diff options
Diffstat (limited to 'test/OpenMP/nvptx_teams_reduction_codegen.cpp')
| -rw-r--r-- | test/OpenMP/nvptx_teams_reduction_codegen.cpp | 1143 |
1 files changed, 1143 insertions, 0 deletions
diff --git a/test/OpenMP/nvptx_teams_reduction_codegen.cpp b/test/OpenMP/nvptx_teams_reduction_codegen.cpp new file mode 100644 index 000000000000..ae129ebfae4d --- /dev/null +++ b/test/OpenMP/nvptx_teams_reduction_codegen.cpp @@ -0,0 +1,1143 @@ +// Test target codegen - host bc file has to be created first. +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 +// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 +// expected-no-diagnostics +#ifndef HEADER +#define HEADER + +// Check for the data transfer medium in shared memory to transfer the reduction list to the first warp. +// CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = common addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i64] + +// Check that the execution mode of all 3 target regions is set to Generic Mode. +// CHECK-DAG: {{@__omp_offloading_.+l27}}_exec_mode = weak constant i8 1 +// CHECK-DAG: {{@__omp_offloading_.+l33}}_exec_mode = weak constant i8 1 +// CHECK-DAG: {{@__omp_offloading_.+l40}}_exec_mode = weak constant i8 1 + +template<typename tx> +tx ftemplate(int n) { + int a; + short b; + tx c; + float d; + double e; + + #pragma omp target + #pragma omp teams reduction(+: e) + { + e += 5; + } + + #pragma omp target + #pragma omp teams reduction(^: c) reduction(*: d) + { + c ^= 2; + d *= 33; + } + + #pragma omp target + #pragma omp teams reduction(|: a) reduction(max: b) + { + a |= 1; + b = 99 > b ? 99 : b; + } + + return a+b+c+d+e; +} + +int bar(int n){ + int a = 0; + + a += ftemplate<char>(n); + + return a; +} + + // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l27}}_worker() + + // CHECK: define {{.*}}void [[T1:@__omp_offloading_.+template.+l27]]( + // + // CHECK: {{call|invoke}} void [[T1]]_worker() + // + // CHECK: call void @__kmpc_kernel_init( + // + // CHECK: store double {{[0\.e\+]+}}, double* [[E:%.+]], align + // CHECK: [[EV:%.+]] = load double, double* [[E]], align + // CHECK: [[ADD:%.+]] = fadd double [[EV]], 5 + // CHECK: store double [[ADD]], double* [[E]], align + // CHECK: [[PTR1:%.+]] = getelementptr inbounds [[RLT:.+]], [1 x i8*]* [[RL:%.+]], i[[SZ:32|64]] 0, i{{32|64}} 0 + // CHECK: [[E_CAST:%.+]] = bitcast double* [[E]] to i8* + // CHECK: store i8* [[E_CAST]], i8** [[PTR1]], align + // CHECK: [[ARG_RL:%.+]] = bitcast [[RLT]]* [[RL]] to i8* + // CHECK: [[RET:%.+]] = call i32 @__kmpc_nvptx_teams_reduce_nowait(i32 {{.+}}, i32 1, i[[SZ]] {{4|8}}, i8* [[ARG_RL]], void (i8*, i16, i16, i16)* [[SHUFFLE_REDUCE_FN:@.+]], void (i8*, i32)* [[WARP_COPY_FN:@.+]], void (i8*, i8*, i32, i32)* [[SCRATCH_COPY_FN:@.+]], void (i8*, i8*, i32, i32, i32)* [[LOAD_REDUCE_FN:@.+]]) + // CHECK: [[COND:%.+]] = icmp eq i32 [[RET]], 1 + // CHECK: br i1 [[COND]], label {{%?}}[[IFLABEL:.+]], label {{%?}}[[EXIT:.+]] + // + // CHECK: [[IFLABEL]] + // CHECK: [[E_INV:%.+]] = load double, double* [[E_IN:%.+]], align + // CHECK: [[EV:%.+]] = load double, double* [[E]], align + // CHECK: [[ADD:%.+]] = fadd double [[E_INV]], [[EV]] + // CHECK: store double [[ADD]], double* [[E_IN]], align + // CHECK: call void @__kmpc_nvptx_end_reduce_nowait( + // CHECK: br label %[[EXIT]] + // + // CHECK: [[EXIT]] + // CHECK: call void @__kmpc_kernel_deinit() + + // + // Reduction function + // CHECK: define internal void [[REDUCTION_FUNC:@.+]](i8*, i8*) + // CHECK: [[VAR_RHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_RHS:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[VAR_RHS_VOID:%.+]] = load i8*, i8** [[VAR_RHS_REF]], + // CHECK: [[VAR_RHS:%.+]] = bitcast i8* [[VAR_RHS_VOID]] to double* + // + // CHECK: [[VAR_LHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_LHS:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[VAR_LHS_VOID:%.+]] = load i8*, i8** [[VAR_LHS_REF]], + // CHECK: [[VAR_LHS:%.+]] = bitcast i8* [[VAR_LHS_VOID]] to double* + // + // CHECK: [[VAR_LHS_VAL:%.+]] = load double, double* [[VAR_LHS]], + // CHECK: [[VAR_RHS_VAL:%.+]] = load double, double* [[VAR_RHS]], + // CHECK: [[RES:%.+]] = fadd double [[VAR_LHS_VAL]], [[VAR_RHS_VAL]] + // CHECK: store double [[RES]], double* [[VAR_LHS]], + // CHECK: ret void + + // + // Shuffle and reduce function + // CHECK: define internal void [[SHUFFLE_REDUCE_FN]](i8*, i16 {{.*}}, i16 {{.*}}, i16 {{.*}}) + // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align + // CHECK: [[REMOTE_ELT:%.+]] = alloca double + // + // CHECK: [[LANEID:%.+]] = load i16, i16* {{.+}}, align + // CHECK: [[LANEOFFSET:%.+]] = load i16, i16* {{.+}}, align + // CHECK: [[ALGVER:%.+]] = load i16, i16* {{.+}}, align + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to double* + // CHECK: [[ELT_VAL:%.+]] = load double, double* [[ELT]], align + // + // CHECK: [[ELT_CAST:%.+]] = bitcast double [[ELT_VAL]] to i64 + // CHECK: [[WS32:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[WS:%.+]] = trunc i32 [[WS32]] to i16 + // CHECK: [[REMOTE_ELT_VAL64:%.+]] = call i64 @__kmpc_shuffle_int64(i64 [[ELT_CAST]], i16 [[LANEOFFSET]], i16 [[WS]]) + // CHECK: [[REMOTE_ELT_VAL:%.+]] = bitcast i64 [[REMOTE_ELT_VAL64]] to double + // + // CHECK: store double [[REMOTE_ELT_VAL]], double* [[REMOTE_ELT]], align + // CHECK: [[REMOTE_ELT_VOID:%.+]] = bitcast double* [[REMOTE_ELT]] to i8* + // CHECK: store i8* [[REMOTE_ELT_VOID]], i8** [[REMOTE_ELT_REF]], align + // + // Condition to reduce + // CHECK: [[CONDALG0:%.+]] = icmp eq i16 [[ALGVER]], 0 + // + // CHECK: [[COND1:%.+]] = icmp eq i16 [[ALGVER]], 1 + // CHECK: [[COND2:%.+]] = icmp ult i16 [[LANEID]], [[LANEOFFSET]] + // CHECK: [[CONDALG1:%.+]] = and i1 [[COND1]], [[COND2]] + // + // CHECK: [[COND3:%.+]] = icmp eq i16 [[ALGVER]], 2 + // CHECK: [[COND4:%.