[clang] [clang] Generate nuw GEPs for struct member accesses (PR #99538)
via cfe-commits
cfe-commits at lists.llvm.org
Thu Jul 18 11:10:29 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Hari Limaye (hazzlim)
<details>
<summary>Changes</summary>
Generate nuw GEPs for struct member accesses, as these are always constant positive offsets derived from the index of the struct member.
Regression tests are updated using update_cc_test_checks.py where possible, and by find + replace where not.
---
Patch is 7.54 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/99538.diff
456 Files Affected:
- (modified) clang/lib/CodeGen/CGBuilder.h (+3-3)
- (modified) clang/test/C/C2y/n3254.c (+13-13)
- (modified) clang/test/C/C2y/n3259.c (+16-16)
- (modified) clang/test/CodeGen/PowerPC/powerpc-c99complex.c (+6-6)
- (modified) clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c (+1-1)
- (modified) clang/test/CodeGen/RISCV/bfloat-abi.c (+60-60)
- (modified) clang/test/CodeGen/RISCV/riscv32-vararg.c (+42-42)
- (modified) clang/test/CodeGen/RISCV/riscv64-vararg.c (+27-27)
- (modified) clang/test/CodeGen/SystemZ/systemz-abi-vector.c (+52-52)
- (modified) clang/test/CodeGen/SystemZ/systemz-abi.c (+61-61)
- (modified) clang/test/CodeGen/X86/Float16-arithmetic.c (+25-25)
- (modified) clang/test/CodeGen/X86/Float16-complex.c (+328-328)
- (modified) clang/test/CodeGen/X86/cx-complex-range.c (+197-192)
- (modified) clang/test/CodeGen/X86/va-arg-sse.c (+25-25)
- (modified) clang/test/CodeGen/X86/x86_64-floatvectors.c (+14-14)
- (modified) clang/test/CodeGen/X86/x86_64-vaarg.c (+5-5)
- (modified) clang/test/CodeGen/aapcs-bitfield.c (+216-216)
- (modified) clang/test/CodeGen/aarch64-neon-intrinsics.c (+360-360)
- (modified) clang/test/CodeGen/aarch64-neon-ldst-one.c (+672-672)
- (modified) clang/test/CodeGen/aarch64-neon-perm.c (+54-54)
- (modified) clang/test/CodeGen/aarch64-neon-tbl.c (+156-156)
- (modified) clang/test/CodeGen/aarch64-poly64.c (+24-24)
- (modified) clang/test/CodeGen/aarch64-soft-float-abi.c (+4-4)
- (modified) clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics-generic.c (+6-6)
- (modified) clang/test/CodeGen/address-space-field1.c (+4-4)
- (modified) clang/test/CodeGen/align_value.cpp (+2-2)
- (modified) clang/test/CodeGen/alloc-align-attr.c (+31-31)
- (modified) clang/test/CodeGen/annotations-field.c (+1-1)
- (modified) clang/test/CodeGen/arm-neon-vst.c (+288-288)
- (modified) clang/test/CodeGen/arm-swiftcall.c (+78-78)
- (modified) clang/test/CodeGen/arm-varargs.c (+2-2)
- (modified) clang/test/CodeGen/arm64-arguments.c (+48-48)
- (modified) clang/test/CodeGen/arm64-be-bitfield.c (+1-1)
- (modified) clang/test/CodeGen/arm64-be-hfa-vararg.c (+2-2)
- (modified) clang/test/CodeGen/arm_neon_intrinsics.c (+708-708)
- (modified) clang/test/CodeGen/attr-arm-sve-vector-bits-bitcast.c (+24-24)
- (modified) clang/test/CodeGen/attr-counted-by-pr88931.c (+1-1)
- (modified) clang/test/CodeGen/attr-counted-by.c (+50-50)
- (modified) clang/test/CodeGen/block-byref-aggr.c (+8-8)
- (modified) clang/test/CodeGen/blocks-seq.c (+2-2)
- (modified) clang/test/CodeGen/blocks.c (+4-4)
- (modified) clang/test/CodeGen/builtin-complex.c (+2-2)
- (modified) clang/test/CodeGen/builtin-dump-struct.c (+31-31)
- (modified) clang/test/CodeGen/builtins.c (+4-4)
- (modified) clang/test/CodeGen/c11atomics-ios.c (+30-30)
- (modified) clang/test/CodeGen/c11atomics.c (+32-32)
- (modified) clang/test/CodeGen/capture-complex-expr-in-block.c (+2-2)
- (modified) clang/test/CodeGen/captured-statements-nested.c (+20-20)
- (modified) clang/test/CodeGen/captured-statements.c (+2-2)
- (modified) clang/test/CodeGen/catch-alignment-assumption-attribute-align_value-on-lvalue.cpp (+1-1)
- (modified) clang/test/CodeGen/complex-convert.c (+176-176)
- (modified) clang/test/CodeGen/compound-literal.c (+7-7)
- (modified) clang/test/CodeGen/cx-complex-range.c (+764-764)
- (modified) clang/test/CodeGen/ext-int.c (+9-9)
- (modified) clang/test/CodeGen/matrix-type-builtins.c (+2-2)
- (modified) clang/test/CodeGen/matrix-type.c (+2-2)
- (modified) clang/test/CodeGen/ms-anonymous-struct.c (+24-24)
- (modified) clang/test/CodeGen/packed-structure.c (+1-1)
- (modified) clang/test/CodeGen/paren-list-agg-init.cpp (+41-41)
- (modified) clang/test/CodeGen/pragma-cx-limited-range.c (+2-2)
- (modified) clang/test/CodeGen/smiths-complex-div.c (+6-6)
- (modified) clang/test/CodeGen/transparent-union-redecl.c (+3-3)
- (modified) clang/test/CodeGen/unaligned-expr.c (+2-2)
- (modified) clang/test/CodeGen/variadic-gpfp-x86.c (+1-1)
- (modified) clang/test/CodeGen/variadic-nvptx.c (+9-9)
- (modified) clang/test/CodeGen/windows-seh-EHa-CppCondiTemps.cpp (+3-3)
- (modified) clang/test/CodeGen/windows-swiftcall.c (+56-56)
- (modified) clang/test/CodeGenCUDA/lambda-reference-var.cu (+3-3)
- (modified) clang/test/CodeGenCUDA/record-layout.cu (+6-6)
