OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Transforms/PhaseOrdering/AArch64/peel-multiple-unreachable-e...

315 lines
19 KiB
LLVM
Raw Blame History

; 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: at_with_int_conversion.exit12.peel:
; 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_END_I3:%.*]] = getelementptr [[VEC]], %vec* [[B:%.*]], i64 0, i32 1
; CHECK-NEXT: [[GEP_START_I1:%.*]] = getelementptr [[VEC]], %vec* [[B]], i64 0, i32 0
; CHECK-NEXT: [[START_I2_PEEL:%.*]] = load i64*, i64** [[GEP_START_I1]], align 8
; CHECK-NEXT: [[END_I4_PEEL:%.*]] = load i64*, i64** [[GEP_END_I3]], align 8
; CHECK-NEXT: [[START_INT_I5_PEEL:%.*]] = ptrtoint i64* [[START_I2_PEEL]] to i64
; CHECK-NEXT: [[END_INT_I6_PEEL:%.*]] = ptrtoint i64* [[END_I4_PEEL]] to i64
; CHECK-NEXT: [[SUB_I7_PEEL:%.*]] = sub i64 [[END_INT_I6_PEEL]], [[START_INT_I5_PEEL]]
; CHECK-NEXT: [[LV_I_PEEL:%.*]] = load i64, i64* [[START_I]], align 4
; CHECK-NEXT: [[LV_I10_PEEL:%.*]] = load i64, i64* [[START_I2_PEEL]], align 4
; CHECK-NEXT: [[SUM_NEXT_PEEL:%.*]] = add i64 [[LV_I_PEEL]], [[LV_I10_PEEL]]
; CHECK-NEXT: [[C_PEEL:%.*]] = icmp sgt i64 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[C_PEEL]], label [[LOOP_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK: loop.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N]], -1
; CHECK-NEXT: [[UMIN:%.*]] = tail call i64 @llvm.umin.i64(i64 [[SUB_I7_PEEL]], i64 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = freeze i64 [[UMIN]]
; CHECK-NEXT: [[UMIN16:%.*]] = tail call i64 @llvm.umin.i64(i64 [[TMP1]], i64 [[SUB_I]])
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[UMIN16]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 5
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[LOOP_PREHEADER21:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = and i64 [[TMP2]], 3
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i64 4, i64 [[N_MOD_VF]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[IND_END:%.*]] = add i64 [[N_VEC]], 1
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i64> <i64 poison, i64 0>, i64 [[SUM_NEXT_PEEL]], i64 0
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x i64> [ [[TMP5]], [[VECTOR_PH]] ], [ [[TMP16:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI17:%.*]] = phi <2 x i64> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP17:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i64, i64* [[START_I]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i64* [[TMP6]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x i64>, <2 x i64>* [[TMP7]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i64, i64* [[TMP6]], i64 2
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i64* [[TMP8]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD18:%.*]] = load <2 x i64>, <2 x i64>* [[TMP9]], align 4
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr i64, i64* [[START_I2_PEEL]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP11:%.*]] = bitcast i64* [[TMP10]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD19:%.*]] = load <2 x i64>, <2 x i64>* [[TMP11]], align 4
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i64, i64* [[TMP10]], i64 2
; CHECK-NEXT: [[TMP13:%.*]] = bitcast i64* [[TMP12]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD20:%.*]] = load <2 x i64>, <2 x i64>* [[TMP13]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = add <2 x i64> [[WIDE_LOAD]], [[VEC_PHI]]
; CHECK-NEXT: [[TMP15:%.*]] = add <2 x i64> [[WIDE_LOAD18]], [[VEC_PHI17]]
; CHECK-NEXT: [[TMP16]] = add <2 x i64> [[TMP14]], [[WIDE_LOAD19]]
; CHECK-NEXT: [[TMP17]] = add <2 x i64> [[TMP15]], [[WIDE_LOAD20]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <2 x i64> [[TMP17]], [[TMP16]]
; CHECK-NEXT: [[TMP19:%.*]] = tail call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[BIN_RDX]])
