From 39cc0b8c68b8d316954ecfac0d1f8498ea42866c Mon Sep 17 00:00:00 2001 From: Florian Hahn Date: Fri, 13 Aug 2021 11:23:58 +0100 Subject: [PATCH] [PhaseOrdering] Add test for missed vectorization with vector::at calls. This test illustrates missed vectorization of loops with multiple std::vector::at calls, like int sum(std::vector *A, std::vector *B, int N) { int cost = 0; for (int i = 0; i < N; ++i) cost += A->at(i) + B->at(i); return cost; } https://clang.godbolt.org/z/KbYoaPhvq --- ...multiple-unreachable-exits-for-vectorization.ll | 196 +++++++++++++++++++++ 1 file changed, 196 insertions(+) create mode 100644 llvm/test/Transforms/PhaseOrdering/AArch64/peel-multiple-unreachable-exits-for-vectorization.ll diff --git a/llvm/test/Transforms/PhaseOrdering/AArch64/peel-multiple-unreachable-exits-for-vectorization.ll b/llvm/test/Transforms/PhaseOrdering/AArch64/peel-multiple-unreachable-exits-for-vectorization.ll new file mode 100644 index 0000000..c24affb --- /dev/null +++ b/llvm/test/Transforms/PhaseOrdering/AArch64/peel-multiple-unreachable-exits-for-vectorization.ll @@ -0,0 +1,196 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt -O2 -mtriple=arm64-apple-ios -S %s | FileCheck %s + +%vec = type { i64*, i64* } + +; Test to ensure a loop with multiple loads guarded by runtime-checks (like +; from multiple calls to C++'s std::vector::at) can be vectorized after +; hoisting the runtime checks out of the loop. + +define i64 @sum_2_at_with_int_conversion(%vec* %A, %vec* %B, i64 %N) { +; CHECK-LABEL: @sum_2_at_with_int_conversion( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[GEP_START_I:%.*]] = getelementptr [[VEC:%.*]], %vec* [[A:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[START_I:%.*]] = load i64*, i64** [[GEP_START_I]], align 8 +; CHECK-NEXT: [[GEP_END_I:%.*]] = getelementptr [[VEC]], %vec* [[A]], i64 0, i32 1 +; CHECK-NEXT: [[END_I:%.*]] = load i64*, i64** [[GEP_END_I]], align 8 +; CHECK-NEXT: [[START_INT_I:%.*]] = ptrtoint i64* [[START_I]] to i64 +; CHECK-NEXT: [[END_INT_I:%.*]] = ptrtoint i64* [[END_I]] to i64 +; CHECK-NEXT: [[SUB_I:%.*]] = sub i64 [[END_INT_I]], [[START_INT_I]] +; CHECK-NEXT: [[GEP_START_I1:%.*]] = getelementptr [[VEC]], %vec* [[B:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[GEP_END_I3:%.*]] = getelementptr [[VEC]], %vec* [[B]], i64 0, i32 1 +; CHECK-NEXT: br label [[LOOP:%.*]] +; CHECK: loop: +; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT12:%.*]] ] +; CHECK-NEXT: [[SUM:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT12]] ] +; CHECK-NEXT: [[INRANGE_I:%.*]] = icmp ult i64 [[SUB_I]], [[IV]] +; CHECK-NEXT: br i1 [[INRANGE_I]], label [[ERROR_I:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT:%.*]] +; CHECK: error.i: +; CHECK-NEXT: tail call void @error() +; CHECK-NEXT: unreachable +; CHECK: at_with_int_conversion.exit: +; CHECK-NEXT: [[START_I2:%.*]] = load i64*, i64** [[GEP_START_I1]], align 8 +; CHECK-NEXT: [[END_I4:%.*]] = load i64*, i64** [[GEP_END_I3]], align 8 +; CHECK-NEXT: [[START_INT_I5:%.*]] = ptrtoint i64* [[START_I2]] to i64 +; CHECK-NEXT: [[END_INT_I6:%.*]] = ptrtoint i64* [[END_I4]] to i64 +; CHECK-NEXT: [[SUB_I7:%.*]] = sub i64 [[END_INT_I6]], [[START_INT_I5]] +; CHECK-NEXT: [[INRANGE_I8:%.*]] = icmp ult i64 [[SUB_I7]], [[IV]] +; CHECK-NEXT: br i1 [[INRANGE_I8]], label [[ERROR_I11:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT12]] +; CHECK: error.i11: +; CHECK-NEXT: tail call void @error() +; CHECK-NEXT: unreachable +; CHECK: at_with_int_conversion.exit12: +; CHECK-NEXT: [[GEP_IDX_I:%.