- (modified) clang/test/CodeGenCXX/RelativeVTablesABI/type-info.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/alignment.cpp (+8-8)
- (modified) clang/test/CodeGenCXX/arm-swiftcall.cpp (+16-16)
- (modified) clang/test/CodeGenCXX/asm.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/attr-annotate.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/attr-target-mv-inalloca.cpp (+9-9)
- (modified) clang/test/CodeGenCXX/auto-var-init.cpp (+24-24)
- (modified) clang/test/CodeGenCXX/bitfield-ir.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/bitfield.cpp (+16-16)
- (modified) clang/test/CodeGenCXX/block-capture.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/block-inalloca.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/blocks-cxx11.cpp (+4-4)
- (modified) clang/test/CodeGenCXX/blocks.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/builtin-dump-struct.cpp (+8-8)
- (modified) clang/test/CodeGenCXX/captured-statements.cpp (+6-6)
- (modified) clang/test/CodeGenCXX/catch-undef-behavior.cpp (+4-4)
- (modified) clang/test/CodeGenCXX/copy-constructor-synthesis.cpp (+4-4)
- (modified) clang/test/CodeGenCXX/cxx11-initializer-aggregate.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/cxx11-initializer-array-new.cpp (+6-6)
- (modified) clang/test/CodeGenCXX/cxx1z-lambda-star-this.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/cxx20-consteval-crash.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/cxx20-decomposition.cpp (+6-6)
- (modified) clang/test/CodeGenCXX/cxx2a-compare.cpp (+5-5)
- (modified) clang/test/CodeGenCXX/cxx2a-consteval.cpp (+10-10)
- (modified) clang/test/CodeGenCXX/cxx2b-deducing-this.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/debug-info-lambda.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/debug-info-ptr-to-ptr.cpp (+7-7)
- (modified) clang/test/CodeGenCXX/decl-ref-inheritance.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/eh-aggregated-inits-unwind.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/exceptions-seh-filter-captures.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/exceptions.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/ext-int.cpp (+9-9)
- (modified) clang/test/CodeGenCXX/ibm128-declarations.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/inalloca-lambda.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/inalloca-overaligned.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/inalloca-vector.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/lambda-deterministic-captures.cpp (+6-6)
- (modified) clang/test/CodeGenCXX/matrix-type-builtins.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/matrix-type-operators.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/matrix-type.cpp (+9-9)
- (modified) clang/test/CodeGenCXX/microsoft-abi-arg-order.cpp (+6-6)
- (modified) clang/test/CodeGenCXX/microsoft-abi-byval-thunks.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/microsoft-abi-eh-cleanups.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/microsoft-abi-explicit-object-parameters.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/microsoft-abi-sret-and-byval.cpp (+5-5)
- (modified) clang/test/CodeGenCXX/microsoft-abi-virtual-inheritance.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/microsoft-abi-vtables-multiple-nonvirtual-inheritance-this-adjustment.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/new-array-init.cpp (+8-8)
- (modified) clang/test/CodeGenCXX/noescape.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/nrvo.cpp (+158-158)
- (modified) clang/test/CodeGenCXX/partial-destruction.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/pr20897.cpp (+4-4)
- (modified) clang/test/CodeGenCXX/strict-vtable-pointers.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/temporaries.cpp (+3-3)
- (modified) clang/test/CodeGenCXX/trivial-auto-var-init.cpp (+4-4)
- (modified) clang/test/CodeGenCXX/trivial_abi.cpp (+9-9)
- (modified) clang/test/CodeGenCXX/trivial_abi_debuginfo.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/ubsan-global-alignment.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/vararg-non-pod-ms-compat.cpp (+1-1)
- (modified) clang/test/CodeGenCXX/virtual-bases.cpp (+2-2)
- (modified) clang/test/CodeGenCXX/vla-lambda-capturing.cpp (+30-30)
- (modified) clang/test/CodeGenCXX/x86_64-vaarg.cpp (+3-3)
- (modified) clang/test/CodeGenCoroutines/coro-await.cpp (+1-1)
- (modified) clang/test/CodeGenCoroutines/coro-params.cpp (+2-2)
- (modified) clang/test/CodeGenHLSL/buffer-array-operator.hlsl (+2-2)
- (modified) clang/test/CodeGenHLSL/this-assignment-overload.hlsl (+4-4)
- (modified) clang/test/CodeGenHLSL/this-assignment.hlsl (+2-2)
- (modified) clang/test/CodeGenHLSL/this-reference.hlsl (+2-2)
- (modified) clang/test/CodeGenObjC/arc-blocks.m (+45-45)
- (modified) clang/test/CodeGenObjC/arc-foreach.m (+8-8)