; CHECK-NEXT: br label [[LOOP_PREHEADER21]]
; CHECK: loop.preheader21:
; CHECK-NEXT: [[IV_PH:%.*]] = phi i64 [ 1, [[LOOP_PREHEADER]] ], [ [[IND_END]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: [[SUM_PH:%.*]] = phi i64 [ [[SUM_NEXT_PEEL]], [[LOOP_PREHEADER]] ], [ [[TMP19]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT12:%.*]] ], [ [[IV_PH]], [[LOOP_PREHEADER21]] ]
; CHECK-NEXT: [[SUM:%.*]] = phi i64 [ [[SUM_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT12]] ], [ [[SUM_PH]], [[LOOP_PREHEADER21]] ]
; 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: [[INRANGE_I8:%.*]] = icmp ult i64 [[SUB_I7_PEEL]], [[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_PEEL]], 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]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: [[SUM_NEXT_LCSSA:%.*]] = phi i64 [ [[SUM_NEXT_PEEL]], [[AT_WITH_INT_CONVERSION_EXIT12_PEEL:%.*]] ], [ [[SUM_NEXT]], [[AT_WITH_INT_CONVERSION_EXIT12]] ]
; CHECK-NEXT: ret i64 [[SUM_NEXT_LCSSA]]
;
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: at_with_int_conversion.exit24.peel:
; 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_I13:%.*]] = getelementptr [[VEC]], %vec* [[C:%.*]], i64 0, i32 0
; CHECK-NEXT: [[GEP_END_I15:%.*]] = getelementptr [[VEC]], %vec* [[C]], i64 0, i32 1
; CHECK-NEXT: [[GEP_END_I3:%.*]] = getelementptr [[VEC]], %vec* [[B:%.*]], i64 0, i32 1
; CHECK-NEXT: [[GEP_START_I1:%.*]] = getelementptr [[VEC]], %vec* [[B]], i64 0, i32 0
; CHECK-NEXT: [[LV_I_PEEL:%.*]] = load i64, i64* [[START_I]], align 4
; CHECK-NEXT: [[START_I2_PEEL:%.*]] = load i64*, i64** [[GEP_START_I1]], align 8
; CHECK-NEXT: [[END_I4_PEEL:%.*]] = load i64*, i64** [[GEP_END_I3]], align 8
; CHECK-NEXT: [[START_INT_I5_PEEL:%.*]] = ptrtoint i64* [[START_I2_PEEL]] to i64
; CHECK-NEXT: [[END_I4_PEEL_FR:%.*]] = freeze i64* [[END_I4_PEEL]]
; CHECK-NEXT: [[END_INT_I6_PEEL:%.*]] = ptrtoint i64* [[END_I4_PEEL_FR]] to i64
; CHECK-NEXT: [[SUB_I7_PEEL:%.*]] = sub i64 [[END_INT_I6_PEEL]], [[START_INT_I5_PEEL]]
; CHECK-NEXT: [[START_I14_PEEL:%.*]] = load i64*, i64** [[GEP_START_I13]], align 8
; CHECK-NEXT: [[END_I16_PEEL:%.*]] = load i64*, i64** [[GEP_END_I15]], align 8
; CHECK-NEXT: [[START_INT_I17_PEEL:%.*]] = ptrtoint i64* [[START_I14_PEEL]] to i64
; CHECK-NEXT: [[END_INT_I18_PEEL:%.*]] = ptrtoint i64* [[END_I16_PEEL]] to i64
; CHECK-NEXT: [[SUB_I19_PEEL:%.*]] = sub i64 [[END_INT_I18_PEEL]], [[START_INT_I17_PEEL]]
; CHECK-NEXT: [[LV_I10_PEEL:%.*]] = load i64, i64* [[START_I2_PEEL]], align 4
; CHECK-NEXT: [[LV_I22_PEEL:%.*]] = load i64, i64* [[START_I14_PEEL]], align 4
; CHECK-NEXT: [[ADD_2_PEEL:%.*]] = add i64 [[LV_I_PEEL]], [[LV_I10_PEEL]]
; CHECK-NEXT: [[SUM_NEXT_PEEL:%.*]] = add i64 [[ADD_2_PEEL]], [[LV_I22_PEEL]]
; CHECK-NEXT: [[COND_PEEL:%.*]] = icmp sgt i64 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[COND_PEEL]], label [[LOOP_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK: loop.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N]], -1
; CHECK-NEXT: [[UMIN:%.*]] = tail call i64 @llvm.umin.i64(i64 [[SUB_I19_PEEL]], i64 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = freeze i64 [[UMIN]]
; CHECK-NEXT: [[UMIN28:%.*]] = tail call i64 @llvm.umin.i64(i64 [[TMP1]], i64 [[SUB_I7_PEEL]])
; CHECK-NEXT: [[UMIN29:%.*]] = tail call i64 @llvm.umin.i64(i64 [[UMIN28]], i64 [[SUB_I]])
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[UMIN29]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 5
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[LOOP_PREHEADER36:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = and i64 [[TMP2]], 3
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i64 4, i64 [[N_MOD_VF]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[IND_END:%.*]] = add i64 [[N_VEC]], 1
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i64> <i64 poison, i64 0>, i64 [[SUM_NEXT_PEEL]], i64 0
