Index: llvm/test/Transforms/AggressiveInstCombine/patterned-load.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/AggressiveInstCombine/patterned-load.ll @@ -0,0 +1,163 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -passes=aggressive-instcombine -S -data-layout="e" | FileCheck %s --check-prefixes=CHECK,LE +; RUN: opt < %s -passes=aggressive-instcombine -S -data-layout="E" | FileCheck %s --check-prefixes=CHECK,BE + + +@constarray1 = internal constant [8 x i8] c"\01\00\01\00\01\00\01\00", align 4 +@constarray2 = internal constant [8 x i8] c"\FF\FF\01\00\01\00\01\00", align 4 + +@g = internal constant i32 42 +@constptrarray = internal constant [4 x ptr] [ptr @g, ptr @g, ptr @g, ptr @g], align 4 + +@constpackedstruct = internal constant <{[8 x i8]}> <{[8 x i8] c"\01\00\01\00\01\00\01\00"}>, align 4 +@conststruct = internal constant {i16, [8 x i8]} {i16 1, [8 x i8] c"\01\00\01\00\01\00\01\00"}, align 4 + +define i8 @gep_load_i8_align2(i64 %idx){ +; CHECK-LABEL: @gep_load_i8_align2( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constarray1, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[TMP1]], align 2 +; CHECK-NEXT: ret i8 [[TMP2]] +; + %1 = getelementptr inbounds i8, ptr @constarray1, i64 %idx + %2 = load i8, ptr %1, align 2 + ret i8 %2 +} + +; can't be folded because access with i8 strides is not patterned. +define i8 @gep_load_i8_align1(i64 %idx){ +; CHECK-LABEL: @gep_load_i8_align1( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constarray1, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[TMP1]], align 1 +; CHECK-NEXT: ret i8 [[TMP2]] +; + %1 = getelementptr inbounds i8, ptr @constarray1, i64 %idx + %2 = load i8, ptr %1, align 1 + ret i8 %2 +} + +; can't be folded because volatile load cannot assure same results. +define i8 @gep_load_i8_align2_volatile(i64 %idx){ +; CHECK-LABEL: @gep_load_i8_align2_volatile( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constarray1, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load volatile i8, ptr [[TMP1]], align 2 +; CHECK-NEXT: ret i8 [[TMP2]] +; + %1 = getelementptr inbounds i8, ptr @constarray1, i64 %idx + %2 = load volatile i8, ptr %1, align 2 + ret i8 %2 +} + +declare ptr @llvm.ptrmask.p0.i64(ptr , i64) + +; can't be folded because ptrmask can change ptr, while preserving provenance +define i8 @gep_load_i8_align2_ptrmasked(i64 %idx, i64 %mask){ +; CHECK-LABEL: @gep_load_i8_align2_ptrmasked( +; CHECK-NEXT: [[TMP1:%.*]] = call ptr @llvm.ptrmask.p0.i64(ptr @constarray1, i64 [[MASK:%.*]]) +; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr [[TMP2]], align 2 +; CHECK-NEXT: ret i8 [[TMP3]] +; + %1 = call ptr @llvm.ptrmask.p0.i64(ptr @constarray1, i64 %mask) + %2 = getelementptr inbounds i8, ptr %1, i64 %idx + %3 = load i8, ptr %2, align 2 + ret i8 %3 +} + +; can't be folded because gep is not inbounds +define i8 @gep_load_i8_align2_not_inbounds(i64 %idx, i64 %mask){ +; CHECK-LABEL: @gep_load_i8_align2_not_inbounds( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, ptr @constarray1, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[TMP1]], align 2 +; CHECK-NEXT: ret i8 [[TMP2]] +; + %1 = getelementptr i8, ptr @constarray1, i64 %idx + %2 = load i8, ptr %1, align 2 + ret i8 %2 +} + +define i32 @gep_i16_load_i32_align1(i64 %idx){ +; CHECK-LABEL: @gep_i16_load_i32_align1( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i16, ptr @constarray1, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 1 +; CHECK-NEXT: ret i32 [[TMP2]] +; + %1 = getelementptr inbounds i16, ptr @constarray1, i64 %idx + %2 = load i32, ptr %1, align 1 + ret i32 %2 +} + +define i32 @gep_i32_load_i32_align8(i64 %idx){ +; CHECK-LABEL: @gep_i32_load_i32_align8( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr @constarray1, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 8 +; CHECK-NEXT: ret i32 [[TMP2]] +; + %1 = getelementptr inbounds i32, ptr @constarray1, i64 %idx + %2 = load i32, ptr %1, align 8 + ret i32 %2 +} + +define i32 @gep_i32_load_i32_with_const_offset(i64 %idx){ +; CHECK-LABEL: @gep_i32_load_i32_with_const_offset( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i16, ptr @constarray2, i64 1 +; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[TMP2]], align 