*]] = getelementptr i64, i64* [[START_I]], i64 [[IV]] +; CHECK-NEXT: [[LV_I:%.*]] = load i64, i64* [[GEP_IDX_I]], align 4 +; CHECK-NEXT: [[GEP_IDX_I9:%.*]] = getelementptr i64, i64* [[START_I2]], i64 [[IV]] +; CHECK-NEXT: [[LV_I10:%.*]] = load i64, i64* [[GEP_IDX_I9]], align 4 +; CHECK-NEXT: [[ADD:%.*]] = add i64 [[LV_I]], [[SUM]] +; CHECK-NEXT: [[SUM_NEXT]] = add i64 [[ADD]], [[LV_I10]] +; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1 +; CHECK-NEXT: [[C:%.*]] = icmp slt i64 [[IV]], [[N:%.*]] +; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]] +; CHECK: exit: +; CHECK-NEXT: ret i64 [[SUM_NEXT]] +; +entry: + br label %loop + +loop: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ] + %sum = phi i64 [ 0, %entry ], [ %sum.next, %loop ] + %a = call i64 @at_with_int_conversion(%vec* %A, i64 %iv) + %b = call i64 @at_with_int_conversion(%vec* %B, i64 %iv) + %add = add i64 %a, %b + %sum.next = add i64 %sum, %add + %iv.next = add nuw nsw i64 %iv, 1 + %c = icmp slt i64 %iv, %N + br i1 %c, label %loop, label %exit + +exit: + ret i64 %sum.next +} + +define i64 @sum_3_at_with_int_conversion(%vec* %A, %vec* %B, %vec* %C, i64 %N) { +; CHECK-LABEL: @sum_3_at_with_int_conversion( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[GEP_START_I:%.*]] = getelementptr [[VEC:%.*]], %vec* [[A:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[START_I:%.*]] = load i64*, i64** [[GEP_START_I]], align 8 +; CHECK-NEXT: [[GEP_END_I:%.*]] = getelementptr [[VEC]], %vec* [[A]], i64 0, i32 1 +; CHECK-NEXT: [[END_I:%.*]] = load i64*, i64** [[GEP_END_I]], align 8 +; CHECK-NEXT: [[START_INT_I:%.*]] = ptrtoint i64* [[START_I]] to i64 +; CHECK-NEXT: [[END_INT_I:%.*]] = ptrtoint i64* [[END_I]] to i64 +; CHECK-NEXT: [[SUB_I:%.*]] = sub i64 [[END_INT_I]], [[START_INT_I]] +; CHECK-NEXT: [[GEP_START_I1:%.*]] = getelementptr [[VEC]], %vec* [[B:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[GEP_END_I3:%.*]] = getelementptr [[VEC]], %vec* [[B]], i64 0, i32 1 +; CHECK-NEXT: [[GEP_START_I13:%.*]] = getelementptr [[VEC]], %vec* [[C:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[GEP_END_I15:%.*]] = getelementptr [[VEC]], %vec* [[C]], i64 0, i32 1 +; CHECK-NEXT: br label [[LOOP:%.*]] +; CHECK: loop: +; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT24:%.*]] ] +; CHECK-NEXT: [[SUM:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT24]] ] +; CHECK-NEXT: [[INRANGE_I:%.*]] = icmp ult i64 [[SUB_I]], [[IV]] +; CHECK-NEXT: br i1 [[INRANGE_I]], label [[ERROR_I:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT:%.*]] +; CHECK: error.i: +; CHECK-NEXT: tail call void @error() +; CHECK-NEXT: unreachable +; CHECK: at_with_int_conversion.exit: +; CHECK-NEXT: [[GEP_IDX_I:%.*]] = getelementptr i64, i64* [[START_I]], i64 [[IV]] +; CHECK-NEXT: [[LV_I:%.*]] = load i64, i64* [[GEP_IDX_I]], align 4 +; CHECK-NEXT: [[START_I2:%.*]] = load i64*, i64** [[GEP_START_I1]], align 8 +; CHECK-NEXT: [[END_I4:%.*]] = load i64*, i64** [[GEP_END_I3]], align 8 +; CHECK-NEXT: [[START_INT_I5:%.*]] = ptrtoint i64* [[START_I2]] to i64 +; CHECK-NEXT: [[END_INT_I6:%.*]] = ptrtoint i64* [[END_I4]] to i64 +; CHECK-NEXT: [[SUB_I7:%.*]] = sub i64 [[END_INT_I6]], [[START_INT_I5]] +; CHECK-NEXT: [[INRANGE_I8:%.*]] = icmp ult i64 [[SUB_I7]], [[IV]] +; CHECK-NEXT: br i1 [[INRANGE_I8]], label [[ERROR_I11:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT12:%.*]] +; CHECK: error.i11: +; CHECK-NEXT: tail call void @error() +; CHECK-NEXT: unreachable +; CHECK: at_with_int_conversion.exit12: +; CHECK-NEXT: [[START_I14:%.