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x i64> [ [[TMP5]], [[VECTOR_PH]] ], [ [[TMP22:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI30:%.*]] = phi <2 x i64> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP23:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i64, i64* [[START_I]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i64* [[TMP6]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x i64>, <2 x i64>* [[TMP7]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i64, i64* [[TMP6]], i64 2
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i64* [[TMP8]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD31:%.*]] = load <2 x i64>, <2 x i64>* [[TMP9]], align 4
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr i64, i64* [[START_I2_PEEL]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP11:%.*]] = bitcast i64* [[TMP10]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD32:%.*]] = load <2 x i64>, <2 x i64>* [[TMP11]], align 4
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i64, i64* [[TMP10]], i64 2
; CHECK-NEXT: [[TMP13:%.*]] = bitcast i64* [[TMP12]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD33:%.*]] = load <2 x i64>, <2 x i64>* [[TMP13]], align 4
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr i64, i64* [[START_I14_PEEL]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP15:%.*]] = bitcast i64* [[TMP14]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD34:%.*]] = load <2 x i64>, <2 x i64>* [[TMP15]], align 4
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr i64, i64* [[TMP14]], i64 2
; CHECK-NEXT: [[TMP17:%.*]] = bitcast i64* [[TMP16]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD35:%.*]] = load <2 x i64>, <2 x i64>* [[TMP17]], align 4
; CHECK-NEXT: [[TMP18:%.*]] = add <2 x i64> [[WIDE_LOAD]], [[VEC_PHI]]
; CHECK-NEXT: [[TMP19:%.*]] = add <2 x i64> [[WIDE_LOAD31]], [[VEC_PHI30]]
; CHECK-NEXT: [[TMP20:%.*]] = add <2 x i64> [[TMP18]], [[WIDE_LOAD32]]
; CHECK-NEXT: [[TMP21:%.*]] = add <2 x i64> [[TMP19]], [[WIDE_LOAD33]]
; CHECK-NEXT: [[TMP22]] = add <2 x i64> [[TMP20]], [[WIDE_LOAD34]]
; CHECK-NEXT: [[TMP23]] = add <2 x i64> [[TMP21]], [[WIDE_LOAD35]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP24:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <2 x i64> [[TMP23]], [[TMP22]]
; CHECK-NEXT: [[TMP25:%.*]] = tail call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[BIN_RDX]])
; CHECK-NEXT: br label [[LOOP_PREHEADER36]]
; CHECK: loop.preheader36:
; CHECK-NEXT: [[IV_PH:%.*]] = phi i64 [ 1, [[LOOP_PREHEADER]] ], [ [[IND_END]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: [[SUM_PH:%.*]] = phi i64 [ [[SUM_NEXT_PEEL]], [[LOOP_PREHEADER]] ], [ [[TMP25]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT24:%.*]] ], [ [[IV_PH]], [[LOOP_PREHEADER36]] ]
; CHECK-NEXT: [[SUM:%.*]] = phi i64 [ [[SUM_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT24]] ], [ [[SUM_PH]], [[LOOP_PREHEADER36]] ]
; 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: [[INRANGE_I8:%.*]] = icmp ult i64 [[SUB_I7_PEEL]], [[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: [[INRANGE_I20:%.*]] = icmp ult i64 [[SUB_I19_PEEL]], [[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_PEEL]], i64 [[IV]]
; CHECK-NEXT: [[LV_I10:%.*]] = load i64, i64* [[GEP_IDX_I9]], align 4
; CHECK-NEXT: [[GEP_IDX_I21:%.*]] = getelementptr i64, i64* [[START_I14_PEEL]], 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]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: [[SUM_NEXT_LCSSA:%.*]] = phi i64 [ [[SUM_NEXT_PEEL]], [[AT_WITH_INT_CONVERSION_EXIT24_PEEL:%.*]] ], [ [[SUM_NEXT]], [[AT_WITH_INT_CONVERSION_EXIT24]] ]
; CHECK-NEXT: ret i64 [[SUM_NEXT_LCSSA]]
;
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()
Reference in New Issue View Git Blame Copy Permalink