[llvm] ca9b60f - [LoopVectorize] Regenerate sve-vector-reverse.ll test checks
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Wed Jul 21 07:15:40 PDT 2021
Author: Simon Pilgrim
Date: 2021-07-21T15:14:04+01:00
New Revision: ca9b60f9dee41ff293b42b5a443f47ab13647387
URL: https://github.com/llvm/llvm-project/commit/ca9b60f9dee41ff293b42b5a443f47ab13647387
DIFF: https://github.com/llvm/llvm-project/commit/ca9b60f9dee41ff293b42b5a443f47ab13647387.diff
LOG: [LoopVectorize] Regenerate sve-vector-reverse.ll test checks
Added:
Modified:
llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
Removed:
################################################################################
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
index 002daddc26f33..5cd5af5dd9e6d 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; This is the loop in c++ being vectorize in this file with
;experimental.vector.reverse
; #pragma clang loop vectorize_width(8, scalable)
@@ -7,29 +8,77 @@
; RUN: opt -loop-vectorize -scalable-vectorization=on -dce -instcombine -mtriple aarch64-linux-gnu -S < %s | FileCheck %s
define void @vector_reverse_f64(i64 %N, double* %a, double* %b) #0{
-; CHECK-LABEL: @vector_reverse_f64
-; CHECK-LABEL: vector.body:
-; CHECK: %[[ADD:.*]] = add i64 %{{.*}}, %N
-; CHECK-NEXT: %[[GEP:.*]] = getelementptr inbounds double, double* %b, i64 %[[ADD]]
-; CHECK-NEXT: %[[VSCALE:.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: %[[MUL:.*]] = mul i32 %[[VSCALE]], -8
-; CHECK-NEXT: %[[OR:.*]] = or i32 %[[MUL]], 1
-; CHECK-NEXT: %[[SEXT:.*]] = sext i32 %[[OR]] to i64
-; CHECK-NEXT: %[[GEP1:.*]] = getelementptr inbounds double, double* %[[GEP]], i64 %[[SEXT]]
-; CHECK-NEXT: %[[CAST:.*]] = bitcast double* %[[GEP1]] to <vscale x 8 x double>*
-; CHECK-NEXT: %[[WIDE:.*]] = load <vscale x 8 x double>, <vscale x 8 x double>* %[[CAST]], align 8
-; CHECK-NEXT: %[[REVERSE:.*]] = call <vscale x 8 x double> @llvm.experimental.vector.reverse.nxv8f64(<vscale x 8 x double> %[[WIDE]])
-; CHECK-NEXT: %[[FADD:.*]] = fadd <vscale x 8 x double> %[[REVERSE]], shufflevector
-; CHECK-NEXT: %[[GEP2:.*]] = getelementptr inbounds double, double* %a, i64 %[[ADD]]
-; CHECK-NEXT: %[[REVERSE6:.*]] = call <vscale x 8 x double> @llvm.experimental.vector.reverse.nxv8f64(<vscale x 8 x double> %[[FADD]])
-; CHECK-NEXT: %[[VSCALE1:.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: %[[MUL1:.*]] = mul i32 %[[VSCALE1]], -8
-; CHECK-NEXT: %[[OR1:.*]] = or i32 %[[MUL1]], 1
-; CHECK-NEXT: %[[SEXT1:.*]] = sext i32 %[[OR1]] to i64
-; CHECK-NEXT: %[[GEP3:.*]] = getelementptr inbounds double, double* %[[GEP2]], i64 %[[SEXT1]]
-; CHECK-NEXT: %[[CAST1:.*]] = bitcast double* %[[GEP3]] to <vscale x 8 x double>*
-; CHECK-NEXT: store <vscale x 8 x double> %[[REVERSE6]], <vscale x 8 x double>* %[[CAST1]], align 8
-
+; CHECK-LABEL: @vector_reverse_f64(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[CMP7:%.*]] = icmp sgt i64 [[N:%.*]], 0
+; CHECK-NEXT: br i1 [[CMP7]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK: for.body.preheader:
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = shl i64 [[TMP0]], 3
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
+; CHECK: vector.memcheck:
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr double, double* [[A:%.*]], i64 [[N]]
+; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr double, double* [[B:%.*]], i64 [[N]]
+; CHECK-NEXT: [[BOUND0:%.*]] = icmp ugt double* [[SCEVGEP4]], [[A]]
+; CHECK-NEXT: [[BOUND1:%.*]] = icmp ugt double* [[SCEVGEP]], [[B]]
+; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = shl i64 [[TMP2]], 3
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP4:%.*]] = xor i64 [[INDEX]], -1
+; CHECK-NEXT: [[TMP5:%.*]] = add i64 [[TMP4]], [[N]]
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[TMP5]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[DOTNEG:%.*]] = mul i32 [[TMP7]], -8
+; CHECK-NEXT: [[TMP8:%.*]] = or i32 [[DOTNEG]], 1
+; CHECK-NEXT: [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds double, double* [[TMP6]], i64 [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = bitcast double* [[TMP10]] to <vscale x 8 x double>*