- (modified) clang/test/CodeGenObjC/arc-unoptimized-byref-var.m (+2-2)
- (modified) clang/test/CodeGenObjC/asm.m (+2-2)
- (modified) clang/test/CodeGenObjC/block-6.m (+3-3)
- (modified) clang/test/CodeGenObjC/blocks-2.m (+1-1)
- (modified) clang/test/CodeGenObjC/blocks.m (+12-12)
- (modified) clang/test/CodeGenObjC/category-super-class-meth.m (+1-1)
- (modified) clang/test/CodeGenObjC/class-stubs.m (+2-2)
- (modified) clang/test/CodeGenObjC/noescape.m (+6-6)
- (modified) clang/test/CodeGenObjC/nontrivial-c-struct-property.m (+2-2)
- (modified) clang/test/CodeGenObjC/nontrivial-struct-param-init.m (+1-1)
- (modified) clang/test/CodeGenObjC/ns_consume_null_check.m (+4-4)
- (modified) clang/test/CodeGenObjC/objc-dispatch-null-check.m (+2-2)
- (modified) clang/test/CodeGenObjC/objc-non-trivial-struct-nrvo.m (+1-1)
- (modified) clang/test/CodeGenObjC/property-array-type.m (+1-1)
- (modified) clang/test/CodeGenObjC/strong-in-c-struct.m (+18-18)
- (modified) clang/test/CodeGenObjCXX/arc-blocks.mm (+24-24)
- (modified) clang/test/CodeGenObjCXX/arc-cxx11-init-list.mm (+1-1)
- (modified) clang/test/CodeGenObjCXX/arc-cxx11-member-init.mm (+1-1)
- (modified) clang/test/CodeGenObjCXX/arc-exceptions.mm (+2-2)
- (modified) clang/test/CodeGenObjCXX/arc-indirect.mm (+1-1)
- (modified) clang/test/CodeGenObjCXX/arc-special-member-functions.mm (+2-2)
- (modified) clang/test/CodeGenObjCXX/block-default-arg.mm (+1-1)
- (modified) clang/test/CodeGenObjCXX/block-nested-in-lambda.mm (+16-16)
- (modified) clang/test/CodeGenObjCXX/gc.mm (+1-1)
- (modified) clang/test/CodeGenObjCXX/lambda-expressions.mm (+5-5)
- (modified) clang/test/CodeGenObjCXX/lambda-to-block.mm (+4-4)
- (modified) clang/test/CodeGenObjCXX/objc-struct-cxx-abi.mm (+6-6)
- (modified) clang/test/CodeGenObjCXX/property-object-conditional-exp.mm (+2-2)
- (modified) clang/test/CodeGenObjCXX/property-objects.mm (+1-1)
- (modified) clang/test/CodeGenOpenCL/addr-space-struct-arg.cl (+1-1)
- (modified) clang/test/CodeGenOpenCL/amdgpu-abi-struct-arg-byref.cl (+24-24)
- (modified) clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl (+152-151)
- (modified) clang/test/CodeGenOpenCL/blocks.cl (+10-10)
- (modified) clang/test/CodeGenOpenCL/cl20-device-side-enqueue-attributes.cl (+30-30)
- (modified) clang/test/CodeGenOpenCLCXX/addrspace-operators.clcpp (+2-2)
- (modified) clang/test/CodeGenSYCL/field-annotate-addr-space.cpp (+1-1)
- (modified) clang/test/OpenMP/atomic_capture_codegen.cpp (+20-20)
- (modified) clang/test/OpenMP/atomic_update_codegen.cpp (+20-20)
- (modified) clang/test/OpenMP/bug57757.cpp (+4-4)
- (modified) clang/test/OpenMP/cancel_codegen.cpp (+47-47)
- (modified) clang/test/OpenMP/cancellation_point_codegen.cpp (+37-37)
- (modified) clang/test/OpenMP/critical_codegen.cpp (+2-2)
- (modified) clang/test/OpenMP/critical_codegen_attr.cpp (+2-2)
- (modified) clang/test/OpenMP/declare_mapper_codegen.cpp (+46-46)
- (modified) clang/test/OpenMP/depobj_codegen.cpp (+22-22)
- (modified) clang/test/OpenMP/distribute_firstprivate_codegen.cpp (+20-20)
- (modified) clang/test/OpenMP/distribute_lastprivate_codegen.cpp (+20-20)
- (modified) clang/test/OpenMP/distribute_parallel_for_codegen.cpp (+66-66)
- (modified) clang/test/OpenMP/distribute_parallel_for_firstprivate_codegen.cpp (+20-20)
- (modified) clang/test/OpenMP/distribute_parallel_for_lastprivate_codegen.cpp (+20-20)
- (modified) clang/test/OpenMP/distribute_parallel_for_num_threads_codegen.cpp (+8-8)
- (modified) clang/test/OpenMP/distribute_parallel_for_private_codegen.cpp (+16-16)
- (modified) clang/test/OpenMP/distribute_parallel_for_reduction_task_codegen.cpp (+31-31)
- (modified) clang/test/OpenMP/distribute_parallel_for_simd_codegen.cpp (+76-76)
- (modified) clang/test/OpenMP/distribute_parallel_for_simd_firstprivate_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/distribute_parallel_for_simd_lastprivate_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/distribute_parallel_for_simd_num_threads_codegen.cpp (+12-12)
- (modified) clang/test/OpenMP/distribute_parallel_for_simd_private_codegen.cpp (+24-24)
- (modified) clang/test/OpenMP/distribute_private_codegen.cpp (+16-16)
- (modified) clang/test/OpenMP/distribute_simd_firstprivate_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/distribute_simd_lastprivate_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/distribute_simd_private_codegen.cpp (+24-24)
- (modified) clang/test/OpenMP/distribute_simd_reduction_codegen.cpp (+1-1)
- (modified) clang/test/OpenMP/for_firstprivate_codegen.cpp (+34-34)
- (modified) clang/test/OpenMP/for_lastprivate_codegen.cpp (+113-113)
- (modified) clang/test/OpenMP/for_linear_codegen.cpp (+62-62)
- (modified) clang/test/OpenMP/for_private_codegen.cpp (+17-17)
- (modified) clang/test/OpenMP/for_reduction_codegen.cpp (+13-13)
- (modified) clang/test/OpenMP/for_reduction_codegen_UDR.cpp (+16-16)
