[llvm] d7323f6 - [RISCV][NFC] Add tests for interleaved accesses in loop vectorizer

Luke Lau via llvm-commits llvm-commits at lists.llvm.org
Thu Mar 9 09:43:23 PST 2023


Author: Luke Lau
Date: 2023-03-09T17:43:16Z
New Revision: d7323f6a7a6c1cc77cb8fb8ae2895f6d509fcbc3

URL: https://github.com/llvm/llvm-project/commit/d7323f6a7a6c1cc77cb8fb8ae2895f6d509fcbc3
DIFF: https://github.com/llvm/llvm-project/commit/d7323f6a7a6c1cc77cb8fb8ae2895f6d509fcbc3.diff

LOG: [RISCV][NFC] Add tests for interleaved accesses in loop vectorizer

Precommit test for D145155

Reviewed By: reames

Differential Revision: https://reviews.llvm.org/D145697

Added: 
    llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses-zve32x.ll
    llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses-zve32x.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses-zve32x.ll
new file mode 100644
index 0000000000000..241fa9d8cd49b
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses-zve32x.ll
@@ -0,0 +1,49 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+zve32x,+zvl1024b -S | FileCheck %s
+
+; This element type isn't a supported SEW so this shouldn't be interleaved
+define void @load_store_zve32x(ptr %p) {
+; CHECK-LABEL: @load_store_zve32x(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = shl i64 [[I]], 1
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i64, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[Y0:%.*]] = add i64 [[X0]], 1
+; CHECK-NEXT:    store i64 [[Y0]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i64, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[Y1:%.*]] = add i64 [[X1]], 2
+; CHECK-NEXT:    store i64 [[Y1]], ptr [[Q1]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = shl i64 %i, 1
+  %q0 = getelementptr i64, ptr %p, i64 %offset0
+  %x0 = load i64, ptr %q0
+  %y0 = add i64 %x0, 1
+  store i64 %y0, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i64, ptr %p, i64 %offset1
+  %x1 = load i64, ptr %q1
+  %y1 = add i64 %x1, 2
+  store i64 %y1, ptr %q1
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}

