLVM ERROR: cannot lower LDS 'function.lds' to kernel access as it is reachable from multiple kernels |
| |
| @function.lds = addrspace(3) global i16 undef |
| define void @f0() { |
| ; M_OR_HY-LABEL: @f0( |
| ; M_OR_HY-NEXT: [[LD:%.*]] = load i16, ptr addrspace(3) @llvm.amdgcn.module.lds, align 2 |
| ; M_OR_HY-NEXT: [[MUL:%.*]] = mul i16 [[LD]], 4 |
| ; M_OR_HY-NEXT: store i16 [[MUL]], ptr addrspace(3) @llvm.amdgcn.module.lds, align 2 |
| ; M_OR_HY-NEXT: ret void |
| ; |
| ; TABLE-LABEL: @f0( |
| ; TABLE-NEXT: [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id() |
| ; TABLE-NEXT: [[FUNCTION_LDS2:%.*]] = getelementptr inbounds [2 x [1 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 0 |
| ; TABLE-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(4) [[FUNCTION_LDS2]], align 4 |
| ; TABLE-NEXT: [[FUNCTION_LDS3:%.*]] = inttoptr i32 [[TMP2]] to ptr addrspace(3) |
| ; TABLE-NEXT: [[LD:%.*]] = load i16, ptr addrspace(3) [[FUNCTION_LDS3]], align 2 |
| ; TABLE-NEXT: [[MUL:%.*]] = mul i16 [[LD]], 4 |
| ; TABLE-NEXT: [[FUNCTION_LDS:%.*]] = getelementptr inbounds [2 x [1 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 0 |
| ; TABLE-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(4) [[FUNCTION_LDS]], align 4 |
| ; TABLE-NEXT: [[FUNCTION_LDS1:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3) |
| ; TABLE-NEXT: store i16 [[MUL]], ptr addrspace(3) [[FUNCTION_LDS1]], align 2 |
| ; TABLE-NEXT: ret void |
| ; |
| %ld = load i16, ptr addrspace(3) @function.lds |
| %mul = mul i16 %ld, 4 |
| store i16 %mul, ptr addrspace(3) @function.lds |
| ret void |
| } |
| |
| |
| define amdgpu_kernel void @k0_f0() { |
| ; M_OR_HY-LABEL: @k0_f0( |
| ; M_OR_HY-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ] |
| ; M_OR_HY-NEXT: call void @f0() |
| ; M_OR_HY-NEXT: ret void |
| ; |
| ; TABLE-LABEL: @k0_f0( |
| ; TABLE-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0_f0.lds) ] |
| ; TABLE-NEXT: call void @f0() |
| ; TABLE-NEXT: ret void |
| ; |
| call void @f0() |
| ret void |
| } |
| |
| define amdgpu_kernel void @k1_f0() { |
| ; M_OR_HY-LABEL: @k1_f0( |
| ; M_OR_HY-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ] |
| ; M_OR_HY-NEXT: call void @f0() |
| ; M_OR_HY-NEXT: ret void |
| ; |
| ; TABLE-LABEL: @k1_f0( |
| ; TABLE-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k1_f0.lds) ] |
| ; TABLE-NEXT: call void @f0() |
| ; TABLE-NEXT: ret void |
| ; |
| call void @f0() |
| ret void |
| } |