4 +; CHECK-NEXT: ret i32 [[TMP3]] +; + %1 = getelementptr inbounds i16, ptr @constarray2, i64 1 + %2 = getelementptr inbounds i32, ptr %1, i64 %idx + %3 = load i32, ptr %2, align 4 + ret i32 %3 +} + +define i32 @gep_i32_load_i32_const_ptr_array(i64 %idx){ +; CHECK-LABEL: @gep_i32_load_i32_const_ptr_array( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds ptr, ptr @constptrarray, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TMP1]], align 4 +; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[TMP2]], align 4 +; CHECK-NEXT: ret i32 [[TMP3]] +; + %1 = getelementptr inbounds ptr, ptr @constptrarray, i64 %idx + %2 = load ptr, ptr %1, align 4 + %3 = load i32, ptr %2, align 4 + ret i32 %3 +} + +define i32 @gep_i32_load_i32_align4_packedstruct(i64 %idx){ +; CHECK-LABEL: @gep_i32_load_i32_align4_packedstruct( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr @constpackedstruct, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4 +; CHECK-NEXT: ret i32 [[TMP2]] +; + %1 = getelementptr inbounds i32, ptr @constpackedstruct, i64 %idx + %2 = load i32, ptr %1, align 4 + ret i32 %2 +} + +; can't be folded +define i32 @gep_i8_load_i32_align1_packedstruct(i64 %idx){ +; CHECK-LABEL: @gep_i8_load_i32_align1_packedstruct( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constpackedstruct, i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 1 +; CHECK-NEXT: ret i32 [[TMP2]] +; + %1 = getelementptr inbounds i8, ptr @constpackedstruct, i64 %idx + %2 = load i32, ptr %1, align 1 + ret i32 %2 +} + +define i32 @gep_i32_load_i32_align4_struct_with_const_offset(i64 %idx){ +; CHECK-LABEL: @gep_i32_load_i32_align4_struct_with_const_offset( +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i16, ptr @conststruct, i64 1 +; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 [[IDX:%.*]] +; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[TMP2]], align 4 +; CHECK-NEXT: ret i32 [[TMP3]] +; + %1 = getelementptr inbounds i16, ptr @conststruct, i64 1 + %2 = getelementptr inbounds i32, ptr %1, i64 %idx + %3 = load i32, ptr %2, align 4 + ret i32 %3 +} +;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line: +; BE: {{.*}} +; LE: {{.*}} Index: llvm/test/Transforms/InstSimplify/load-patterned-aggregates.ll =================================================================== --- llvm/test/Transforms/InstSimplify/load-patterned-aggregates.ll +++ /dev/null @@ -1,134 +0,0 @@ -; NOTE: Assertions have been autogenerated by utils/update_test_checks.py -; RUN: opt < %s -passes=instsimplify -S | FileCheck %s -target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32" -@constzeroarray = internal constant [4 x i32] zeroinitializer - -@constarray = internal constant [8 x i8] c"\01\00\01\00\01\00\01\00", align 4 -@conststruct = internal constant <{[8 x i8]}> <{[8 x i8] c"\01\00\01\00\01\00\01\00"}>, align 4 - -define i32 @load_gep_const_zero_array(i64 %idx) { -; CHECK-LABEL: @load_gep_const_zero_array( -; CHECK-NEXT: ret i32 0 -; - %gep = getelementptr inbounds [4 x i32], ptr @constzeroarray, i64 0, i64 %idx - %load = load i32, ptr %gep - ret i32 %load -} - -define i8 @load_i8_multi_gep_const_zero_array(i64 %idx1, i64 %idx2) { -; CHECK-LABEL: @load_i8_multi_gep_const_zero_array( -; CHECK-NEXT: ret i8 0 -; - %gep1 = getelementptr inbounds i8, ptr @constzeroarray, i64 %idx1 - %gep = getelementptr inbounds i8, ptr %gep1, i64 %idx2 - %load = load i8, ptr %gep - ret i8 %load -} - - -define i32 @load_gep_const_patterned_array(i64 %idx) { -; CHECK-LABEL: @load_gep_const_patterned_array( -; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds [4 x i32], ptr @constarray, i64 0, i64 [[IDX:%.*]] -; CHECK-NEXT: [[LOAD:%.*]] = load i32, ptr [[GEP]], align 4 -; CHECK-NEXT: ret i32 [[LOAD]] -; - %gep = getelementptr inbounds [4 x i32], ptr @constarray, i64 0, i64 %idx - %load = load i32, ptr %gep - ret i32 %load -} - -define i8 @load_i8_multi_gep_const_array(i64 %idx1, i64 %idx2) { -; CHECK-LABEL: @load_i8_multi_gep_const_array( -; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, ptr @constarray, i64 [[IDX1:%.*]] -; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[GEP1]], i64 [[IDX2:%.*]] -; CHECK-NEXT: [[LOAD:%.