- (modified) clang/test/OpenMP/for_reduction_task_codegen.cpp (+47-47)
- (modified) clang/test/OpenMP/interop_irbuilder.cpp (+49-49)
- (modified) clang/test/OpenMP/irbuilder_for_iterator.cpp (+28-28)
- (modified) clang/test/OpenMP/irbuilder_for_rangefor.cpp (+28-28)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned_auto.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned_down.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned_dynamic.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned_dynamic_chunked.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned_runtime.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_for_unsigned_static_chunked.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_nested_parallel_for.c (+80-80)
- (modified) clang/test/OpenMP/irbuilder_safelen.cpp (+22-22)
- (modified) clang/test/OpenMP/irbuilder_safelen_order_concurrent.cpp (+24-24)
- (modified) clang/test/OpenMP/irbuilder_simd.cpp (+3-3)
- (modified) clang/test/OpenMP/irbuilder_simd_aligned.cpp (+26-26)
- (modified) clang/test/OpenMP/irbuilder_simdlen.cpp (+24-24)
- (modified) clang/test/OpenMP/irbuilder_simdlen_safelen.cpp (+22-22)
- (modified) clang/test/OpenMP/irbuilder_unroll_full.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_unroll_heuristic.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_unroll_partial_factor.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_unroll_partial_factor_for.c (+6-6)
- (modified) clang/test/OpenMP/irbuilder_unroll_partial_heuristic.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_unroll_unroll_partial_factor.c (+4-4)
- (modified) clang/test/OpenMP/irbuilder_unroll_unroll_partial_heuristic.c (+4-4)
- (modified) clang/test/OpenMP/loops_explicit_clauses_codegen.cpp (+19-19)
- (modified) clang/test/OpenMP/map_struct_ordering.cpp (+9-9)
- (modified) clang/test/OpenMP/master_taskloop_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/master_taskloop_firstprivate_codegen.cpp (+57-57)
- (modified) clang/test/OpenMP/master_taskloop_in_reduction_codegen.cpp (+63-63)
- (modified) clang/test/OpenMP/master_taskloop_lastprivate_codegen.cpp (+57-57)
- (modified) clang/test/OpenMP/master_taskloop_private_codegen.cpp (+44-44)
- (modified) clang/test/OpenMP/master_taskloop_reduction_codegen.cpp (+28-28)
- (modified) clang/test/OpenMP/master_taskloop_simd_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/master_taskloop_simd_firstprivate_codegen.cpp (+57-57)
- (modified) clang/test/OpenMP/master_taskloop_simd_in_reduction_codegen.cpp (+64-64)
- (modified) clang/test/OpenMP/master_taskloop_simd_lastprivate_codegen.cpp (+57-57)
- (modified) clang/test/OpenMP/master_taskloop_simd_private_codegen.cpp (+44-44)
- (modified) clang/test/OpenMP/master_taskloop_simd_reduction_codegen.cpp (+28-28)
- (modified) clang/test/OpenMP/nested_loop_codegen.cpp (+16-16)
- (modified) clang/test/OpenMP/nvptx_lambda_pointer_capturing.cpp (+7-7)
- (modified) clang/test/OpenMP/nvptx_target_codegen.cpp (+14-14)
- (modified) clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp (+322-322)
- (modified) clang/test/OpenMP/ordered_doacross_codegen.c (+2-2)
- (modified) clang/test/OpenMP/ordered_doacross_codegen.cpp (+8-8)
- (modified) clang/test/OpenMP/parallel_copyin_codegen.cpp (+12-12)
- (modified) clang/test/OpenMP/parallel_firstprivate_codegen.cpp (+161-161)
- (modified) clang/test/OpenMP/parallel_for_lastprivate_conditional.cpp (+6-6)
- (modified) clang/test/OpenMP/parallel_for_linear_codegen.cpp (+12-12)
- (modified) clang/test/OpenMP/parallel_for_reduction_task_codegen.cpp (+47-47)
- (modified) clang/test/OpenMP/parallel_master_codegen.cpp (+14-14)
- (modified) clang/test/OpenMP/parallel_master_reduction_task_codegen.cpp (+47-47)
- (modified) clang/test/OpenMP/parallel_master_taskloop_codegen.cpp (+234-234)
- (modified) clang/test/OpenMP/parallel_master_taskloop_firstprivate_codegen.cpp (+169-169)
- (modified) clang/test/OpenMP/parallel_master_taskloop_lastprivate_codegen.cpp (+182-182)
- (modified) clang/test/OpenMP/parallel_master_taskloop_private_codegen.cpp (+40-40)
- (modified) clang/test/OpenMP/parallel_master_taskloop_reduction_codegen.cpp (+28-28)
- (modified) clang/test/OpenMP/parallel_master_taskloop_simd_codegen.cpp (+231-231)
- (modified) clang/test/OpenMP/parallel_master_taskloop_simd_firstprivate_codegen.cpp (+169-169)
- (modified) clang/test/OpenMP/parallel_master_taskloop_simd_lastprivate_codegen.cpp (+192-192)
- (modified) clang/test/OpenMP/parallel_master_taskloop_simd_private_codegen.cpp (+40-40)
- (modified) clang/test/OpenMP/parallel_master_taskloop_simd_reduction_codegen.cpp (+28-28)
- (modified) clang/test/OpenMP/parallel_private_codegen.cpp (+44-44)
- (modified) clang/test/OpenMP/parallel_reduction_codegen.cpp (+84-84)
- (modified) clang/test/OpenMP/parallel_reduction_task_codegen.cpp (+47-47)
- (modified) clang/test/OpenMP/parallel_sections_reduction_task_codegen.cpp (+48-48)