+]] = and i16 [[LANEID]], 1 + // CHECK: [[COND5:%.+]] = icmp eq i16 [[COND4]], 0 + // CHECK: [[COND6:%.+]] = and i1 [[COND3]], [[COND5]] + // CHECK: [[COND7:%.+]] = icmp sgt i16 [[LANEOFFSET]], 0 + // CHECK: [[CONDALG2:%.+]] = and i1 [[COND6]], [[COND7]] + // + // CHECK: [[COND8:%.+]] = or i1 [[CONDALG0]], [[CONDALG1]] + // CHECK: [[SHOULD_REDUCE:%.+]] = or i1 [[COND8]], [[CONDALG2]] + // CHECK: br i1 [[SHOULD_REDUCE]], label {{%?}}[[DO_REDUCE:.+]], label {{%?}}[[REDUCE_ELSE:.+]] + // + // CHECK: [[DO_REDUCE]] + // CHECK: [[RED_LIST1_VOID:%.+]] = bitcast [[RLT]]* [[RED_LIST]] to i8* + // CHECK: [[RED_LIST2_VOID:%.+]] = bitcast [[RLT]]* [[REMOTE_RED_LIST]] to i8* + // CHECK: call void [[REDUCTION_FUNC]](i8* [[RED_LIST1_VOID]], i8* [[RED_LIST2_VOID]]) + // CHECK: br label {{%?}}[[REDUCE_CONT:.+]] + // + // CHECK: [[REDUCE_ELSE]] + // CHECK: br label {{%?}}[[REDUCE_CONT]] + // + // CHECK: [[REDUCE_CONT]] + // Now check if we should just copy over the remote reduction list + // CHECK: [[COND1:%.+]] = icmp eq i16 [[ALGVER]], 1 + // CHECK: [[COND2:%.+]] = icmp uge i16 [[LANEID]], [[LANEOFFSET]] + // CHECK: [[SHOULD_COPY:%.+]] = and i1 [[COND1]], [[COND2]] + // CHECK: br i1 [[SHOULD_COPY]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // CHECK: [[DO_COPY]] + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to double* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to double* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load double, double* [[REMOTE_ELT]], align + // CHECK: store double [[REMOTE_ELT_VAL]], double* [[ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // CHECK: [[COPY_CONT]] + // CHECK: void + + // + // Inter warp copy function + // CHECK: define internal void [[WARP_COPY_FN]](i8*, i32) + // CHECK-DAG: [[LANEID:%.+]] = and i32 {{.+}}, 31 + // CHECK-DAG: [[WARPID:%.+]] = ashr i32 {{.+}}, 5 + // CHECK-DAG: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[IS_WARP_MASTER:%.+]] = icmp eq i32 [[LANEID]], 0 + // CHECK: br i1 [[IS_WARP_MASTER]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // [[DO_COPY]] + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to double* + // CHECK: [[ELT_VAL:%.+]] = load double, double* [[ELT]], align + // + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to double addrspace([[SHARED_ADDRSPACE]])* + // CHECK: store double [[ELT_VAL]], double addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // Barrier after copy to shared memory storage medium. + // CHECK: [[COPY_CONT]] + // CHECK: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[ACTIVE_THREADS:%.+]] = mul nsw i32 [[ACTIVE_WARPS:%.+]], [[WS]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // + // Read into warp 0. + // CHECK: [[IS_W0_ACTIVE_THREAD:%.+]] = icmp ult i32 [[TID:%.+]], [[ACTIVE_WARPS]] + // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]] + // + // CHECK: [[DO_READ]] + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to double addrspace([[SHARED_ADDRSPACE]])* + // CHECK: [[MEDIUM_ELT_VAL:%.+]] = load double, double addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to double* + // CHECK: store double [[MEDIUM_ELT_VAL]], double* [[ELT]], align + // CHECK: br label {{%?}}[[READ_CONT:.+]] + // + // CHECK: [[READ_ELSE]] + // CHECK: br label {{%?}}[[READ_CONT]] + // + // CHECK: [[READ_CONT]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // CHECK: ret + + // + // Copy to scratchpad function + // CHECK: define internal void [[SCRATCH_COPY_FN]](i8*, i8*, i32, i32) + // CHECK: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[SCRATCHPAD_PTR:%.+]] = load i8*, i8** {{.+}}, align + // CHECK-64: [[TEAM32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[TEAM:%.+]] = sext i32 [[TEAM32]] to i64 + // CHECK-32: [[TEAM:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS:%.+]] = sext i32 [[NUM_TEAMS32]] to i64 + // CHECK-32: [[NUM_TEAMS:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SCRATCHPAD:%.+]] = ptrtoint i8* [[SCRATCHPAD_PTR]] to i[[SZ]] + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 8, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to double* + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to double* + // CHECK: [[ELT_VAL:%.+]] = load double, double* [[ELT]], align + // CHECK: store double [[ELT_VAL]], double* [[SCRATCHPAD_ELT_PTR]], align + // + // CHECK: ret + + // + // Load and reduce function + // CHECK: define internal void [[LOAD_REDUCE_FN]](i8*, i8*, i32, i32, i32) + // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align + // CHECK: [[REMOTE_ELT:%.+]] = alloca double + // CHECK: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[SCRATCHPAD_PTR:%.+]] = load i8*, i8** {{.+}}, align + // CHECK-64: [[TEAM32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[TEAM:%.+]] = sext i32 [[TEAM32]] to i64 + // CHECK-32: [[TEAM:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS:%.+]] = sext i32 [[NUM_TEAMS32]] to i64 + // CHECK-32: [[NUM_TEAMS:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SHOULD_REDUCE:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SCRATCHPAD:%.+]] = ptrtoint i8* [[SCRATCHPAD_PTR]] to i[[SZ]] + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 8, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to double* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load double, double* [[SCRATCHPAD_ELT_PTR]], align + // CHECK: store double [[REMOTE_ELT_VAL]], double* [[REMOTE_ELT]], align + // CHECK: [[REMOTE_ELT_PTR:%.+]] = bitcast double* [[REMOTE_ELT]] to i8* + // CHECK: store i8* [[REMOTE_ELT_PTR]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[REDUCE:%.+]] = icmp eq i32 [[SHOULD_REDUCE]], 1 + // CHECK: br i1 [[REDUCE]], label {{%?}}[[DO_REDUCE:.+]], label {{%?}}[[REDUCE_ELSE:.+]] + // + // CHECK: [[DO_REDUCE]] + // CHECK: [[RED_LIST1_VOID:%.+]] = bitcast [[RLT]]* [[RED_LIST]] to i8* + // CHECK: [[RED_LIST2_VOID:%.