*]] = load i8, ptr [[GEP]], align 1 -; CHECK-NEXT: ret i8 [[LOAD]] -; - %gep1 = getelementptr inbounds i8, ptr @constarray, i64 %idx1 - %gep = getelementptr inbounds i8, ptr %gep1, i64 %idx2 - %load = load i8, ptr %gep - ret i8 %load -} - -; TODO: this should be ret i8 1 -define i8 @gep_load_i8_align2(i64 %idx){ -; CHECK-LABEL: @gep_load_i8_align2( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constarray, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[TMP1]], align 2 -; CHECK-NEXT: ret i8 [[TMP2]] -; - %1 = getelementptr inbounds i8, ptr @constarray, i64 %idx - %2 = load i8, ptr %1, align 2 - ret i8 %2 -} - -; can't be folded -define i8 @gep_load_i8_align1(i64 %idx){ -; CHECK-LABEL: @gep_load_i8_align1( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constarray, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[TMP1]], align 1 -; CHECK-NEXT: ret i8 [[TMP2]] -; - %1 = getelementptr inbounds i8, ptr @constarray, i64 %idx - %2 = load i8, ptr %1, align 1 - ret i8 %2 -} - -; TODO: this should be ret i8 65537 on the case for little endian -define i32 @gep_i32_load_i32_align4(i64 %idx){ -; CHECK-LABEL: @gep_i32_load_i32_align4( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr @constarray, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4 -; CHECK-NEXT: ret i32 [[TMP2]] -; - %1 = getelementptr inbounds i32, ptr @constarray, i64 %idx - %2 = load i32, ptr %1, align 4 - ret i32 %2 -} - -; TODO: this should be ret i8 65537 on the case for little endian -define i32 @gep_i32_load_i32_align4_struct(i64 %idx){ -; CHECK-LABEL: @gep_i32_load_i32_align4_struct( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr @conststruct, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4 -; CHECK-NEXT: ret i32 [[TMP2]] -; - %1 = getelementptr inbounds i32, ptr @conststruct, i64 %idx - %2 = load i32, ptr %1, align 4 - ret i32 %2 -} - -; can't be folded -define i32 @gep_i8_load_i32_align1(i64 %idx){ -; CHECK-LABEL: @gep_i8_load_i32_align1( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @constarray, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 1 -; CHECK-NEXT: ret i32 [[TMP2]] -; - %1 = getelementptr inbounds i8, ptr @constarray, i64 %idx - %2 = load i32, ptr %1, align 1 - ret i32 %2 -} - -; can't be folded -define i32 @gep_i8_load_i32_align1_struct(i64 %idx){ -; CHECK-LABEL: @gep_i8_load_i32_align1_struct( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr @conststruct, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 1 -; CHECK-NEXT: ret i32 [[TMP2]] -; - %1 = getelementptr inbounds i8, ptr @conststruct, i64 %idx - %2 = load i32, ptr %1, align 1 - ret i32 %2 -} -; TODO: This could be folded but need to see GEP source types -define i32 @gep_i16_load_i32_align1(i64 %idx){ -; CHECK-LABEL: @gep_i16_load_i32_align1( -; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i16, ptr @constarray, i64 [[IDX:%.*]] -; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 1 -; CHECK-NEXT: ret i32 [[TMP2]] -; - %1 = getelementptr inbounds i16, ptr @constarray, i64 %idx - %2 = load i32, ptr %1, align 1 - ret i32 %2 -} Index: llvm/test/Transforms/InstSimplify/load.ll =================================================================== --- llvm/test/Transforms/InstSimplify/load.ll +++ llvm/test/Transforms/InstSimplify/load.ll @@ -3,6 +3,7 @@ @zeroinit = constant {} zeroinitializer @poison = constant {} poison +@constzeroarray = internal constant [4 x i32] zeroinitializer define i32 @crash_on_zeroinit() { ; CHECK-LABEL: @crash_on_zeroinit( @@ -40,3 +41,22 @@ %1 = load <3 x float>, ptr getelementptr inbounds (<3 x float>, ptr @constvec, i64 1) ret <3 x float> %1 } + +define i32 @load_gep_const_zero_array(i64 %idx) { +; CHECK-LABEL: @load_gep_const_zero_array( +; CHECK-NEXT: ret i32 0 +; + %gep = getelementptr inbounds [4 x i32], ptr @constzeroarray, i64 0, i64 %idx + %load = load i32, ptr %gep + ret i32 %load +} + +define i8 @load_i8_multi_gep_const_zero_array(i64 %idx1, i64 %idx2) { +; CHECK-LABEL: @load_i8_multi_gep_const_zero_array( +; CHECK-NEXT: ret i8 0 +; + %gep1 = getelementptr inbounds i8, ptr @constzeroarray, i64 %idx1 + %gep = getelementptr inbounds i8, ptr %gep1, i64 %idx2 + %load = load i8, ptr %gep + ret i8 %load +}