diff  --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
new file mode 100644
index 0000000000000..d520a70af69f3
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
@@ -0,0 +1,540 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -S | FileCheck %s
+
+define void @load_store_factor2_i32(ptr %p) {
+; CHECK-LABEL: @load_store_factor2_i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = add <vscale x 2 x i64> [[TMP4]], zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = mul <vscale x 2 x i64> [[TMP5]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP6]]
+; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 2
+; CHECK-NEXT:    [[TMP9:%.*]] = mul i64 1, [[TMP8]]
+; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP9]], i64 0
+; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP10:%.*]] = shl <vscale x 2 x i64> [[VEC_IND]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 2 x i64> [[TMP10]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP11]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i32> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 1, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> [[TMP12]], <vscale x 2 x ptr> [[TMP11]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 2 x i64> [[TMP10]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, ptr [[P]], <vscale x 2 x i64> [[TMP13]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP14]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 2 x i32> [[WIDE_MASKED_GATHER1]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 2, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> [[TMP15]], <vscale x 2 x ptr> [[TMP14]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 2
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP17]]
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; 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:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = shl i64 [[I]], 1
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; CHECK-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i32, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[Y1:%.*]] = add i32 [[X1]], 2
+; CHECK-NEXT:    store i32 [[Y1]], ptr [[Q1]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = shl i64 %i, 1
+  %q0 = getelementptr i32, ptr %p, i64 %offset0
+  %x0 = load i32, ptr %q0
+  %y0 = add i32 %x0, 1
+  store i32 %y0, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i32, ptr %p, i64 %offset1
+  %x1 = load i32, ptr %q1
+  %y1 = add i32 %x1, 2
+  store i32 %y1, ptr %q1
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}
+
+define void @load_store_factor2_i64(ptr %p) {
+; CHECK-LABEL: @load_store_factor2_i64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = shl i64 [[I]], 1
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i64, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[Y0:%.*]] = add i64 [[X0]], 1
+; CHECK-NEXT:    store i64 [[Y0]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i64, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[Y1:%.*]] = add i64 [[X1]], 2
+; CHECK-NEXT:    store i64 [[Y1]], ptr [[Q1]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = shl i64 %i, 1
+  %q0 = getelementptr i64, ptr %p, i64 %offset0
+  %x0 = load i64, ptr %q0
+  %y0 = add i64 %x0, 1
+  store i64 %y0, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i64, ptr %p, i64 %offset1
+  %x1 = load i64, ptr %q1
+  %y1 = add i64 %x1, 2
+  store i64 %y1, ptr %q1
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}
+
+define void @load_store_factor3_i32(ptr %p) {
+; CHECK-LABEL: @load_store_factor3_i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = add <vscale x 2 x i64> [[TMP4]], zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = mul <vscale x 2 x i64> [[TMP5]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP6]]
+; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 2
+; CHECK-NEXT:    [[TMP9:%.*]] = mul i64 1, [[TMP8]]
+; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP9]], i64 0
+; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP10:%.*]] = mul <vscale x 2 x i64> [[VEC_IND]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 3, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 2 x i64> [[TMP10]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP11]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i32> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 1, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> [[TMP12]], <vscale x 2 x ptr> [[TMP11]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 2 x i64> [[TMP10]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, ptr [[P]], <vscale x 2 x i64> [[TMP13]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP14]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 2 x i32> [[WIDE_MASKED_GATHER1]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 2, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> [[TMP15]], <vscale x 2 x ptr> [[TMP14]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; CHECK-NEXT:    [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP13]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr i32, ptr [[P]], <vscale x 2 x i64> [[TMP16]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER2:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP17]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP18:%.*]] = add <vscale x 2 x i32> [[WIDE_MASKED_GATHER2]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 3, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> [[TMP18]], <vscale x 2 x ptr> [[TMP17]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; CHECK-NEXT:    [[TMP19:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP20:%.*]] = mul i64 [[TMP19]], 2