- (modified) clang/test/OpenMP/reduction_compound_op.cpp (+98-98)
- (modified) clang/test/OpenMP/reduction_implicit_map.cpp (+38-38)
- (modified) clang/test/OpenMP/reverse_codegen.cpp (+6-5)
- (modified) clang/test/OpenMP/sections_firstprivate_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/sections_lastprivate_codegen.cpp (+26-26)
- (modified) clang/test/OpenMP/sections_private_codegen.cpp (+13-13)
- (modified) clang/test/OpenMP/sections_reduction_codegen.cpp (+11-11)
- (modified) clang/test/OpenMP/sections_reduction_task_codegen.cpp (+48-48)
- (modified) clang/test/OpenMP/simd_private_taskloop_codegen.cpp (+196-196)
- (modified) clang/test/OpenMP/single_codegen.cpp (+662-662)
- (modified) clang/test/OpenMP/single_firstprivate_codegen.cpp (+32-32)
- (modified) clang/test/OpenMP/single_private_codegen.cpp (+13-13)
- (modified) clang/test/OpenMP/target_codegen.cpp (+10-10)
- (modified) clang/test/OpenMP/target_data_map_codegen_hold.cpp (+44-44)
- (modified) clang/test/OpenMP/target_data_no_device_codegen.cpp (+2-2)
- (modified) clang/test/OpenMP/target_data_use_device_addr_codegen.cpp (+8-8)
- (modified) clang/test/OpenMP/target_data_use_device_ptr_codegen.cpp (+5-5)
- (modified) clang/test/OpenMP/target_data_use_device_ptr_inheritance_codegen.cpp (+14-14)
- (modified) clang/test/OpenMP/target_defaultmap_codegen_01.cpp (+8-8)
- (modified) clang/test/OpenMP/target_defaultmap_codegen_02.cpp (+1-1)
- (modified) clang/test/OpenMP/target_depend_codegen.cpp (+14-14)
``````````diff
diff --git a/clang/lib/CodeGen/CGBuilder.h b/clang/lib/CodeGen/CGBuilder.h
index 5d59d5a4ae2c1..66bd2e4d36d3f 100644
--- a/clang/lib/CodeGen/CGBuilder.h
+++ b/clang/lib/CodeGen/CGBuilder.h
@@ -210,10 +210,10 @@ class CGBuilderTy : public CGBuilderBaseTy {
/// Given
/// %addr = {T1, T2...}* ...
/// produce
- /// %name = getelementptr inbounds %addr, i32 0, i32 index
+ /// %name = getelementptr inbounds nuw %addr, i32 0, i32 index
///
/// This API assumes that drilling into a struct like this is always an
- /// inbounds operation.
+ /// inbounds and nuw operation.
using CGBuilderBaseTy::CreateStructGEP;
Address CreateStructGEP(Address Addr, unsigned Index,
const llvm::Twine &Name = "") {
@@ -222,7 +222,7 @@ class CGBuilderTy : public CGBuilderBaseTy {
const llvm::StructLayout *Layout = DL.getStructLayout(ElTy);
auto Offset = CharUnits::fromQuantity(Layout->getElementOffset(Index));
- return Address(CreateStructGEP(Addr.getElementType(), Addr.getBasePointer(),
+ return Address(CreateNUWStructGEP(Addr.getElementType(), Addr.getBasePointer(),
Index, Name),
ElTy->getElementType(Index),
Addr.getAlignment().alignmentAtOffset(Offset),
diff --git a/clang/test/C/C2y/n3254.c b/clang/test/C/C2y/n3254.c
index 60d068cf9980b..e114735a9cb79 100644
--- a/clang/test/C/C2y/n3254.c
+++ b/clang/test/C/C2y/n3254.c
@@ -27,7 +27,7 @@ struct S {
// CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
// CHECK-NEXT: store ptr [[ARRAYDECAY]], ptr [[S_PTR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[S_PTR]], align 8
-// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[TMP0]], i32 0, i32 0
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_S:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[X]], align 4
// CHECK-NEXT: ret i32 [[TMP1]]
//
@@ -42,10 +42,10 @@ int foo() {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[BUFFER:%.*]] = alloca [12 x i8], align 4
// CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
-// CHECK-NEXT: [[C:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 1
+// CHECK-NEXT: [[C:%.*]] = getelementptr inbounds nuw [[STRUCT_S:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 1
// CHECK-NEXT: store i8 97, ptr [[C]], align 4
// CHECK-NEXT: [[ARRAYDECAY1:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
-// CHECK-NEXT: [[C2:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[ARRAYDECAY1]], i32 0, i32 1
+// CHECK-NEXT: [[C2:%.*]] = getelementptr inbounds nuw [[STRUCT_S]], ptr [[ARRAYDECAY1]], i32 0, i32 1
// CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[C2]], align 4
// CHECK-NEXT: ret i8 [[TMP0]]
//
@@ -60,10 +60,10 @@ char bar() {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[BUFFER:%.*]] = alloca [12 x i8], align 4
// CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
-// CHECK-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 2
+// CHECK-NEXT: [[F:%.*]] = getelementptr inbounds nuw [[STRUCT_S:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 2
// CHECK-NEXT: store float 3.000000e+00, ptr [[F]], align 4
// CHECK-NEXT: [[ARRAYDECAY1:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
-// CHECK-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[ARRAYDECAY1]], i32 0, i32 2
+// CHECK-NEXT: [[F2:%.*]] = getelementptr inbounds nuw [[STRUCT_S]], ptr [[ARRAYDECAY1]], i32 0, i32 2