*]] = load i64*, i64** [[GEP_START_I13]], align 8 +; CHECK-NEXT: [[END_I16:%.*]] = load i64*, i64** [[GEP_END_I15]], align 8 +; CHECK-NEXT: [[START_INT_I17:%.*]] = ptrtoint i64* [[START_I14]] to i64 +; CHECK-NEXT: [[END_INT_I18:%.*]] = ptrtoint i64* [[END_I16]] to i64 +; CHECK-NEXT: [[SUB_I19:%.*]] = sub i64 [[END_INT_I18]], [[START_INT_I17]] +; CHECK-NEXT: [[INRANGE_I20:%.*]] = icmp ult i64 [[SUB_I19]], [[IV]] +; CHECK-NEXT: br i1 [[INRANGE_I20]], label [[ERROR_I23:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT24]] +; CHECK: error.i23: +; CHECK-NEXT: tail call void @error() +; CHECK-NEXT: unreachable +; CHECK: at_with_int_conversion.exit24: +; CHECK-NEXT: [[GEP_IDX_I9:%.*]] = getelementptr i64, i64* [[START_I2]], i64 [[IV]] +; CHECK-NEXT: [[LV_I10:%.*]] = load i64, i64* [[GEP_IDX_I9]], align 4 +; CHECK-NEXT: [[GEP_IDX_I21:%.*]] = getelementptr i64, i64* [[START_I14]], i64 [[IV]] +; CHECK-NEXT: [[LV_I22:%.*]] = load i64, i64* [[GEP_IDX_I21]], align 4 +; CHECK-NEXT: [[ADD_1:%.*]] = add i64 [[LV_I]], [[SUM]] +; CHECK-NEXT: [[ADD_2:%.*]] = add i64 [[ADD_1]], [[LV_I10]] +; CHECK-NEXT: [[SUM_NEXT]] = add i64 [[ADD_2]], [[LV_I22]] +; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1 +; CHECK-NEXT: [[COND:%.*]] = icmp slt i64 [[IV]], [[N:%.*]] +; CHECK-NEXT: br i1 [[COND]], label [[LOOP]], label [[EXIT:%.*]] +; CHECK: exit: +; CHECK-NEXT: ret i64 [[SUM_NEXT]] +; +entry: + br label %loop + +loop: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ] + %sum = phi i64 [ 0, %entry ], [ %sum.next, %loop ] + %a = call i64 @at_with_int_conversion(%vec* %A, i64 %iv) + %b = call i64 @at_with_int_conversion(%vec* %B, i64 %iv) + %c = call i64 @at_with_int_conversion(%vec* %C, i64 %iv) + %add.1 = add i64 %a, %b + %add.2 = add i64 %add.1, %c + %sum.next = add i64 %sum, %add.2 + %iv.next = add nuw nsw i64 %iv, 1 + %cond = icmp slt i64 %iv, %N + br i1 %cond, label %loop, label %exit + +exit: + ret i64 %sum.next +} + + +define i64 @at_with_int_conversion(%vec* %ptr, i64 %idx) { +; CHECK-LABEL: @at_with_int_conversion( +; CHECK-NEXT: [[GEP_START:%.*]] = getelementptr [[VEC:%.*]], %vec* [[PTR:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[START:%.*]] = load i64*, i64** [[GEP_START]], align 8 +; CHECK-NEXT: [[GEP_END:%.*]] = getelementptr [[VEC]], %vec* [[PTR]], i64 0, i32 1 +; CHECK-NEXT: [[END:%.*]] = load i64*, i64** [[GEP_END]], align 8 +; CHECK-NEXT: [[START_INT:%.*]] = ptrtoint i64* [[START]] to i64 +; CHECK-NEXT: [[END_INT:%.*]] = ptrtoint i64* [[END]] to i64 +; CHECK-NEXT: [[SUB:%.*]] = sub i64 [[END_INT]], [[START_INT]] +; CHECK-NEXT: [[INRANGE:%.*]] = icmp ult i64 [[SUB]], [[IDX:%.*]] +; CHECK-NEXT: br i1 [[INRANGE]], label [[ERROR:%.*]], label [[EXIT:%.*]] +; CHECK: exit: +; CHECK-NEXT: [[GEP_IDX:%.*]] = getelementptr i64, i64* [[START]], i64 [[IDX]] +; CHECK-NEXT: [[LV:%.*]] = load i64, i64* [[GEP_IDX]], align 4 +; CHECK-NEXT: ret i64 [[LV]] +; CHECK: error: +; CHECK-NEXT: tail call void @error() +; CHECK-NEXT: unreachable +; + %gep.start = getelementptr %vec, %vec* %ptr, i64 0, i32 0 + %start = load i64*, i64** %gep.start + %gep.end = getelementptr %vec, %vec* %ptr, i64 0, i32 1 + %end = load i64*, i64** %gep.end + %start.int = ptrtoint i64* %start to i64 + %end.int = ptrtoint i64* %end to i64 + %sub = sub i64 %end.int, %start.int + %inrange = icmp ugt i64 %idx, %sub + br i1 %inrange, label %error, label %exit + +exit: + %gep.idx = getelementptr i64, i64* %start, i64 %idx + %lv = load i64, i64* %gep.idx + ret i64 %lv + +error: + call void @error() + unreachable +} + +declare void @error() + + -- 2.7.4