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 8 x double>, <vscale x 8 x double>* [[TMP11]], align 8, !alias.scope !0
+; CHECK-NEXT: [[REVERSE:%.*]] = call <vscale x 8 x double> @llvm.experimental.vector.reverse.nxv8f64(<vscale x 8 x double> [[WIDE_LOAD]])
+; CHECK-NEXT: [[TMP12:%.*]] = fadd <vscale x 8 x double> [[REVERSE]], shufflevector (<vscale x 8 x double> insertelement (<vscale x 8 x double> poison, double 1.000000e+00, i32 0), <vscale x 8 x double> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[TMP5]]
+; CHECK-NEXT: [[REVERSE6:%.*]] = call <vscale x 8 x double> @llvm.experimental.vector.reverse.nxv8f64(<vscale x 8 x double> [[TMP12]])
+; CHECK-NEXT: [[TMP14:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[DOTNEG7:%.*]] = mul i32 [[TMP14]], -8
+; CHECK-NEXT: [[TMP15:%.*]] = or i32 [[DOTNEG7]], 1
+; CHECK-NEXT: [[TMP16:%.*]] = sext i32 [[TMP15]] to i64
+; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds double, double* [[TMP13]], i64 [[TMP16]]
+; CHECK-NEXT: [[TMP18:%.*]] = bitcast double* [[TMP17]] to <vscale x 8 x double>*
+; CHECK-NEXT: store <vscale x 8 x double> [[REVERSE6]], <vscale x 8 x double>* [[TMP18]], align 8, !alias.scope !3, !noalias !0
+; CHECK-NEXT: [[TMP19:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP20:%.*]] = shl i64 [[TMP19]], 3
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP20]]
+; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK: middle.block:
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
+; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_MOD_VF]], [[MIDDLE_BLOCK]] ], [ [[N]], [[FOR_BODY_PREHEADER]] ], [ [[N]], [[VECTOR_MEMCHECK]] ]
+; CHECK-NEXT: br label [[FOR_BODY:%.*]]
+; CHECK: for.cond.cleanup.loopexit:
+; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: ret void
+; CHECK: for.body:
+; CHECK-NEXT: [[I_08_IN:%.*]] = phi i64 [ [[I_08:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[I_08]] = add nsw i64 [[I_08_IN]], -1
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[B]], i64 [[I_08]]
+; CHECK-NEXT: [[TMP22:%.*]] = load double, double* [[ARRAYIDX]], align 8
+; CHECK-NEXT: [[ADD:%.*]] = fadd double [[TMP22]], 1.000000e+00
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[I_08]]
+; CHECK-NEXT: store double [[ADD]], double* [[ARRAYIDX1]], align 8
+; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i64 [[I_08_IN]], 1
+; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]], !llvm.loop [[LOOP8:![0-9]+]]
+;
entry:
%cmp7 = icmp sgt i64 %N, 0
br i1 %cmp7, label %for.body, label %for.cond.cleanup
@@ -51,29 +100,77 @@ for.body: ; preds = %entry, %for.body
define void @vector_reverse_i64(i64 %N, i64* %a, i64* %b) #0 {
-; CHECK-LABEL: vector_reverse_i64
-; CHECK-LABEL: vector.body:
-; CHECK: %[[ADD:.*]] = add i64 %{{.*}}, %N
-; CHECK-NEXT: %[[GEP:.*]] = getelementptr inbounds i64, i64* %b, i64 %[[ADD]]
-; CHECK-NEXT: %[[VSCALE:.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: %[[MUL:.*]] = mul i32 %[[VSCALE]], -8
-; CHECK-NEXT: %[[OR:.*]] = or i32 %[[MUL]], 1
-; CHECK-NEXT: %[[SEXT:.*]] = sext i32 %[[OR]] to i64
-; CHECK-NEXT: %[[GEP1:.*]] = getelementptr inbounds i64, i64* %[[GEP]], i64 %[[SEXT]]
-; CHECK-NEXT: %[[CAST:.*]] = bitcast i64* %[[GEP1]] to <vscale x 8 x i64>*
-; CHECK-NEXT: %[[WIDE:.*]] = load <vscale x 8 x i64>, <vscale x 8 x i64>* %[[CAST]], align 8
-; CHECK-NEXT: %[[REVERSE:.*]] = call <vscale x 8 x i64> @llvm.experimental.vector.reverse.nxv8i64(<vscale x 8 x i64> %[[WIDE]])
-; CHECK-NEXT: %[[ADD1:.*]] = add <vscale x 8 x i64> %[[REVERSE]]
-; CHECK-NEXT: %[[GEP2:.*]] = getelementptr inbounds i64, i64* %a, i64 %[[ADD]]
-; CHECK-NEXT: %[[REVERSE6]] = call <vscale x 8 x i64> @llvm.experimental.vector.reverse.nxv8i64(<vscale x 8 x i64> %[[ADD1]])
-; CHECK-NEXT: %[[VSCALE:.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: %[[MUL1:.*]] = mul i32 %[[VSCALE]], -8
-; CHECK-NEXT: %[[OR1:.*]] = or i32 %[[MUL1]], 1
-; CHECK-NEXT: %[[SEXT1:.*]] = sext i32 %[[OR1]] to i64