+]] = bitcast [[RLT]]* [[REMOTE_RED_LIST]] to i8* + // CHECK: call void [[REDUCTION_FUNC]](i8* [[RED_LIST1_VOID]], i8* [[RED_LIST2_VOID]]) + // CHECK: br label {{%?}}[[REDUCE_CONT:.+]] + // + // Copy element from remote reduce list + // CHECK: [[REDUCE_ELSE]] + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to double* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to double* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load double, double* [[REMOTE_ELT]], align + // CHECK: store double [[REMOTE_ELT_VAL]], double* [[ELT]], align + // CHECK: br label {{%?}}[[REDUCE_CONT]] + // + // CHECK: [[REDUCE_CONT]] + // CHECK: ret + + + + + + + + + + + + // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l33}}_worker() + + // CHECK: define {{.*}}void [[T2:@__omp_offloading_.+template.+l33]]( + // + // CHECK: {{call|invoke}} void [[T2]]_worker() + // + // CHECK: call void @__kmpc_kernel_init( + // + // CHECK: store float {{1\.[0e\+]+}}, float* [[D:%.+]], align + // CHECK: [[C_VAL:%.+]] = load i8, i8* [[C:%.+]], align + // CHECK: [[CONV:%.+]] = sext i8 [[C_VAL]] to i32 + // CHECK: [[XOR:%.+]] = xor i32 [[CONV]], 2 + // CHECK: [[TRUNC:%.+]] = trunc i32 [[XOR]] to i8 + // CHECK: store i8 [[TRUNC]], i8* [[C]], align + // CHECK: [[DV:%.+]] = load float, float* [[D]], align + // CHECK: [[MUL:%.+]] = fmul float [[DV]], {{[0-9e\.\+]+}} + // CHECK: store float [[MUL]], float* [[D]], align + // CHECK: [[PTR1:%.+]] = getelementptr inbounds [[RLT:.+]], [2 x i8*]* [[RL:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: store i8* [[C]], i8** [[PTR1]], align + // CHECK: [[PTR2:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RL]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[D_CAST:%.+]] = bitcast float* [[D]] to i8* + // CHECK: store i8* [[D_CAST]], i8** [[PTR2]], align + // CHECK: [[ARG_RL:%.+]] = bitcast [[RLT]]* [[RL]] to i8* + // CHECK: [[RET:%.+]] = call i32 @__kmpc_nvptx_teams_reduce_nowait(i32 {{.+}}, i32 2, i[[SZ]] {{8|16}}, i8* [[ARG_RL]], void (i8*, i16, i16, i16)* [[SHUFFLE_REDUCE_FN:@.+]], void (i8*, i32)* [[WARP_COPY_FN:@.+]], void (i8*, i8*, i32, i32)* [[SCRATCH_COPY_FN:@.+]], void (i8*, i8*, i32, i32, i32)* [[LOAD_REDUCE_FN:@.+]]) + // CHECK: [[COND:%.+]] = icmp eq i32 [[RET]], 1 + // CHECK: br i1 [[COND]], label {{%?}}[[IFLABEL:.+]], label {{%?}}[[EXIT:.+]] + // + // CHECK: [[IFLABEL]] + // CHECK: [[C_INV8:%.+]] = load i8, i8* [[C_IN:%.+]], align + // CHECK: [[C_INV:%.+]] = sext i8 [[C_INV8]] to i32 + // CHECK: [[CV8:%.+]] = load i8, i8* [[C]], align + // CHECK: [[CV:%.+]] = sext i8 [[CV8]] to i32 + // CHECK: [[XOR:%.+]] = xor i32 [[C_INV]], [[CV]] + // CHECK: [[TRUNC:%.+]] = trunc i32 [[XOR]] to i8 + // CHECK: store i8 [[TRUNC]], i8* [[C_IN]], align + // CHECK: [[D_INV:%.+]] = load float, float* [[D_IN:%.+]], align + // CHECK: [[DV:%.+]] = load float, float* [[D]], align + // CHECK: [[MUL:%.+]] = fmul float [[D_INV]], [[DV]] + // CHECK: store float [[MUL]], float* [[D_IN]], align + // CHECK: call void @__kmpc_nvptx_end_reduce_nowait( + // CHECK: br label %[[EXIT]] + // + // CHECK: [[EXIT]] + // CHECK: call void @__kmpc_kernel_deinit() + + // + // Reduction function + // CHECK: define internal void [[REDUCTION_FUNC:@.+]](i8*, i8*) + // CHECK: [[VAR1_RHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_RHS:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[VAR1_RHS:%.+]] = load i8*, i8** [[VAR1_RHS_REF]], + // + // CHECK: [[VAR1_LHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_LHS:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[VAR1_LHS:%.+]] = load i8*, i8** [[VAR1_LHS_REF]], + // + // CHECK: [[VAR2_RHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_RHS]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[VAR2_RHS_VOID:%.+]] = load i8*, i8** [[VAR2_RHS_REF]], + // CHECK: [[VAR2_RHS:%.+]] = bitcast i8* [[VAR2_RHS_VOID]] to float* + // + // CHECK: [[VAR2_LHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_LHS]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[VAR2_LHS_VOID:%.+]] = load i8*, i8** [[VAR2_LHS_REF]], + // CHECK: [[VAR2_LHS:%.+]] = bitcast i8* [[VAR2_LHS_VOID]] to float* + // + // CHECK: [[VAR1_LHS_VAL8:%.+]] = load i8, i8* [[VAR1_LHS]], + // CHECK: [[VAR1_LHS_VAL:%.+]] = sext i8 [[VAR1_LHS_VAL8]] to i32 + // CHECK: [[VAR1_RHS_VAL8:%.+]] = load i8, i8* [[VAR1_RHS]], + // CHECK: [[VAR1_RHS_VAL:%.+]] = sext i8 [[VAR1_RHS_VAL8]] to i32 + // CHECK: [[XOR:%.+]] = xor i32 [[VAR1_LHS_VAL]], [[VAR1_RHS_VAL]] + // CHECK: [[RES:%.+]] = trunc i32 [[XOR]] to i8 + // CHECK: store i8 [[RES]], i8* [[VAR1_LHS]], + // + // CHECK: [[VAR2_LHS_VAL:%.+]] = load float, float* [[VAR2_LHS]], + // CHECK: [[VAR2_RHS_VAL:%.+]] = load float, float* [[VAR2_RHS]], + // CHECK: [[RES:%.+]] = fmul float [[VAR2_LHS_VAL]], [[VAR2_RHS_VAL]] + // CHECK: store float [[RES]], float* [[VAR2_LHS]], + // CHECK: ret void + + // + // Shuffle and reduce function + // CHECK: define internal void [[SHUFFLE_REDUCE_FN]](i8*, i16 {{.*}}, i16 {{.*}}, i16 {{.*}}) + // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align + // CHECK: [[REMOTE_ELT1:%.+]] = alloca i8 + // CHECK: [[REMOTE_ELT2:%.+]] = alloca float + // + // CHECK: [[LANEID:%.+]] = load i16, i16* {{.+}}, align + // CHECK: [[LANEOFFSET:%.+]] = load i16, i16* {{.+}}, align + // CHECK: [[ALGVER:%.+]] = load i16, i16* {{.+}}, align + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VAL:%.+]] = load i8, i8* [[ELT_VOID]], align + // + // CHECK: [[ELT_CAST:%.+]] = sext i8 [[ELT_VAL]] to i32 + // CHECK: [[WS32:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[WS:%.+]] = trunc i32 [[WS32]] to i16 + // CHECK: [[REMOTE_ELT1_VAL32:%.+]] = call i32 @__kmpc_shuffle_int32(i32 [[ELT_CAST]], i16 [[LANEOFFSET]], i16 [[WS]]) + // CHECK: [[REMOTE_ELT1_VAL:%.