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP20]]
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; CHECK-NEXT:    [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = mul i64 [[I]], 3
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; CHECK-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i32, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[Y1:%.*]] = add i32 [[X1]], 2
+; CHECK-NEXT:    store i32 [[Y1]], ptr [[Q1]], align 4
+; CHECK-NEXT:    [[OFFSET2:%.*]] = add i64 [[OFFSET1]], 1
+; CHECK-NEXT:    [[Q2:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET2]]
+; CHECK-NEXT:    [[X2:%.*]] = load i32, ptr [[Q2]], align 4
+; CHECK-NEXT:    [[Y2:%.*]] = add i32 [[X2]], 3
+; CHECK-NEXT:    store i32 [[Y2]], ptr [[Q2]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = mul i64 %i, 3
+  %q0 = getelementptr i32, ptr %p, i64 %offset0
+  %x0 = load i32, ptr %q0
+  %y0 = add i32 %x0, 1
+  store i32 %y0, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i32, ptr %p, i64 %offset1
+  %x1 = load i32, ptr %q1
+  %y1 = add i32 %x1, 2
+  store i32 %y1, ptr %q1
+
+  %offset2 = add i64 %offset1, 1
+  %q2 = getelementptr i32, ptr %p, i64 %offset2
+  %x2 = load i32, ptr %q2
+  %y2 = add i32 %x2, 3
+  store i32 %y2, ptr %q2
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}
+
+define void @load_store_factor3_i64(ptr %p) {
+; CHECK-LABEL: @load_store_factor3_i64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = mul i64 [[I]], 3
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i64, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[Y0:%.*]] = add i64 [[X0]], 1
+; CHECK-NEXT:    store i64 [[Y0]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i64, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[Y1:%.*]] = add i64 [[X1]], 2
+; CHECK-NEXT:    store i64 [[Y1]], ptr [[Q1]], align 4
+; CHECK-NEXT:    [[OFFSET2:%.*]] = add i64 [[OFFSET1]], 1
+; CHECK-NEXT:    [[Q2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET2]]
+; CHECK-NEXT:    [[X2:%.*]] = load i64, ptr [[Q2]], align 4
+; CHECK-NEXT:    [[Y2:%.*]] = add i64 [[X2]], 3
+; CHECK-NEXT:    store i64 [[Y2]], ptr [[Q2]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = mul i64 %i, 3
+  %q0 = getelementptr i64, ptr %p, i64 %offset0
+  %x0 = load i64, ptr %q0
+  %y0 = add i64 %x0, 1
+  store i64 %y0, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i64, ptr %p, i64 %offset1
+  %x1 = load i64, ptr %q1
+  %y1 = add i64 %x1, 2
+  store i64 %y1, ptr %q1
+
+  %offset2 = add i64 %offset1, 1
+  %q2 = getelementptr i64, ptr %p, i64 %offset2
+  %x2 = load i64, ptr %q2
+  %y2 = add i64 %x2, 3
+  store i64 %y2, ptr %q2
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}
+
+define void @load_store_factor8(ptr %p) {
+; CHECK-LABEL: @load_store_factor8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = shl i64 [[I]], 3
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i64, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[Y0:%.*]] = add i64 [[X0]], 1
+; CHECK-NEXT:    store i64 [[Y0]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i64, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[Y1:%.*]] = add i64 [[X1]], 2
+; CHECK-NEXT:    store i64 [[Y1]], ptr [[Q1]], align 4
+; CHECK-NEXT:    [[OFFSET2:%.*]] = add i64 [[OFFSET1]], 1
+; CHECK-NEXT:    [[Q2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET2]]
+; CHECK-NEXT:    [[X2:%.*]] = load i64, ptr [[Q2]], align 4
+; CHECK-NEXT:    [[Y2:%.*]] = add i64 [[X2]], 3
+; CHECK-NEXT:    store i64 [[Y2]], ptr [[Q2]], align 4
+; CHECK-NEXT:    [[OFFSET3:%.*]] = add i64 [[OFFSET2]], 1
+; CHECK-NEXT:    [[Q3:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET3]]
+; CHECK-NEXT:    [[X3:%.*]] = load i64, ptr [[Q3]], align 4
+; CHECK-NEXT:    [[Y3:%.*]] = add i64 [[X3]], 4
+; CHECK-NEXT:    store i64 [[Y3]], ptr [[Q3]], align 4
+; CHECK-NEXT:    [[OFFSET4:%.*]] = add i64 [[OFFSET3]], 1
+; CHECK-NEXT:    [[Q4:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET4]]
+; CHECK-NEXT:    [[X4:%.*]] = load i64, ptr [[Q4]], align 4
+; CHECK-NEXT:    [[Y4:%.*]] = add i64 [[X4]], 5
+; CHECK-NEXT:    store i64 [[Y4]], ptr [[Q4]], align 4
+; CHECK-NEXT:    [[OFFSET5:%.*]] = add i64 [[OFFSET4]], 1
+; CHECK-NEXT:    [[Q5:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET5]]
+; CHECK-NEXT:    [[X5:%.*]] = load i64, ptr [[Q5]], align 4
+; CHECK-NEXT:    [[Y5:%.*]] = add i64 [[X5]], 6
+; CHECK-NEXT:    store i64 [[Y5]], ptr [[Q5]], align 4