-; CHECK-NEXT: %[[GEP3:.*]] = getelementptr inbounds i64, i64* %[[GEP2]], i64 %[[SEXT1]]
-; CHECK-NEXT: %[[CAST1:.*]] = bitcast i64* %[[GEP3]] to <vscale x 8 x i64>*
-; CHECK-NEXT: store <vscale x 8 x i64> %[[REVERSE6]], <vscale x 8 x i64>* %[[CAST1]], align 8
-
+; CHECK-LABEL: @vector_reverse_i64(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[CMP8:%.*]] = icmp sgt i64 [[N:%.*]], 0
+; CHECK-NEXT: br i1 [[CMP8]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK: for.body.preheader:
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = shl i64 [[TMP0]], 3
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
+; CHECK: vector.memcheck:
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i64, i64* [[A:%.*]], i64 [[N]]
+; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 [[N]]
+; CHECK-NEXT: [[BOUND0:%.*]] = icmp ugt i64* [[SCEVGEP4]], [[A]]
+; CHECK-NEXT: [[BOUND1:%.*]] = icmp ugt i64* [[SCEVGEP]], [[B]]
+; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = shl i64 [[TMP2]], 3
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP4:%.*]] = xor i64 [[INDEX]], -1
+; CHECK-NEXT: [[TMP5:%.*]] = add i64 [[TMP4]], [[N]]
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i64, i64* [[B]], i64 [[TMP5]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[DOTNEG:%.*]] = mul i32 [[TMP7]], -8
+; CHECK-NEXT: [[TMP8:%.*]] = or i32 [[DOTNEG]], 1
+; CHECK-NEXT: [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP6]], i64 [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = bitcast i64* [[TMP10]] to <vscale x 8 x i64>*
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 8 x i64>, <vscale x 8 x i64>* [[TMP11]], align 8, !alias.scope !9
+; CHECK-NEXT: [[REVERSE:%.*]] = call <vscale x 8 x i64> @llvm.experimental.vector.reverse.nxv8i64(<vscale x 8 x i64> [[WIDE_LOAD]])
+; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 8 x i64> [[REVERSE]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i32 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[TMP5]]
+; CHECK-NEXT: [[REVERSE6:%.*]] = call <vscale x 8 x i64> @llvm.experimental.vector.reverse.nxv8i64(<vscale x 8 x i64> [[TMP12]])
+; CHECK-NEXT: [[TMP14:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[DOTNEG7:%.*]] = mul i32 [[TMP14]], -8
+; CHECK-NEXT: [[TMP15:%.*]] = or i32 [[DOTNEG7]], 1
+; CHECK-NEXT: [[TMP16:%.*]] = sext i32 [[TMP15]] to i64
+; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds i64, i64* [[TMP13]], i64 [[TMP16]]
+; CHECK-NEXT: [[TMP18:%.*]] = bitcast i64* [[TMP17]] to <vscale x 8 x i64>*
+; CHECK-NEXT: store <vscale x 8 x i64> [[REVERSE6]], <vscale x 8 x i64>* [[TMP18]], align 8, !alias.scope !12, !noalias !9
+; CHECK-NEXT: [[TMP19:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP20:%.*]] = shl i64 [[TMP19]], 3
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP20]]
+; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; CHECK: middle.block:
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
+; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_MOD_VF]], [[MIDDLE_BLOCK]] ], [ [[N]], [[FOR_BODY_PREHEADER]] ], [ [[N]], [[VECTOR_MEMCHECK]] ]
+; CHECK-NEXT: br label [[FOR_BODY:%.*]]
+; CHECK: for.cond.cleanup.loopexit:
+; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: ret void
+; CHECK: for.body:
+; CHECK-NEXT: [[I_09_IN:%.*]] = phi i64 [ [[I_09:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[I_09]] = add nsw i64 [[I_09_IN]], -1
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[B]], i64 [[I_09]]
+; CHECK-NEXT: [[TMP22:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
+; CHECK-NEXT: [[ADD:%.*]] = add i64 [[TMP22]], 1
+; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[A]], i64 [[I_09]]
+; CHECK-NEXT: store i64 [[ADD]], i64* [[ARRAYIDX2]], align 8
+; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i64 [[I_09_IN]], 1
+; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]], !llvm.loop [[LOOP15:![0-9]+]]
+;
entry:
%cmp8 = icmp sgt i64 %N, 0
br i1 %cmp8, label %for.body, label %for.cond.cleanup
More information about the llvm-commits
mailing list