+]] = trunc i32 [[REMOTE_ELT1_VAL32]] to i8 + // + // CHECK: store i8 [[REMOTE_ELT1_VAL]], i8* [[REMOTE_ELT1]], align + // CHECK: store i8* [[REMOTE_ELT1]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to float* + // CHECK: [[ELT_VAL:%.+]] = load float, float* [[ELT]], align + // + // CHECK: [[ELT_CAST:%.+]] = bitcast float [[ELT_VAL]] to i32 + // CHECK: [[WS32:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[WS:%.+]] = trunc i32 [[WS32]] to i16 + // CHECK: [[REMOTE_ELT2_VAL32:%.+]] = call i32 @__kmpc_shuffle_int32(i32 [[ELT_CAST]], i16 [[LANEOFFSET]], i16 [[WS]]) + // CHECK: [[REMOTE_ELT2_VAL:%.+]] = bitcast i32 [[REMOTE_ELT2_VAL32]] to float + // + // CHECK: store float [[REMOTE_ELT2_VAL]], float* [[REMOTE_ELT2]], align + // CHECK: [[REMOTE_ELT2C:%.+]] = bitcast float* [[REMOTE_ELT2]] to i8* + // CHECK: store i8* [[REMOTE_ELT2C]], i8** [[REMOTE_ELT_REF]], align + // + // Condition to reduce + // CHECK: [[CONDALG0:%.+]] = icmp eq i16 [[ALGVER]], 0 + // + // CHECK: [[COND1:%.+]] = icmp eq i16 [[ALGVER]], 1 + // CHECK: [[COND2:%.+]] = icmp ult i16 [[LANEID]], [[LANEOFFSET]] + // CHECK: [[CONDALG1:%.+]] = and i1 [[COND1]], [[COND2]] + // + // CHECK: [[COND3:%.+]] = icmp eq i16 [[ALGVER]], 2 + // CHECK: [[COND4:%.+]] = and i16 [[LANEID]], 1 + // CHECK: [[COND5:%.+]] = icmp eq i16 [[COND4]], 0 + // CHECK: [[COND6:%.+]] = and i1 [[COND3]], [[COND5]] + // CHECK: [[COND7:%.+]] = icmp sgt i16 [[LANEOFFSET]], 0 + // CHECK: [[CONDALG2:%.+]] = and i1 [[COND6]], [[COND7]] + // + // CHECK: [[COND8:%.+]] = or i1 [[CONDALG0]], [[CONDALG1]] + // CHECK: [[SHOULD_REDUCE:%.+]] = or i1 [[COND8]], [[CONDALG2]] + // CHECK: br i1 [[SHOULD_REDUCE]], label {{%?}}[[DO_REDUCE:.+]], label {{%?}}[[REDUCE_ELSE:.+]] + // + // CHECK: [[DO_REDUCE]] + // CHECK: [[RED_LIST1_VOID:%.+]] = bitcast [[RLT]]* [[RED_LIST]] to i8* + // CHECK: [[RED_LIST2_VOID:%.+]] = bitcast [[RLT]]* [[REMOTE_RED_LIST]] to i8* + // CHECK: call void [[REDUCTION_FUNC]](i8* [[RED_LIST1_VOID]], i8* [[RED_LIST2_VOID]]) + // CHECK: br label {{%?}}[[REDUCE_CONT:.+]] + // + // CHECK: [[REDUCE_ELSE]] + // CHECK: br label {{%?}}[[REDUCE_CONT]] + // + // CHECK: [[REDUCE_CONT]] + // Now check if we should just copy over the remote reduction list + // CHECK: [[COND1:%.+]] = icmp eq i16 [[ALGVER]], 1 + // CHECK: [[COND2:%.+]] = icmp uge i16 [[LANEID]], [[LANEOFFSET]] + // CHECK: [[SHOULD_COPY:%.+]] = and i1 [[COND1]], [[COND2]] + // CHECK: br i1 [[SHOULD_COPY]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // CHECK: [[DO_COPY]] + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i8, i8* [[REMOTE_ELT_VOID]], align + // CHECK: store i8 [[REMOTE_ELT_VAL]], i8* [[ELT_VOID]], align + // + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to float* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to float* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load float, float* [[REMOTE_ELT]], align + // CHECK: store float [[REMOTE_ELT_VAL]], float* [[ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // CHECK: [[COPY_CONT]] + // CHECK: void + + // + // Inter warp copy function + // CHECK: define internal void [[WARP_COPY_FN]](i8*, i32) + // CHECK-DAG: [[LANEID:%.+]] = and i32 {{.+}}, 31 + // CHECK-DAG: [[WARPID:%.+]] = ashr i32 {{.+}}, 5 + // CHECK-DAG: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[IS_WARP_MASTER:%.+]] = icmp eq i32 [[LANEID]], 0 + // CHECK: br i1 [[IS_WARP_MASTER]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // [[DO_COPY]] + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT_VAL:%.+]] = load i8, i8* [[ELT_VOID]], align + // + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i8 addrspace([[SHARED_ADDRSPACE]])* + // CHECK: store i8 [[ELT_VAL]], i8 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // Barrier after copy to shared memory storage medium. + // CHECK: [[COPY_CONT]] + // CHECK: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[ACTIVE_THREADS:%.+]] = mul nsw i32 [[ACTIVE_WARPS:%.+]], [[WS]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // + // Read into warp 0. + // CHECK: [[IS_W0_ACTIVE_THREAD:%.+]] = icmp ult i32 [[TID:%.+]], [[ACTIVE_WARPS]] + // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]] + // + // CHECK: [[DO_READ]] + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i8 addrspace([[SHARED_ADDRSPACE]])* + // CHECK: [[MEDIUM_ELT_VAL:%.+]] = load i8, i8 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: store i8 [[MEDIUM_ELT_VAL]], i8* [[ELT_VOID]], align + // CHECK: br label {{%?}}[[READ_CONT:.+]] + // + // CHECK: [[READ_ELSE]] + // CHECK: br label {{%?}}[[READ_CONT]] + // + // CHECK: [[READ_CONT]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // CHECK: [[IS_WARP_MASTER:%.+]] = icmp eq i32 [[LANEID]], 0 + // CHECK: br i1 [[IS_WARP_MASTER]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // [[DO_COPY]] + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to float* + // CHECK: [[ELT_VAL:%.+]] = load float, float* [[ELT]], align + // + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to float addrspace([[SHARED_ADDRSPACE]])* + // CHECK: store float [[ELT_VAL]], float addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // Barrier after copy to shared memory storage medium. + // CHECK: [[COPY_CONT]] + // CHECK: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[ACTIVE_THREADS:%.+]] = mul nsw i32 [[ACTIVE_WARPS:%.+]], [[WS]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // + // Read into warp 0. + // CHECK: [[IS_W0_ACTIVE_THREAD:%.+]] = icmp ult i32 [[TID:%.+]], [[ACTIVE_WARPS]] + // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]] + // + // CHECK: [[DO_READ]] + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to float addrspace([[SHARED_ADDRSPACE]])* + // CHECK: [[MEDIUM_ELT_VAL:%.+]] = load float, float addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to float* + // CHECK: store float [[MEDIUM_ELT_VAL]], float* [[ELT]], align + // CHECK: br label {{%?