llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-amdgpu @llvm/pr-subscribers-clang-codegen Author: Alok Kumar Sharma (alokkrsharma) <details> <summary>Changes</summary> This fixes https://github.com/llvm/llvm-project/issues/110700 Work-sharing loop iterator variable had incorrect debug info attached to it. It was due to redundant/incorrect debug info overwrites the correct debug info appearing later in LLVM IR. ------------------ define internal void @<!-- -->main.omp_outlined_debug__( ) %i = alloca i32, align 4 ;;------------------ (Incorrect) %i4 = alloca i32, align 4 ;;------------------ (Correct) #dbg_declare(ptr %i, !82, !DIExpression(), !67) ;;--- (Incorrect) store i32 0, ptr %i, align 4, !dbg !83 ;;--- (Incorrect) omp.precond.then: ; preds = %entry #dbg_declare(ptr %i4, !82, !DIExpression(), !67) ;;--- (Correct) omp.inner.for.body: ; preds = %omp.inner.for.cond %18 = load i32, ptr %.omp.iv, align 4, !dbg !85 %mul = mul nsw i32 %18, 1, !dbg !83 %add = add nsw i32 0, %mul, !dbg !83 store i32 %add, ptr %i4, align 4, !dbg !83 ;;--- (Correct) ------------------ Suppressing the incorrect IR, enables emission of correct debug info. --- Patch is 1.32 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/122047.diff 77 Files Affected: - (modified) clang/lib/CodeGen/CGStmtOpenMP.cpp (+2-9) - (modified) clang/test/OpenMP/amdgcn_target_device_vla.cpp (+11-29) - (modified) clang/test/OpenMP/amdgpu_target_with_aligned_attribute.c (+3-9) - (modified) clang/test/OpenMP/bug60602.cpp (-6) - (modified) clang/test/OpenMP/cancel_codegen.cpp (+8-16) - (modified) clang/test/OpenMP/cancellation_point_codegen.cpp (+17-21) - (modified) clang/test/OpenMP/debug-info-openmp-array.cpp (+2-5) - (added) clang/test/OpenMP/debug_loopsharing_iter_var.c (+25) - (modified) clang/test/OpenMP/distribute_codegen.cpp (+4-16) - (modified) clang/test/OpenMP/distribute_parallel_for_codegen.cpp (+18-186) - (modified) clang/test/OpenMP/distribute_parallel_for_simd_codegen.cpp (+186-410) - (modified) clang/test/OpenMP/distribute_simd_codegen.cpp (+42-78) - (modified) clang/test/OpenMP/for_codegen.cpp (+1-3) - (modified) clang/test/OpenMP/for_non_rectangular_codegen.c (+3-10) - (modified) clang/test/OpenMP/generic_loop_codegen.cpp (-8) - (modified) clang/test/OpenMP/interchange_codegen.cpp (+12-72) - (modified) clang/test/OpenMP/irbuilder_unroll_partial_factor_for_collapse.c (-4) - (modified) clang/test/OpenMP/irbuilder_unroll_partial_heuristic_for_collapse.c (-4) - (modified) clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp (+6-14) - (modified) clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp (-10) - (modified) clang/test/OpenMP/nvptx_target_simd_codegen.cpp (-24) - (modified) clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp (+36-96) - (modified) clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp (+6-14) - (modified) clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp (+12-28) - (modified) clang/test/OpenMP/nvptx_target_teams_distribute_simd_codegen.cpp (-24) - (modified) clang/test/OpenMP/nvptx_target_teams_generic_loop_codegen.cpp (+27-75) - (modified) clang/test/OpenMP/nvptx_target_teams_generic_loop_generic_mode_codegen.cpp (-4) - (modified) clang/test/OpenMP/ordered_codegen.cpp (+42-92) - (modified) clang/test/OpenMP/parallel_for_codegen.cpp (+6-43) - (modified) clang/test/OpenMP/parallel_master_taskloop_codegen.cpp (-10) - (modified) clang/test/OpenMP/parallel_master_taskloop_simd_codegen.cpp (+33-103) - (modified) clang/test/OpenMP/reduction_compound_op.cpp (-32) - (modified) clang/test/OpenMP/reduction_implicit_map.cpp (+8-16) - (modified) clang/test/OpenMP/reverse_codegen.cpp (-12) - (modified) clang/test/OpenMP/target_ompx_dyn_cgroup_mem_codegen.cpp (-16) - (modified) clang/test/OpenMP/target_teams_distribute_codegen.cpp (+1-13) - (modified) clang/test/OpenMP/target_teams_distribute_collapse_codegen.cpp (-8) - (modified) clang/test/OpenMP/target_teams_distribute_dist_schedule_codegen.cpp (-12) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_codegen.cpp (-40) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_collapse_codegen.cpp (-16) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_dist_schedule_codegen.cpp (+6-30) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_schedule_codegen.cpp (+12-92) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_simd_codegen.cpp (+14-54) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_simd_collapse_codegen.cpp (-24) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_simd_dist_schedule_codegen.cpp (+68-104) - (modified) clang/test/OpenMP/target_teams_distribute_parallel_for_simd_schedule_codegen.cpp (+142-242) - (modified) clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp (-36) - (modified) clang/test/OpenMP/target_teams_distribute_simd_collapse_codegen.cpp (-16) - (modified) clang/test/OpenMP/target_teams_distribute_simd_dist_schedule_codegen.cpp (+68-92) - (modified) clang/test/OpenMP/target_teams_generic_loop_codegen-1.cpp (-40) - (modified) clang/test/OpenMP/target_teams_generic_loop_codegen_as_parallel_for.cpp (+12-96) - (modified) clang/test/OpenMP/target_teams_generic_loop_collapse_codegen.cpp (-16) - (modified) clang/test/OpenMP/teams_distribute_codegen.cpp (-16) - (modified) clang/test/OpenMP/teams_distribute_collapse_codegen.cpp (-8) - (modified) clang/test/OpenMP/teams_distribute_dist_schedule_codegen.cpp (-12) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_codegen.cpp (-32) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_collapse_codegen.cpp (-16) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_dist_schedule_codegen.cpp (+18-42) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_schedule_codegen.cpp (+12-92) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_simd_codegen.cpp (+14-62) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_simd_collapse_codegen.cpp (-24) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_simd_dist_schedule_codegen.cpp (+86-122) - (modified) clang/test/OpenMP/teams_distribute_parallel_for_simd_schedule_codegen.cpp (+68-168) - (modified) clang/test/OpenMP/teams_distribute_simd_codegen.cpp (+34-74) - (modified) clang/test/OpenMP/teams_distribute_simd_collapse_codegen.cpp (-16) - (modified) clang/test/OpenMP/teams_distribute_simd_dist_schedule_codegen.cpp (+28-52) - (modified) clang/test/OpenMP/teams_generic_loop_codegen-1.cpp (-16) - (modified) clang/test/OpenMP/teams_generic_loop_collapse_codegen.cpp (-8) - (modified) clang/test/OpenMP/tile_codegen.cpp (+18-32) - (modified) clang/test/OpenMP/tile_codegen_for_dependent.cpp (-2) - (modified) clang/test/OpenMP/tile_codegen_tile_for.cpp (-2) - (modified) clang/test/OpenMP/unroll_codegen_for_collapse_outer.cpp (+1-6) - (modified) clang/test/OpenMP/unroll_codegen_for_partial.cpp (-2) - (modified) clang/test/OpenMP/unroll_codegen_parallel_for_factor.cpp (-2) - (modified) clang/test/OpenMP/unroll_codegen_tile_for.cpp (-2) - (modified) clang/test/OpenMP/unroll_codegen_unroll_for.cpp (-2) - (modified) clang/test/OpenMP/unroll_codegen_unroll_for_attr.cpp (+1-3) ``````````diff diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp index 6cb37b20b7aeee..0dcba56698c800 100644 --- a/clang/lib/CodeGen/CGStmtOpenMP.cpp +++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp @@ -2367,15 +2367,8 @@ static void emitPreCond(CodeGenFunction &CGF, const OMPLoopDirective &S, llvm::BasicBlock *FalseBlock, uint64_t TrueCount) { if (!CGF.HaveInsertPoint()) return; - { - CodeGenFunction::OMPPrivateScope PreCondScope(CGF); - CGF.EmitOMPPrivateLoopCounters(S, PreCondScope); - (void)PreCondScope.Privatize(); - // Get initial values of real counters. - for (const Expr *I : S.inits()) { - CGF.EmitIgnoredExpr(I); - } - } + // The Private counters are not needed to be emitted here as these + // are emitted later. // Create temp loop control variables with their init values to support // non-rectangular loops. CodeGenFunction::OMPMapVars PreCondVars; diff --git a/clang/test/OpenMP/amdgcn_target_device_vla.cpp b/clang/test/OpenMP/amdgcn_target_device_vla.cpp index 58fef517a9e72d..72804fd49ed9fa 100644 --- a/clang/test/OpenMP/amdgcn_target_device_vla.cpp +++ b/clang/test/OpenMP/amdgcn_target_device_vla.cpp @@ -151,12 +151,12 @@ int main() { // CHECK: for.end: // CHECK-NEXT: store i32 0, ptr [[I1_ASCAST]], align 4 // CHECK-NEXT: br label [[FOR_COND2:%.*]] -// CHECK: for.cond2: +// CHECK: for.cond // CHECK-NEXT: [[TMP13:%.*]] = load i32, ptr [[I1_ASCAST]], align 4 // CHECK-NEXT: [[TMP14:%.*]] = load i32, ptr [[N_ASCAST]], align 4 // CHECK-NEXT: [[CMP3:%.