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F2]], align 4
// CHECK-NEXT: ret float [[TMP0]]
//
@@ -83,11 +83,11 @@ struct T {
// CHECK-NEXT: [[T:%.*]] = alloca [[STRUCT_T:%.*]], align 4
// CHECK-NEXT: [[S_PTR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[T]], i8 0, i64 12, i1 false)
-// CHECK-NEXT: [[BUFFER:%.*]] = getelementptr inbounds [[STRUCT_T]], ptr [[T]], i32 0, i32 0
+// CHECK-NEXT: [[BUFFER:%.*]] = getelementptr inbounds nuw [[STRUCT_T]], ptr [[T]], i32 0, i32 0
// CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
// CHECK-NEXT: store ptr [[ARRAYDECAY]], ptr [[S_PTR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[S_PTR]], align 8
-// CHECK-NEXT: [[C:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[TMP0]], i32 0, i32 1
+// CHECK-NEXT: [[C:%.*]] = getelementptr inbounds nuw [[STRUCT_S:%.*]], ptr [[TMP0]], i32 0, i32 1
// CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[C]], align 4
// CHECK-NEXT: ret i8 [[TMP1]]
//
@@ -107,11 +107,11 @@ char quux() {
// CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
// CHECK-NEXT: store ptr [[ARRAYDECAY]], ptr [[T_PTR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[T_PTR]], align 8
-// CHECK-NEXT: [[BUFFER1:%.*]] = getelementptr inbounds [[STRUCT_T:%.*]], ptr [[TMP0]], i32 0, i32 0
+// CHECK-NEXT: [[BUFFER1:%.*]] = getelementptr inbounds nuw [[STRUCT_T:%.*]], ptr [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[ARRAYDECAY2:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER1]], i64 0, i64 0
// CHECK-NEXT: store ptr [[ARRAYDECAY2]], ptr [[S_PTR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[S_PTR]], align 8
-// CHECK-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[TMP1]], i32 0, i32 2
+// CHECK-NEXT: [[F:%.*]] = getelementptr inbounds nuw [[STRUCT_S:%.*]], ptr [[TMP1]], i32 0, i32 2
// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[F]], align 4
// CHECK-NEXT: ret float [[TMP2]]
//
@@ -128,16 +128,16 @@ float quibble() {
// CHECK-NEXT: [[BUFFER:%.*]] = alloca [12 x i8], align 4
// CHECK-NEXT: [[S_PTR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
-// CHECK-NEXT: [[BUFFER1:%.*]] = getelementptr inbounds [[STRUCT_T:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 0
+// CHECK-NEXT: [[BUFFER1:%.*]] = getelementptr inbounds nuw [[STRUCT_T:%.*]], ptr [[ARRAYDECAY]], i32 0, i32 0
// CHECK-NEXT: [[ARRAYDECAY2:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER1]], i64 0, i64 0
-// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], ptr [[ARRAYDECAY2]], i32 0, i32 0
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_S:%.*]], ptr [[ARRAYDECAY2]], i32 0, i32 0
// CHECK-NEXT: store i32 12, ptr [[X]], align 4
// CHECK-NEXT: [[ARRAYDECAY3:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER]], i64 0, i64 0
-// CHECK-NEXT: [[BUFFER4:%.*]] = getelementptr inbounds [[STRUCT_T]], ptr [[ARRAYDECAY3]], i32 0, i32 0
+// CHECK-NEXT: [[BUFFER4:%.*]] = getelementptr inbounds nuw [[STRUCT_T]], ptr [[ARRAYDECAY3]], i32 0, i32 0
// CHECK-NEXT: [[ARRAYDECAY5:%.*]] = getelementptr inbounds [12 x i8], ptr [[BUFFER4]], i64 0, i64 0
// CHECK-NEXT: store ptr [[ARRAYDECAY5]], ptr [[S_PTR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[S_PTR]], align 8
-// CHECK-NEXT: [[X6:%.*]] = getelementptr inbounds [[STRUCT_S]], ptr [[TMP0]], i32 0, i32 0
+// CHECK-NEXT: [[X6:%.*]] = getelementptr inbounds nuw [[STRUCT_S]], ptr [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[X6]], align 4
// CHECK-NEXT: ret i32 [[TMP1]]
//
diff --git a/clang/test/C/C2y/n3259.c b/clang/test/C/C2y/n3259.c
index 42c6720b2a665..2e94e3fc971df 100644
--- a/clang/test/C/C2y/n3259.c
+++ b/clang/test/C/C2y/n3259.c
@@ -12,52 +12,52 @@ void test() {
// CHECK: store float 0
_Complex float f = __builtin_complex(1.0f, 0.0f);
- // CHECK: %[[F_REALP1:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK: %[[F_REALP1:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
// CHECK-NEXT: %[[F_REAL:.+]] = load float, ptr %[[F_REALP1]]
- // CHECK-NEXT: %[[F_IMAGP2:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_IMAGP2:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: %[[F_IMAG:.+]] = load float, ptr %[[F_IMAGP2]]
// CHECK-NEXT: %[[INC:.+]] = fadd float %[[F_REAL]], 1.000000e+00
- // CHECK-NEXT: %[[F_REALP3:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
- // CHECK-NEXT: %[[F_IMAGP4:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_REALP3:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK-NEXT: %[[F_IMAGP4:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: store float %[[INC]], ptr %[[F_REALP3]]
// CHECK-NEXT: store float %[[F_IMAG]], ptr %[[F_IMAGP4]]
f++; /* expected-warning {{'++' on an object of complex type is a C2y extension}}
pre-c2y-warning {{'++' on an object of complex type is incompatible with C standards before C2y}}
*/
- // CHECK: %[[F_REALP5:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK: %[[F_REALP5:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