}}[[READ_CONT:.+]] + // + // CHECK: [[READ_ELSE]] + // CHECK: br label {{%?}}[[READ_CONT]] + // + // CHECK: [[READ_CONT]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // CHECK: ret + + // + // Copy to scratchpad function + // CHECK: define internal void [[SCRATCH_COPY_FN]](i8*, i8*, i32, i32) + // CHECK: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[SCRATCHPAD_PTR:%.+]] = load i8*, i8** {{.+}}, align + // CHECK-64: [[TEAM32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[TEAM:%.+]] = sext i32 [[TEAM32]] to i64 + // CHECK-32: [[TEAM:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS:%.+]] = sext i32 [[NUM_TEAMS32]] to i64 + // CHECK-32: [[NUM_TEAMS:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SCRATCHPAD:%.+]] = ptrtoint i8* [[SCRATCHPAD_PTR]] to i[[SZ]] + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 1, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + // CHECK: [[ELT_VAL:%.+]] = load i8, i8* [[ELT_VOID]], align + // CHECK: store i8 [[ELT_VAL]], i8* [[SCRATCHPAD_ELT_PTR]], align + // + // CHECK: [[OF:%.+]] = mul i[[SZ]] [[NUM_TEAMS]], 1 + // CHECK: [[POS1:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[OF]] + // CHECK: [[POS2:%.+]] = sub i[[SZ]] [[POS1]], 1 + // CHECK: [[POS3:%.+]] = sdiv i[[SZ]] [[POS2]], 256 + // CHECK: [[POS4:%.+]] = add i[[SZ]] [[POS3]], 1 + // CHECK: [[SCRATCHPAD_NEXT:%.+]] = mul i[[SZ]] [[POS4]], 256 + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 4, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD_NEXT]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to float* + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to float* + // CHECK: [[ELT_VAL:%.+]] = load float, float* [[ELT]], align + // CHECK: store float [[ELT_VAL]], float* [[SCRATCHPAD_ELT_PTR]], align + // + // CHECK: ret + + // + // Load and reduce function + // CHECK: define internal void [[LOAD_REDUCE_FN]](i8*, i8*, i32, i32, i32) + // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align + // CHECK: [[REMOTE_ELT1:%.+]] = alloca i8 + // CHECK: [[REMOTE_ELT2:%.+]] = alloca float + // CHECK: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[SCRATCHPAD_PTR:%.+]] = load i8*, i8** {{.+}}, align + // CHECK-64: [[TEAM32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[TEAM:%.+]] = sext i32 [[TEAM32]] to i64 + // CHECK-32: [[TEAM:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS:%.+]] = sext i32 [[NUM_TEAMS32]] to i64 + // CHECK-32: [[NUM_TEAMS:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SHOULD_REDUCE:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SCRATCHPAD:%.+]] = ptrtoint i8* [[SCRATCHPAD_PTR]] to i[[SZ]] + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 1, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i8, i8* [[SCRATCHPAD_ELT_PTR_VOID]], align + // CHECK: store i8 [[REMOTE_ELT_VAL]], i8* [[REMOTE_ELT1]], align + // CHECK: store i8* [[REMOTE_ELT1]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[OF:%.+]] = mul i[[SZ]] [[NUM_TEAMS]], 1 + // CHECK: [[POS1:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[OF]] + // CHECK: [[POS2:%.+]] = sub i[[SZ]] [[POS1]], 1 + // CHECK: [[POS3:%.+]] = sdiv i[[SZ]] [[POS2]], 256 + // CHECK: [[POS4:%.+]] = add i[[SZ]] [[POS3]], 1 + // CHECK: [[SCRATCHPAD_NEXT:%.+]] = mul i[[SZ]] [[POS4]], 256 + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 4, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD_NEXT]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to float* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load float, float* [[SCRATCHPAD_ELT_PTR]], align + // CHECK: store float [[REMOTE_ELT_VAL]], float* [[REMOTE_ELT2]], align + // CHECK: [[REMOTE_ELT_PTR:%.+]] = bitcast float* [[REMOTE_ELT2]] to i8* + // CHECK: store i8* [[REMOTE_ELT_PTR]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[REDUCE:%.+]] = icmp eq i32 [[SHOULD_REDUCE]], 1 + // CHECK: br i1 [[REDUCE]], label {{%?}}[[DO_REDUCE:.+]], label {{%?}}[[REDUCE_ELSE:.+]] + // + // CHECK: [[DO_REDUCE]] + // CHECK: [[RED_LIST1_VOID:%.+]] = bitcast [[RLT]]* [[RED_LIST]] to i8* + // CHECK: [[RED_LIST2_VOID:%.+]] = bitcast [[RLT]]* [[REMOTE_RED_LIST]] to i8* + // CHECK: call void [[REDUCTION_FUNC]](i8* [[RED_LIST1_VOID]], i8* [[RED_LIST2_VOID]]) + // CHECK: br label {{%?}}[[REDUCE_CONT:.+]] + // + // Copy element from remote reduce list + // CHECK: [[REDUCE_ELSE]] + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i8, i8* [[REMOTE_ELT_VOID]], align + // CHECK: store i8 [[REMOTE_ELT_VAL]], i8* [[ELT_VOID]], align + // + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to float* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to float* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load float, float* [[REMOTE_ELT]], align + // CHECK: store float [[REMOTE_ELT_VAL]], float* [[ELT]], align + // CHECK: br label {{%?}}[[REDUCE_CONT]] + // + // CHECK: [[REDUCE_CONT]] + // CHECK: ret + + + + + + + + + + + // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l40}}_worker() + + // CHECK: define {{.*}}void [[T3:@__omp_offloading_.+template.+l40]]( + // + // CHECK: {{call|invoke}} void [[T3]]_worker() + // + // CHECK: call void @__kmpc_kernel_init( + // + // CHECK: store i32 0, i32* [[A:%.+]], align + // CHECK: store i16 -32768, i16* [[B:%.+]], align + // CHECK: [[A_VAL:%.+]] = load i32, i32* [[A:%.+]], align + // CHECK: [[OR:%.+]] = or i32 [[A_VAL]], 1 + // CHECK: store i32 [[OR]], i32* [[A]], align + // CHECK: [[BV16:%.+]] = load i16, i16* [[B]], align + // CHECK: [[BV:%.+]] = sext i16 [[BV16]] to i32 + // CHECK: [[CMP:%.+]] = icmp sgt i32 99, [[BV]] + // CHECK: br i1 [[CMP]], label {{%?}}[[DO_MAX:.+]], label {{%?}}[[MAX_ELSE:.+]] + // + // CHECK: [[DO_MAX]] + // CHECK: br label {{%?}}[[MAX_CONT:.+]] + // + // CHECK: [[MAX_ELSE]] + // CHECK: [[BV:%.+]] = load i16, i16* [[B]], align + // CHECK: [[MAX:%.