*]] = icmp slt i32 [[TMP13]], [[TMP14]] // CHECK-NEXT: br i1 [[CMP3]], label [[FOR_BODY4:%.*]], label [[FOR_END9:%.*]] -// CHECK: for.body4: +// CHECK: for.body // CHECK-NEXT: [[TMP15:%.*]] = load i32, ptr [[I1_ASCAST]], align 4 // CHECK-NEXT: [[IDXPROM5:%.*]] = sext i32 [[TMP15]] to i64 // CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IDXPROM5]] @@ -165,12 +165,12 @@ int main() { // CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP17]], [[TMP16]] // CHECK-NEXT: store i32 [[ADD]], ptr [[TMP0]], align 4 // CHECK-NEXT: br label [[FOR_INC7:%.*]] -// CHECK: for.inc7: +// CHECK: for.inc // CHECK-NEXT: [[TMP18:%.*]] = load i32, ptr [[I1_ASCAST]], align 4 // CHECK-NEXT: [[INC8:%.*]] = add nsw i32 [[TMP18]], 1 // CHECK-NEXT: store i32 [[INC8]], ptr [[I1_ASCAST]], align 4 // CHECK-NEXT: br label [[FOR_COND2]], !llvm.loop [[LOOP15:![0-9]+]] -// CHECK: for.end9: +// CHECK: for.end // CHECK-NEXT: call void @__kmpc_free_shared(ptr [[A]], i64 [[TMP7]]) // CHECK-NEXT: call void @__kmpc_target_deinit() // CHECK-NEXT: ret void @@ -228,7 +228,6 @@ int main() { // CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_COMB_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_COMB_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -245,7 +244,6 @@ int main() { // CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR_1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_1]] to ptr -// CHECK-NEXT: [[I_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I]] to ptr // CHECK-NEXT: [[DOTOMP_COMB_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_COMB_LB]] to ptr // CHECK-NEXT: [[DOTOMP_COMB_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_COMB_UB]] to ptr // CHECK-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -267,7 +265,6 @@ int main() { // CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-NEXT: store i32 [[SUB2]], ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 -// CHECK-NEXT: store i32 0, ptr [[I_ASCAST]], align 4 // CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP4]] // CHECK-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] @@ -346,13 +343,13 @@ int main() { // CHECK-NEXT: [[TMP39:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 // CHECK-NEXT: [[CMP9:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]] // CHECK-NEXT: br i1 [[CMP9]], label [[COND_TRUE10:%.*]], label [[COND_FALSE11:%.*]] -// CHECK: cond.true10: +// CHECK: cond.true // CHECK-NEXT: [[TMP40:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 // CHECK-NEXT: br label [[COND_END12:%.*]] -// CHECK: cond.false11: +// CHECK: cond.false // CHECK-NEXT: [[TMP41:%.*]] = load i32, ptr [[DOTOMP_COMB_UB_ASCAST]], align 4 // CHECK-NEXT: br label [[COND_END12]] -// CHECK: cond.end12: +// CHECK: cond.end // CHECK-NEXT: [[COND13:%.*]] = phi i32 [ [[TMP40]], [[COND_TRUE10]] ], [ [[TMP41]], [[COND_FALSE11]] ] // CHECK-NEXT: store i32 [[COND13]], ptr [[DOTOMP_COMB_UB_ASCAST]], align 4 // CHECK-NEXT: [[TMP42:%.*]] = load i32, ptr [[DOTOMP_COMB_LB_ASCAST]], align 4 @@ -383,7 +380,6 @@ int main() { // CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -405,7 +401,6 @@ int main() { // CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR_1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_1]] to ptr -// CHECK-NEXT: [[I_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I]] to ptr // CHECK-NEXT: [[DOTOMP_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_LB]] to ptr // CHECK-NEXT: [[DOTOMP_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_UB]] to ptr // CHECK-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -432,7 +427,6 @@ int main() { // CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-NEXT: store i32 [[SUB2]], ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 -// CHECK-NEXT: store i32 0, ptr [[I_ASCAST]], align 4 // CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP4]] // CHECK-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] @@ -500,12 +494,12 @@ int main() { // CHECK: for.end: // CHECK-NEXT: store i32 0, ptr [[J11_ASCAST]], align 4 // CHECK-NEXT: br label [[FOR_COND12:%.*]] -// CHECK: for.cond12: +// CHECK: for.cond // CHECK-NEXT: [[TMP24:%.*]] = load i32, ptr [[J11_ASCAST]], align 4 // CHECK-NEXT: [[TMP25:%.*]] = load i32, ptr [[N_ASCAST]], align 4 // CHECK-NEXT: [[CMP13:%.