+; CHECK-NEXT:    [[OFFSET6:%.*]] = add i64 [[OFFSET5]], 1
+; CHECK-NEXT:    [[Q6:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET6]]
+; CHECK-NEXT:    [[X6:%.*]] = load i64, ptr [[Q6]], align 4
+; CHECK-NEXT:    [[Y6:%.*]] = add i64 [[X6]], 7
+; CHECK-NEXT:    store i64 [[Y6]], ptr [[Q6]], align 4
+; CHECK-NEXT:    [[OFFSET7:%.*]] = add i64 [[OFFSET6]], 1
+; CHECK-NEXT:    [[Q7:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET7]]
+; CHECK-NEXT:    [[X7:%.*]] = load i64, ptr [[Q7]], align 4
+; CHECK-NEXT:    [[Y7:%.*]] = add i64 [[X7]], 8
+; CHECK-NEXT:    store i64 [[Y7]], ptr [[Q7]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = shl i64 %i, 3
+  %q0 = getelementptr i64, ptr %p, i64 %offset0
+  %x0 = load i64, ptr %q0
+  %y0 = add i64 %x0, 1
+  store i64 %y0, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i64, ptr %p, i64 %offset1
+  %x1 = load i64, ptr %q1
+  %y1 = add i64 %x1, 2
+  store i64 %y1, ptr %q1
+
+  %offset2 = add i64 %offset1, 1
+  %q2 = getelementptr i64, ptr %p, i64 %offset2
+  %x2 = load i64, ptr %q2
+  %y2 = add i64 %x2, 3
+  store i64 %y2, ptr %q2
+
+  %offset3 = add i64 %offset2, 1
+  %q3 = getelementptr i64, ptr %p, i64 %offset3
+  %x3 = load i64, ptr %q3
+  %y3 = add i64 %x3, 4
+  store i64 %y3, ptr %q3
+
+  %offset4 = add i64 %offset3, 1
+  %q4 = getelementptr i64, ptr %p, i64 %offset4
+  %x4 = load i64, ptr %q4
+  %y4 = add i64 %x4, 5
+  store i64 %y4, ptr %q4
+
+  %offset5 = add i64 %offset4, 1
+  %q5 = getelementptr i64, ptr %p, i64 %offset5
+  %x5 = load i64, ptr %q5
+  %y5 = add i64 %x5, 6
+  store i64 %y5, ptr %q5
+
+  %offset6 = add i64 %offset5, 1
+  %q6 = getelementptr i64, ptr %p, i64 %offset6
+  %x6 = load i64, ptr %q6
+  %y6 = add i64 %x6, 7
+  store i64 %y6, ptr %q6
+
+  %offset7 = add i64 %offset6, 1
+  %q7 = getelementptr i64, ptr %p, i64 %offset7
+  %x7 = load i64, ptr %q7
+  %y7 = add i64 %x7, 8
+  store i64 %y7, ptr %q7
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}
+
+define void @combine_load_factor2_i32(ptr %p) {
+; CHECK-LABEL: @combine_load_factor2_i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = add <vscale x 2 x i64> [[TMP4]], zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = mul <vscale x 2 x i64> [[TMP5]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP6]]
+; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 2
+; CHECK-NEXT:    [[TMP9:%.*]] = mul i64 1, [[TMP8]]
+; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP9]], i64 0
+; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP10:%.*]] = shl <vscale x 2 x i64> [[VEC_IND]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 2 x i64> [[TMP10]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP11]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[TMP10]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, ptr [[P]], <vscale x 2 x i64> [[TMP12]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32.nxv2p0(<vscale x 2 x ptr> [[TMP13]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i32> poison)
+; CHECK-NEXT:    [[TMP14:%.*]] = add <vscale x 2 x i32> [[WIDE_MASKED_GATHER]], [[WIDE_MASKED_GATHER1]]
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> [[TMP14]], <vscale x 2 x ptr> [[TMP11]], i32 4, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 2
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP16]]
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = shl i64 [[I]], 1
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i32, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[RES:%.*]] = add i32 [[X0]], [[X1]]
+; CHECK-NEXT:    store i32 [[RES]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = shl i64 %i, 1
+  %q0 = getelementptr i32, ptr %p, i64 %offset0
+  %x0 = load i32, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i32, ptr %p, i64 %offset1
+  %x1 = load i32, ptr %q1
+
+  %res = add i32 %x0, %x1
+
+  store i32 %res, ptr %q0
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}
+
+define void @combine_load_factor2_i64(ptr %p) {
+; CHECK-LABEL: @combine_load_factor2_i64(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET0:%.*]] = shl i64 [[I]], 1
+; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[OFFSET0]]
+; CHECK-NEXT:    [[X0:%.*]] = load i64, ptr [[Q0]], align 4
+; CHECK-NEXT:    [[OFFSET1:%.*]] = add i64 [[OFFSET0]], 1
+; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET1]]
+; CHECK-NEXT:    [[X1:%.*]] = load i64, ptr [[Q1]], align 4
+; CHECK-NEXT:    [[RES:%.*]] = add i64 [[X0]], [[X1]]
+; CHECK-NEXT:    store i64 [[RES]], ptr [[Q0]], align 4
+; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+loop:
+  %i = phi i64 [0, %entry], [%nexti, %loop]
+
+  %offset0 = shl i64 %i, 1
+  %q0 = getelementptr i64, ptr %p, i64 %offset0
+  %x0 = load i64, ptr %q0
+
+  %offset1 = add i64 %offset0, 1
+  %q1 = getelementptr i64, ptr %p, i64 %offset1
+  %x1 = load i64, ptr %q1
+
+  %res = add i64 %x0, %x1
+
+  store i64 %res, ptr %q0
+
+  %nexti = add i64 %i, 1
+  %done = icmp eq i64 %nexti, 1024
+  br i1 %done, label %exit, label %loop
+exit:
+  ret void
+}


        


More information about the llvm-commits mailing list