+]] = sext i16 [[BV]] to i32 + // CHECK: br label {{%?}}[[MAX_CONT]] + // + // CHECK: [[MAX_CONT]] + // CHECK: [[B_LVALUE:%.+]] = phi i32 [ 99, %[[DO_MAX]] ], [ [[MAX]], %[[MAX_ELSE]] ] + // CHECK: [[TRUNC:%.+]] = trunc i32 [[B_LVALUE]] to i16 + // CHECK: store i16 [[TRUNC]], i16* [[B]], align + // CHECK: [[PTR1:%.+]] = getelementptr inbounds [[RLT:.+]], [2 x i8*]* [[RL:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[A_CAST:%.+]] = bitcast i32* [[A]] to i8* + // CHECK: store i8* [[A_CAST]], i8** [[PTR1]], align + // CHECK: [[PTR2:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RL]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[B_CAST:%.+]] = bitcast i16* [[B]] to i8* + // CHECK: store i8* [[B_CAST]], i8** [[PTR2]], align + // CHECK: [[ARG_RL:%.+]] = bitcast [[RLT]]* [[RL]] to i8* + // CHECK: [[RET:%.+]] = call i32 @__kmpc_nvptx_teams_reduce_nowait(i32 {{.+}}, i32 2, i[[SZ]] {{8|16}}, i8* [[ARG_RL]], void (i8*, i16, i16, i16)* [[SHUFFLE_REDUCE_FN:@.+]], void (i8*, i32)* [[WARP_COPY_FN:@.+]], void (i8*, i8*, i32, i32)* [[SCRATCH_COPY_FN:@.+]], void (i8*, i8*, i32, i32, i32)* [[LOAD_REDUCE_FN:@.+]]) + // CHECK: [[COND:%.+]] = icmp eq i32 [[RET]], 1 + // CHECK: br i1 [[COND]], label {{%?}}[[IFLABEL:.+]], label {{%?}}[[EXIT:.+]] + // + // CHECK: [[IFLABEL]] + // CHECK: [[A_INV:%.+]] = load i32, i32* [[A_IN:%.+]], align + // CHECK: [[AV:%.+]] = load i32, i32* [[A]], align + // CHECK: [[OR:%.+]] = or i32 [[A_INV]], [[AV]] + // CHECK: store i32 [[OR]], i32* [[A_IN]], align + // CHECK: [[B_INV16:%.+]] = load i16, i16* [[B_IN:%.+]], align + // CHECK: [[B_INV:%.+]] = sext i16 [[B_INV16]] to i32 + // CHECK: [[BV16:%.+]] = load i16, i16* [[B]], align + // CHECK: [[BV:%.+]] = sext i16 [[BV16]] to i32 + // CHECK: [[CMP:%.+]] = icmp sgt i32 [[B_INV]], [[BV]] + // CHECK: br i1 [[CMP]], label {{%?}}[[DO_MAX:.+]], label {{%?}}[[MAX_ELSE:.+]] + // + // CHECK: [[DO_MAX]] + // CHECK: [[MAX1:%.+]] = load i16, i16* [[B_IN]], align + // CHECK: br label {{%?}}[[MAX_CONT:.+]] + // + // CHECK: [[MAX_ELSE]] + // CHECK: [[MAX2:%.+]] = load i16, i16* [[B]], align + // CHECK: br label {{%?}}[[MAX_CONT]] + // + // CHECK: [[MAX_CONT]] + // CHECK: [[B_MAX:%.+]] = phi i16 [ [[MAX1]], %[[DO_MAX]] ], [ [[MAX2]], %[[MAX_ELSE]] ] + // CHECK: store i16 [[B_MAX]], i16* [[B_IN]], align + // CHECK: call void @__kmpc_nvptx_end_reduce_nowait( + // CHECK: br label %[[EXIT]] + // + // CHECK: [[EXIT]] + // CHECK: call void @__kmpc_kernel_deinit() + + // + // Reduction function + // CHECK: define internal void [[REDUCTION_FUNC:@.+]](i8*, i8*) + // CHECK: [[VAR1_RHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_RHS:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[VAR1_RHS_VOID:%.+]] = load i8*, i8** [[VAR1_RHS_REF]], + // CHECK: [[VAR1_RHS:%.+]] = bitcast i8* [[VAR1_RHS_VOID]] to i32* + // + // CHECK: [[VAR1_LHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_LHS:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[VAR1_LHS_VOID:%.+]] = load i8*, i8** [[VAR1_LHS_REF]], + // CHECK: [[VAR1_LHS:%.+]] = bitcast i8* [[VAR1_LHS_VOID]] to i32* + // + // CHECK: [[VAR2_RHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_RHS]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[VAR2_RHS_VOID:%.+]] = load i8*, i8** [[VAR2_RHS_REF]], + // CHECK: [[VAR2_RHS:%.+]] = bitcast i8* [[VAR2_RHS_VOID]] to i16* + // + // CHECK: [[VAR2_LHS_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST_LHS]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[VAR2_LHS_VOID:%.+]] = load i8*, i8** [[VAR2_LHS_REF]], + // CHECK: [[VAR2_LHS:%.+]] = bitcast i8* [[VAR2_LHS_VOID]] to i16* + // + // CHECK: [[VAR1_LHS_VAL:%.+]] = load i32, i32* [[VAR1_LHS]], + // CHECK: [[VAR1_RHS_VAL:%.+]] = load i32, i32* [[VAR1_RHS]], + // CHECK: [[OR:%.+]] = or i32 [[VAR1_LHS_VAL]], [[VAR1_RHS_VAL]] + // CHECK: store i32 [[OR]], i32* [[VAR1_LHS]], + // + // CHECK: [[VAR2_LHS_VAL16:%.+]] = load i16, i16* [[VAR2_LHS]], + // CHECK: [[VAR2_LHS_VAL:%.+]] = sext i16 [[VAR2_LHS_VAL16]] to i32 + // CHECK: [[VAR2_RHS_VAL16:%.+]] = load i16, i16* [[VAR2_RHS]], + // CHECK: [[VAR2_RHS_VAL:%.+]] = sext i16 [[VAR2_RHS_VAL16]] to i32 + // + // CHECK: [[CMP:%.+]] = icmp sgt i32 [[VAR2_LHS_VAL]], [[VAR2_RHS_VAL]] + // CHECK: br i1 [[CMP]], label {{%?}}[[DO_MAX:.+]], label {{%?}}[[MAX_ELSE:.+]] + // + // CHECK: [[DO_MAX]] + // CHECK: [[MAX1:%.+]] = load i16, i16* [[VAR2_LHS]], align + // CHECK: br label {{%?}}[[MAX_CONT:.+]] + // + // CHECK: [[MAX_ELSE]] + // CHECK: [[MAX2:%.+]] = load i16, i16* [[VAR2_RHS]], align + // CHECK: br label {{%?}}[[MAX_CONT]] + // + // CHECK: [[MAX_CONT]] + // CHECK: [[MAXV:%.+]] = phi i16 [ [[MAX1]], %[[DO_MAX]] ], [ [[MAX2]], %[[MAX_ELSE]] ] + // CHECK: store i16 [[MAXV]], i16* [[VAR2_LHS]], + // CHECK: ret void + + // + // Shuffle and reduce function + // CHECK: define internal void [[SHUFFLE_REDUCE_FN]](i8*, i16 {{.*}}, i16 {{.*}}, i16 {{.*}}) + // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align + // CHECK: [[REMOTE_ELT1:%.+]] = alloca i32 + // CHECK: [[REMOTE_ELT2:%.+]] = alloca i16 + // + // CHECK: [[LANEID:%.+]] = load i16, i16* {{.+}}, align + // CHECK: [[LANEOFFSET:%.+]] = load i16, i16* {{.+}}, align + // CHECK: [[ALGVER:%.+]] = load i16, i16* {{.+}}, align + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32* + // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]], align + // + // CHECK: [[WS32:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[WS:%.+]] = trunc i32 [[WS32]] to i16 + // CHECK: [[REMOTE_ELT1_VAL:%.+]] = call i32 @__kmpc_shuffle_int32(i32 [[ELT_VAL]], i16 [[LANEOFFSET]], i16 [[WS]]) + // + // CHECK: store i32 [[REMOTE_ELT1_VAL]], i32* [[REMOTE_ELT1]], align + // CHECK: [[REMOTE_ELT1C:%.+]] = bitcast i32* [[REMOTE_ELT1]] to i8* + // CHECK: store i8* [[REMOTE_ELT1C]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16* + // CHECK: [[ELT_VAL:%.