// CHECK-NEXT: %[[F_REAL6:.+]] = load float, ptr %[[F_REALP5]]
- // CHECK-NEXT: %[[F_IMAGP7:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_IMAGP7:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: %[[F_IMAG8:.+]] = load float, ptr %[[F_IMAGP7]]
// CHECK-NEXT: %[[INC9:.+]] = fadd float %[[F_REAL6]], 1.000000e+00
- // CHECK-NEXT: %[[F_REALP10:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
- // CHECK-NEXT: %[[F_IMAGP11:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_REALP10:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK-NEXT: %[[F_IMAGP11:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: store float %[[INC9]], ptr %[[F_REALP10]]
// CHECK-NEXT: store float %[[F_IMAG8]], ptr %[[F_IMAGP11]]
++f; /* expected-warning {{'++' on an object of complex type is a C2y extension}}
pre-c2y-warning {{'++' on an object of complex type is incompatible with C standards before C2y}}
*/
- // CHECK: %[[F_REALP12:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK: %[[F_REALP12:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
// CHECK-NEXT: %[[F_REAL13:.+]] = load float, ptr %[[F_REALP12]]
- // CHECK-NEXT: %[[F_IMAGP14:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_IMAGP14:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: %[[F_IMAG15:.+]] = load float, ptr %[[F_IMAGP14]]
// CHECK-NEXT: %[[DEC:.+]] = fadd float %[[F_REAL13]], -1.000000e+00
- // CHECK-NEXT: %[[F_REALP16:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
- // CHECK-NEXT: %[[F_IMAGP17:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_REALP16:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK-NEXT: %[[F_IMAGP17:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: store float %[[DEC]], ptr %[[F_REALP16]]
// CHECK-NEXT: store float %[[F_IMAG15]], ptr %[[F_IMAGP17]]
f--; /* expected-warning {{'--' on an object of complex type is a C2y extension}}
pre-c2y-warning {{'--' on an object of complex type is incompatible with C standards before C2y}}
*/
- // CHECK: %[[F_REALP18:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK: %[[F_REALP18:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
// CHECK-NEXT: %[[F_REAL19:.+]] = load float, ptr %[[F_REALP18]]
- // CHECK-NEXT: %[[F_IMAGP20:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_IMAGP20:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: %[[F_IMAG21:.+]] = load float, ptr %[[F_IMAGP20]]
// CHECK-NEXT: %[[DEC22:.+]] = fadd float %[[F_REAL19]], -1.000000e+00
- // CHECK-NEXT: %[[F_REALP23:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 0
- // CHECK-NEXT: %[[F_IMAGP24:.+]] = getelementptr inbounds { float, float }, ptr %[[F]], i32 0, i32 1
+ // CHECK-NEXT: %[[F_REALP23:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 0
+ // CHECK-NEXT: %[[F_IMAGP24:.+]] = getelementptr inbounds nuw { float, float }, ptr %[[F]], i32 0, i32 1
// CHECK-NEXT: store float %[[DEC22]], ptr %[[F_REALP23]]
// CHECK-NEXT: store float %[[F_IMAG21]], ptr %[[F_IMAGP24]]
--f; /* expected-warning {{'--' on an object of complex type is a C2y extension}}
diff --git a/clang/test/CodeGen/PowerPC/powerpc-c99complex.c b/clang/test/CodeGen/PowerPC/powerpc-c99complex.c
index 82b5ac0fdc06c..8911257741c33 100644
--- a/clang/test/CodeGen/PowerPC/powerpc-c99complex.c
+++ b/clang/test/CodeGen/PowerPC/powerpc-c99complex.c
@@ -10,8 +10,8 @@ _Complex float foo1(_Complex float x) {
// CHECK: ret { float, float }
// PPC32LNX-LABEL: define{{.*}} void @foo1(ptr dead_on_unwind noalias writable sret({ float, float }) align 4 %agg.result, ptr noundef byval({ float, float }) align 4 %x) #0 {
-// PPC32LNX: [[RETREAL:%.*]] = getelementptr inbounds { float, float }, ptr %agg.result, i32 0, i32 0
-// PPC32LNX-NEXT: [[RETIMAG:%.*]] = getelementptr inbounds { float, float }, ptr %agg.result, i32 0, i32 1
+// PPC32LNX: [[RETREAL:%.*]] = getelementptr inbounds nuw { float, float }, ptr %agg.result, i32 0, i32 0
+// PPC32LNX-NEXT: [[RETIMAG:%.*]] = getelementptr inbounds nuw { float, float }, ptr %agg.result, i32 0, i32 1
// PPC32LNX-NEXT: store float %{{.*}}, ptr [[RETREAL]], align 4
// PPC32LNX-NEXT: store float %{{.*}}, ptr [[RETIMAG]], align 4
}
@@ -22,8 +22,8 @@ _Complex double foo2(_Complex double x) {
// CHECK: ret { double, double }
// PPC32LNX-LABEL: define{{.*}} void @foo2(ptr dead_on_unwind noalias writable sret({ double, double }) align 8 %agg.result, ptr noundef byval({ double, double }) align 8 %x) #0 {
-// PPC32LNX: [[RETREAL:%.*]] = getelementptr inbounds { double, double }, ptr %agg.result, i32 0, i32 0
-// PPC32LNX-NEXT: [[RETIMAG:%.*]] = getelementptr inbounds { double, double }, ptr %agg.result, i32 0, i32 1
+// PPC32LNX: [[RETREAL:%.*]] = getelementptr inbounds nuw { double, double }, ptr %agg.result, i32 0, i32 0
+// PPC32LNX-NEXT: [[RETIMAG:%.*]] = getelementptr inbounds nuw { double, double }, ptr %agg.result, i32 0, i32 1