*]] = icmp slt i32 [[TMP24]], [[TMP25]] // CHECK-NEXT: br i1 [[CMP13]], label [[FOR_BODY14:%.*]], label [[FOR_END22:%.*]] -// CHECK: for.body14: +// CHECK: for.body // CHECK-NEXT: [[TMP26:%.*]] = load i32, ptr [[J11_ASCAST]], align 4 // CHECK-NEXT: [[IDXPROM15:%.*]] = sext i32 [[TMP26]] to i64 // CHECK-NEXT: [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, ptr [[VLA7_ASCAST]], i64 [[IDXPROM15]] @@ -517,12 +511,12 @@ int main() { // CHECK-NEXT: [[ADD19:%.*]] = add nsw i32 [[TMP29]], [[TMP27]] // CHECK-NEXT: store i32 [[ADD19]], ptr [[ARRAYIDX18]], align 4 // CHECK-NEXT: br label [[FOR_INC20:%.*]] -// CHECK: for.inc20: +// CHECK: for.inc // CHECK-NEXT: [[TMP30:%.*]] = load i32, ptr [[J11_ASCAST]], align 4 // CHECK-NEXT: [[INC21:%.*]] = add nsw i32 [[TMP30]], 1 // CHECK-NEXT: store i32 [[INC21]], ptr [[J11_ASCAST]], align 4 // CHECK-NEXT: br label [[FOR_COND12]], !llvm.loop [[LOOP17:![0-9]+]] -// CHECK: for.end22: +// CHECK: for.end // CHECK-NEXT: [[TMP31:%.*]] = load ptr addrspace(5), ptr [[SAVED_STACK_ASCAST]], align 4 // CHECK-NEXT: call void @llvm.stackrestore.p5(ptr addrspace(5) [[TMP31]]) // CHECK-NEXT: br label [[OMP_BODY_CONTINUE:%.*]] @@ -597,7 +591,6 @@ int main() { // CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -615,7 +608,6 @@ int main() { // CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR_1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_1]] to ptr -// CHECK-NEXT: [[I_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I]] to ptr // CHECK-NEXT: [[DOTOMP_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_LB]] to ptr // CHECK-NEXT: [[DOTOMP_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_UB]] to ptr // CHECK-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -639,7 +631,6 @@ int main() { // CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-NEXT: store i32 [[SUB2]], ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 -// CHECK-NEXT: store i32 0, ptr [[I_ASCAST]], align 4 // CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP4]] // CHECK-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] @@ -760,7 +751,6 @@ int main() { // CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-NEXT: [[J:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -775,7 +765,6 @@ int main() { // CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR_1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_1]] to ptr -// CHECK-NEXT: [[J_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[J]] to ptr // CHECK-NEXT: [[DOTOMP_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_LB]] to ptr // CHECK-NEXT: [[DOTOMP_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_UB]] to ptr // CHECK-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -796,7 +785,6 @@ int main() { // CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-NEXT: store i32 [[SUB2]], ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 -// CHECK-NEXT: store i32 0, ptr [[J_ASCAST]], align 4 // CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP5]] // CHECK-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] @@ -963,7 +951,6 @@ int main() { // CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -982,7 +969,6 @@ int main() { // CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR_2_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_2]] to ptr -// CHECK-NEXT: [[I_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I]] to ptr // CHECK-NEXT: [[DOTOMP_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_LB]] to ptr // CHECK-NEXT: [[DOTOMP_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_UB]] to ptr // CHECK-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -1009,7 +995,6 @@ int main() { // CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-NEXT: [[SUB3:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-NEXT: store i32 [[SUB3]], ptr [[DOTCAPTURE_EXPR_2_ASCAST]], align 4 -// CHECK-NEXT: store i32 0, ptr [[I_ASCAST]], align 4 // CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP5]] // CHECK-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] @@ -1129,7 +1114,6 @@ int main() { // CHECK-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-NEXT: [[J:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -1144,7 +1128,6 @@ int main() { // CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-NEXT: [[DOTCAPTURE_EXPR_1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_1]] to ptr -// CHECK-NEXT: [[J_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[J]] to ptr // CHECK-NEXT: [[DOTOMP_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_LB]] to ptr // CHECK-NEXT: [[DOTOMP_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_UB]] to ptr // CHECK-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -1165,7 +1148,6 @@ int main() { // CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-NEXT: store i32 [[SUB2]], ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 -// CHECK-NEXT: store i32 0, ptr [[J_ASCAST]], align 4 // CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP5]] // CHECK-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] diff --git a/clang/test/OpenMP/amdgpu_target_with_aligned_attribute.c b/clang/test/OpenMP/amdgpu_target_with_aligned_attribute.c index cc0cc0def48b81..2e2689da692592 100644 --- a/clang/test/OpenMP/amdgpu_target_with_aligned_attribute.c +++ b/clang/test/OpenMP/amdgpu_target_with_aligned_attribute.c @@ -65,7 +65,6 @@ void write_to_aligned_array(int *a, int N) { // CHECK-AMD-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-AMD-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTOMP_COMB_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTOMP_COMB_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -81,7 +80,6 @@ void write_to_aligned_array(int *a, int N) { // CHECK-AMD-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR_1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_1]] to ptr -// CHECK-AMD-NEXT: [[I_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I]] to ptr // CHECK-AMD-NEXT: [[DOTOMP_COMB_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_COMB_LB]] to ptr // CHECK-AMD-NEXT: [[DOTOMP_COMB_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_COMB_UB]] to ptr // CHECK-AMD-NEXT: [[DOTOMP_STRIDE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_STRIDE]] to ptr @@ -100,7 +98,6 @@ void write_to_aligned_array(int *a, int N) { // CHECK-AMD-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1 // CHECK-AMD-NEXT: [[SUB2:%.*]] = sub nsw i32 [[DIV]], 1 // CHECK-AMD-NEXT: store i32 [[SUB2]], ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 -// CHECK-AMD-NEXT: store i32 0, ptr [[I_ASCAST]], align 4 // CHECK-AMD-NEXT: [[TMP2:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4 // CHECK-AMD-NEXT: [[CMP:%.*]] = icmp slt i32 0, [[TMP2]] // CHECK-AMD-NEXT: br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]] @@ -177,13 +174,13 @@ void write_to_aligned_array(int *a, int N) { // CHECK-AMD-NEXT: [[TMP36:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 // CHECK-AMD-NEXT: [[CMP9:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]] // CHECK-AMD-NEXT: br i1 [[CMP9]], label [[COND_TRUE10:%.*]], label [[COND_FALSE11:%.*]] -// CHECK-AMD: cond.true10: +// CHECK-AMD: cond.true // CHECK-AMD-NEXT: [[TMP37:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1_ASCAST]], align 4 // CHECK-AMD-NEXT: br label [[COND_END12:%.*]] -// CHECK-AMD: cond.false11: +// CHECK-AMD: cond.false // CHECK-AMD-NEXT: [[TMP38:%.*]] = load i32, ptr [[DOTOMP_COMB_UB_ASCAST]], align 4 // CHECK-AMD-NEXT: br label [[COND_END12]] -// CHECK-AMD: cond.end12: +// CHECK-AMD: cond.end // CHECK-AMD-NEXT: [[COND13:%.*]] = phi i32 [ [[TMP37]], [[COND_TRUE10]] ], [ [[TMP38]], [[COND_FALSE11]] ] // CHECK-AMD-NEXT: store i32 [[COND13]], ptr [[DOTOMP_COMB_UB_ASCAST]], align 4 // CHECK-AMD-NEXT: [[TMP39:%.*]] = load i32, ptr [[DOTOMP_COMB_LB_ASCAST]], align 4 @@ -213,7 +210,6 @@ void write_to_aligned_array(int *a, int N) { // CHECK-AMD-NEXT: [[TMP:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR_1:%.*]] = alloca i32, align 4, addrspace(5) -// CHECK-AMD-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5) // CHECK-AMD-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4, addrspace(5) @@ -229,7 +225,6 @@ void write_to_aligned_array(int *a, int N) { // CHECK-AMD-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr // CHECK-AMD-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr // CHECK-AMD... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/122047 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