+]] = load i16, i16* [[ELT]], align + // + // CHECK: [[ELT_CAST:%.+]] = sext i16 [[ELT_VAL]] to i32 + // CHECK: [[WS32:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[WS:%.+]] = trunc i32 [[WS32]] to i16 + // CHECK: [[REMOTE_ELT2_VAL32:%.+]] = call i32 @__kmpc_shuffle_int32(i32 [[ELT_CAST]], i16 [[LANEOFFSET]], i16 [[WS]]) + // CHECK: [[REMOTE_ELT2_VAL:%.+]] = trunc i32 [[REMOTE_ELT2_VAL32]] to i16 + // + // CHECK: store i16 [[REMOTE_ELT2_VAL]], i16* [[REMOTE_ELT2]], align + // CHECK: [[REMOTE_ELT2C:%.+]] = bitcast i16* [[REMOTE_ELT2]] to i8* + // CHECK: store i8* [[REMOTE_ELT2C]], i8** [[REMOTE_ELT_REF]], align + // + // Condition to reduce + // CHECK: [[CONDALG0:%.+]] = icmp eq i16 [[ALGVER]], 0 + // + // CHECK: [[COND1:%.+]] = icmp eq i16 [[ALGVER]], 1 + // CHECK: [[COND2:%.+]] = icmp ult i16 [[LANEID]], [[LANEOFFSET]] + // CHECK: [[CONDALG1:%.+]] = and i1 [[COND1]], [[COND2]] + // + // CHECK: [[COND3:%.+]] = icmp eq i16 [[ALGVER]], 2 + // CHECK: [[COND4:%.+]] = and i16 [[LANEID]], 1 + // CHECK: [[COND5:%.+]] = icmp eq i16 [[COND4]], 0 + // CHECK: [[COND6:%.+]] = and i1 [[COND3]], [[COND5]] + // CHECK: [[COND7:%.+]] = icmp sgt i16 [[LANEOFFSET]], 0 + // CHECK: [[CONDALG2:%.+]] = and i1 [[COND6]], [[COND7]] + // + // CHECK: [[COND8:%.+]] = or i1 [[CONDALG0]], [[CONDALG1]] + // CHECK: [[SHOULD_REDUCE:%.+]] = or i1 [[COND8]], [[CONDALG2]] + // CHECK: br i1 [[SHOULD_REDUCE]], label {{%?}}[[DO_REDUCE:.+]], label {{%?}}[[REDUCE_ELSE:.+]] + // + // CHECK: [[DO_REDUCE]] + // CHECK: [[RED_LIST1_VOID:%.+]] = bitcast [[RLT]]* [[RED_LIST]] to i8* + // CHECK: [[RED_LIST2_VOID:%.+]] = bitcast [[RLT]]* [[REMOTE_RED_LIST]] to i8* + // CHECK: call void [[REDUCTION_FUNC]](i8* [[RED_LIST1_VOID]], i8* [[RED_LIST2_VOID]]) + // CHECK: br label {{%?}}[[REDUCE_CONT:.+]] + // + // CHECK: [[REDUCE_ELSE]] + // CHECK: br label {{%?}}[[REDUCE_CONT]] + // + // CHECK: [[REDUCE_CONT]] + // Now check if we should just copy over the remote reduction list + // CHECK: [[COND1:%.+]] = icmp eq i16 [[ALGVER]], 1 + // CHECK: [[COND2:%.+]] = icmp uge i16 [[LANEID]], [[LANEOFFSET]] + // CHECK: [[SHOULD_COPY:%.+]] = and i1 [[COND1]], [[COND2]] + // CHECK: br i1 [[SHOULD_COPY]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // CHECK: [[DO_COPY]] + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to i32* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i32, i32* [[REMOTE_ELT]], align + // CHECK: store i32 [[REMOTE_ELT_VAL]], i32* [[ELT]], align + // + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to i16* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i16, i16* [[REMOTE_ELT]], align + // CHECK: store i16 [[REMOTE_ELT_VAL]], i16* [[ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // CHECK: [[COPY_CONT]] + // CHECK: void + + // + // Inter warp copy function + // CHECK: define internal void [[WARP_COPY_FN]](i8*, i32) + // CHECK-DAG: [[LANEID:%.+]] = and i32 {{.+}}, 31 + // CHECK-DAG: [[WARPID:%.+]] = ashr i32 {{.+}}, 5 + // CHECK-DAG: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[IS_WARP_MASTER:%.+]] = icmp eq i32 [[LANEID]], 0 + // CHECK: br i1 [[IS_WARP_MASTER]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // [[DO_COPY]] + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32* + // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]], align + // + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i32 addrspace([[SHARED_ADDRSPACE]])* + // CHECK: store i32 [[ELT_VAL]], i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // Barrier after copy to shared memory storage medium. + // CHECK: [[COPY_CONT]] + // CHECK: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[ACTIVE_THREADS:%.+]] = mul nsw i32 [[ACTIVE_WARPS:%.+]], [[WS]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // + // Read into warp 0. + // CHECK: [[IS_W0_ACTIVE_THREAD:%.+]] = icmp ult i32 [[TID:%.+]], [[ACTIVE_WARPS]] + // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]] + // + // CHECK: [[DO_READ]] + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i32 addrspace([[SHARED_ADDRSPACE]])* + // CHECK: [[MEDIUM_ELT_VAL:%.+]] = load i32, i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32* + // CHECK: store i32 [[MEDIUM_ELT_VAL]], i32* [[ELT]], align + // CHECK: br label {{%?}}[[READ_CONT:.+]] + // + // CHECK: [[READ_ELSE]] + // CHECK: br label {{%?}}[[READ_CONT]] + // + // CHECK: [[READ_CONT]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // CHECK: [[IS_WARP_MASTER:%.+]] = icmp eq i32 [[LANEID]], 0 + // CHECK: br i1 [[IS_WARP_MASTER]], label {{%?}}[[DO_COPY:.+]], label {{%?}}[[COPY_ELSE:.+]] + // + // [[DO_COPY]] + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16* + // CHECK: [[ELT_VAL:%.+]] = load i16, i16* [[ELT]], align + // + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i16 addrspace([[SHARED_ADDRSPACE]])* + // CHECK: store i16 [[ELT_VAL]], i16 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: br label {{%?}}[[COPY_CONT:.+]] + // + // CHECK: [[COPY_ELSE]] + // CHECK: br label {{%?}}[[COPY_CONT]] + // + // Barrier after copy to shared memory storage medium. + // CHECK: [[COPY_CONT]] + // CHECK: [[WS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize() + // CHECK: [[ACTIVE_THREADS:%.+]] = mul nsw i32 [[ACTIVE_WARPS:%.+]], [[WS]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // + // Read into warp 0. + // CHECK: [[IS_W0_ACTIVE_THREAD:%.+]] = icmp ult i32 [[TID:%.+]], [[ACTIVE_WARPS]] + // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]] + // + // CHECK: [[DO_READ]] + // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i64], [32 x i64] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]] + // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i64 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i16 addrspace([[SHARED_ADDRSPACE]])* + // CHECK: [[MEDIUM_ELT_VAL:%.