// PPC32LNX-NEXT: store double %{{.*}}, ptr [[RETREAL]], align 8
// PPC32LNX-NEXT: store double %{{.*}}, ptr [[RETIMAG]], align 8
}
@@ -37,8 +37,8 @@ _Complex long double foo3(_Complex long double x) {
// CHECK-LDBL128: ret { ppc_fp128, ppc_fp128 }
// PPC32LNX-LABEL: define{{.*}} void @foo3(ptr dead_on_unwind noalias writable sret({ ppc_fp128, ppc_fp128 }) align 16 %agg.result, ptr noundef byval({ ppc_fp128, ppc_fp128 }) align 16 %x) #0 {
-// PPC32LNX: [[RETREAL:%.*]] = getelementptr inbounds { ppc_fp128, ppc_fp128 }, ptr %agg.result, i32 0, i32 0
-// PPC32LNX-NEXT: [[RETIMAG:%.*]] = getelementptr inbounds { ppc_fp128, ppc_fp128 }, ptr %agg.result, i32 0, i32 1
+// PPC32LNX: [[RETREAL:%.*]] = getelementptr inbounds nuw { ppc_fp128, ppc_fp128 }, ptr %agg.result, i32 0, i32 0
+// PPC32LNX-NEXT: [[RETIMAG:%.*]] = getelementptr inbounds nuw { ppc_fp128, ppc_fp128 }, ptr %agg.result, i32 0, i32 1
// PPC32LNX-NEXT: store ppc_fp128 %{{.*}}, ptr [[RETREAL]], align 16
// PPC32LNX-NEXT: store ppc_fp128 %{{.*}}, ptr [[RETIMAG]], align 16
}
diff --git a/clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c b/clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
index 2f5459d1bb9c4..08d3d2a9cc3c3 100644
--- a/clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
+++ b/clang/test/CodeGen/PowerPC/ppc64le-varargs-f128.c
@@ -93,7 +93,7 @@ void long_double(int n, ...) {
// IEEE: %[[V0:[0-9a-zA-Z_.]+]] = getelementptr inbounds i8, ptr %[[ALIGN]], i64 16
// IEEE: store ptr %[[V0]], ptr %[[AP]], align 8
// IEEE: call void @llvm.memcpy.p0.p0.i64(ptr align 16 %[[TMP:[0-9a-zA-Z_.]+]], ptr align 16 %[[ALIGN]], i64 16, i1 false)
-// IEEE: %[[COERCE:[0-9a-zA-Z_.]+]] = getelementptr inbounds %struct.ldbl128_s, ptr %[[TMP]], i32 0, i32 0
+// IEEE: %[[COERCE:[0-9a-zA-Z_.]+]] = getelementptr inbounds nuw %struct.ldbl128_s, ptr %[[TMP]], i32 0, i32 0
// IEEE: %[[V4:[0-9a-zA-Z_.]+]] = load fp128, ptr %[[COERCE]], align 16
// IEEE: call void @foo_ls(fp128 inreg %[[V4]])
// IEEE: call void @llvm.va_end.p0(ptr %[[AP]])
diff --git a/clang/test/CodeGen/RISCV/bfloat-abi.c b/clang/test/CodeGen/RISCV/bfloat-abi.c
index f38646c8b12ff..f7c82adaa6d89 100644
--- a/clang/test/CodeGen/RISCV/bfloat-abi.c
+++ b/clang/test/CodeGen/RISCV/bfloat-abi.c
@@ -14,9 +14,9 @@ struct bfloat1 {
// CHECK-RV64-NEXT: [[COERCE_DIVE_COERCE:%.*]] = alloca i64, align 8
// CHECK-RV64-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-RV64-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
-// CHECK-RV64-NEXT: [[A1:%.*]] = getelementptr inbounds [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
+// CHECK-RV64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-RV64-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
-// CHECK-RV64-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
+// CHECK-RV64-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-RV64-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[COERCE_DIVE_COERCE]], ptr align 2 [[COERCE_DIVE]], i64 2, i1 false)
// CHECK-RV64-NEXT: [[TMP1:%.*]] = load i64, ptr [[COERCE_DIVE_COERCE]], align 8
// CHECK-RV64-NEXT: ret i64 [[TMP1]]
@@ -29,9 +29,9 @@ struct bfloat1 {
// CHECK-RV32-NEXT: [[COERCE_DIVE_COERCE:%.*]] = alloca i32, align 4
// CHECK-RV32-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-RV32-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
-// CHECK-RV32-NEXT: [[A1:%.*]] = getelementptr inbounds [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
+// CHECK-RV32-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-RV32-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
-// CHECK-RV32-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
+// CHECK-RV32-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT1]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-RV32-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[COERCE_DIVE_COERCE]], ptr align 2 [[COERCE_DIVE]], i32 2, i1 false)
// CHECK-RV32-NEXT: [[TMP1:%.*]] = load i32, ptr [[COERCE_DIVE_COERCE]], align 4
// CHECK-RV32-NEXT: ret i32 [[TMP1]]
@@ -57,10 +57,10 @@ struct bfloat2 {
// CHECK-RV64-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-RV64-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-RV64-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
-// CHECK-RV64-NEXT: [[A1:%.*]] = getelementptr inbounds [[STRUCT_BFLOAT2]], ptr [[RETVAL]], i32 0, i32 0
+// CHECK-RV64-NEXT: [[A1:%.*]] = getelementptr inbounds nuw [[STRUCT_BFLOAT2]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-RV64-NEXT: store bfloat [[TMP0]], ptr [[A1]], align 2
// CHECK-RV64-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
-// CHECK-RV64-NEXT: [[B2:%.*]] = getelementptr inbounds [[STRUCT_BFLOAT2]], ptr [[RETVAL]], i32 0, i32 1
+// CHECK-RV64-NEXT: [[B2...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/99538
More information about the cfe-commits
mailing list