+]] = load i16, i16 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16* + // CHECK: store i16 [[MEDIUM_ELT_VAL]], i16* [[ELT]], align + // CHECK: br label {{%?}}[[READ_CONT:.+]] + // + // CHECK: [[READ_ELSE]] + // CHECK: br label {{%?}}[[READ_CONT]] + // + // CHECK: [[READ_CONT]] + // CHECK: call void @llvm.nvvm.barrier(i32 1, i32 [[ACTIVE_THREADS]]) + // CHECK: ret + + // + // Copy to scratchpad function + // CHECK: define internal void [[SCRATCH_COPY_FN]](i8*, i8*, i32, i32) + // CHECK: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[SCRATCHPAD_PTR:%.+]] = load i8*, i8** {{.+}}, align + // CHECK-64: [[TEAM32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[TEAM:%.+]] = sext i32 [[TEAM32]] to i64 + // CHECK-32: [[TEAM:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS:%.+]] = sext i32 [[NUM_TEAMS32]] to i64 + // CHECK-32: [[NUM_TEAMS:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SCRATCHPAD:%.+]] = ptrtoint i8* [[SCRATCHPAD_PTR]] to i[[SZ]] + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 4, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to i32* + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32* + // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]], align + // CHECK: store i32 [[ELT_VAL]], i32* [[SCRATCHPAD_ELT_PTR]], align + // + // CHECK: [[OF:%.+]] = mul i[[SZ]] [[NUM_TEAMS]], 4 + // CHECK: [[POS1:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[OF]] + // CHECK: [[POS2:%.+]] = sub i[[SZ]] [[POS1]], 1 + // CHECK: [[POS3:%.+]] = sdiv i[[SZ]] [[POS2]], 256 + // CHECK: [[POS4:%.+]] = add i[[SZ]] [[POS3]], 1 + // CHECK: [[SCRATCHPAD_NEXT:%.+]] = mul i[[SZ]] [[POS4]], 256 + // + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 2, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD_NEXT]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to i16* + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16* + // CHECK: [[ELT_VAL:%.+]] = load i16, i16* [[ELT]], align + // CHECK: store i16 [[ELT_VAL]], i16* [[SCRATCHPAD_ELT_PTR]], align + // + // CHECK: ret + + // + // Load and reduce function + // CHECK: define internal void [[LOAD_REDUCE_FN]](i8*, i8*, i32, i32, i32) + // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align + // CHECK: [[REMOTE_ELT1:%.+]] = alloca i32 + // CHECK: [[REMOTE_ELT2:%.+]] = alloca i16 + // CHECK: [[RED_LIST:%.+]] = bitcast i8* {{.+}} to [[RLT]]* + // CHECK: [[SCRATCHPAD_PTR:%.+]] = load i8*, i8** {{.+}}, align + // CHECK-64: [[TEAM32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[TEAM:%.+]] = sext i32 [[TEAM32]] to i64 + // CHECK-32: [[TEAM:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS32:%.+]] = load i32, i32* {{.+}}, align + // CHECK-64: [[NUM_TEAMS:%.+]] = sext i32 [[NUM_TEAMS32]] to i64 + // CHECK-32: [[NUM_TEAMS:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SHOULD_REDUCE:%.+]] = load i32, i32* {{.+}}, align + // CHECK: [[SCRATCHPAD:%.+]] = ptrtoint i8* [[SCRATCHPAD_PTR]] to i[[SZ]] + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 4, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to i32* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i32, i32* [[SCRATCHPAD_ELT_PTR]], align + // CHECK: store i32 [[REMOTE_ELT_VAL]], i32* [[REMOTE_ELT1]], align + // CHECK: [[REMOTE_ELT1_PTR:%.+]] = bitcast i32* [[REMOTE_ELT1]] to i8* + // CHECK: store i8* [[REMOTE_ELT1_PTR]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[OF:%.+]] = mul i[[SZ]] [[NUM_TEAMS]], 4 + // CHECK: [[POS1:%.+]] = add i[[SZ]] [[SCRATCHPAD]], [[OF]] + // CHECK: [[POS2:%.+]] = sub i[[SZ]] [[POS1]], 1 + // CHECK: [[POS3:%.+]] = sdiv i[[SZ]] [[POS2]], 256 + // CHECK: [[POS4:%.+]] = add i[[SZ]] [[POS3]], 1 + // CHECK: [[SCRATCHPAD_NEXT:%.+]] = mul i[[SZ]] [[POS4]], 256 + // + // CHECK: [[P:%.+]] = mul i[[SZ]] 2, [[TEAM]] + // CHECK: [[SCRATCHPAD_ELT_PTR64:%.+]] = add i[[SZ]] [[SCRATCHPAD_NEXT]], [[P]] + // CHECK: [[SCRATCHPAD_ELT_PTR_VOID:%.+]] = inttoptr i[[SZ]] [[SCRATCHPAD_ELT_PTR64]] to i8* + + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[SCRATCHPAD_ELT_PTR:%.+]] = bitcast i8* [[SCRATCHPAD_ELT_PTR_VOID]] to i16* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i16, i16* [[SCRATCHPAD_ELT_PTR]], align + // CHECK: store i16 [[REMOTE_ELT_VAL]], i16* [[REMOTE_ELT2]], align + // CHECK: [[REMOTE_ELT_PTR:%.+]] = bitcast i16* [[REMOTE_ELT2]] to i8* + // CHECK: store i8* [[REMOTE_ELT_PTR]], i8** [[REMOTE_ELT_REF]], align + // + // CHECK: [[REDUCE:%.+]] = icmp eq i32 [[SHOULD_REDUCE]], 1 + // CHECK: br i1 [[REDUCE]], label {{%?}}[[DO_REDUCE:.+]], label {{%?}}[[REDUCE_ELSE:.+]] + // + // CHECK: [[DO_REDUCE]] + // CHECK: [[RED_LIST1_VOID:%.+]] = bitcast [[RLT]]* [[RED_LIST]] to i8* + // CHECK: [[RED_LIST2_VOID:%.+]] = bitcast [[RLT]]* [[REMOTE_RED_LIST]] to i8* + // CHECK: call void [[REDUCTION_FUNC]](i8* [[RED_LIST1_VOID]], i8* [[RED_LIST2_VOID]]) + // CHECK: br label {{%?}}[[REDUCE_CONT:.+]] + // + // Copy element from remote reduce list + // CHECK: [[REDUCE_ELSE]] + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to i32* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i32, i32* [[REMOTE_ELT]], align + // CHECK: store i32 [[REMOTE_ELT_VAL]], i32* [[ELT]], align + // + // CHECK: [[REMOTE_ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[REMOTE_RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[REMOTE_ELT_VOID:%.+]] = load i8*, i8** [[REMOTE_ELT_REF]], + // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1 + // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]], + // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16* + // CHECK: [[REMOTE_ELT:%.+]] = bitcast i8* [[REMOTE_ELT_VOID]] to i16* + // CHECK: [[REMOTE_ELT_VAL:%.+]] = load i16, i16* [[REMOTE_ELT]], align + // CHECK: store i16 [[REMOTE_ELT_VAL]], i16* [[ELT]], align + // CHECK: br label {{%?}}[[REDUCE_CONT]] + // + // CHECK: [[REDUCE_CONT]] + // CHECK: ret + + +#endif |