[llvm] [LV][VP][NFC]Add tests for safe store/load forwarding/dependence distance. (PR #100635)

Florian Hahn via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 25 13:34:20 PDT 2024


================
@@ -0,0 +1,418 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes=loop-vectorize \
+; RUN: -force-tail-folding-style=data-with-evl \
+; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
+; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck %s --check-prefix=IF-EVL
+
+; RUN: opt -passes=loop-vectorize \
+; RUN: -force-tail-folding-style=none \
+; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
+; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck %s --check-prefix=NO-VP
+
+; Dependence distance between read and write is greater than the trip
+; count of the loop.  Thus, values written are never read for any
+; valid vectorization of the loop.
+define void @test(ptr %p) {
+; IF-EVL-LABEL: @test(
+; IF-EVL-NEXT:  entry:
+; IF-EVL-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; IF-EVL:       vector.ph:
+; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 200, [[TMP2]]
+; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; IF-EVL-NEXT:    br label [[VECTOR_BODY:%.*]]
+; IF-EVL:       vector.body:
+; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[TMP5:%.*]] = sub i64 200, [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[TMP5]], i32 2, i1 true)
+; IF-EVL-NEXT:    [[TMP7:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP7]]
+; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[TMP8]], i32 0
+; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 32 [[TMP9]], <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), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP10:%.*]] = add i64 [[TMP7]], 200
+; IF-EVL-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP10]]
+; IF-EVL-NEXT:    [[TMP12:%.*]] = getelementptr i64, ptr [[TMP11]], i32 0
+; IF-EVL-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP_LOAD]], ptr align 32 [[TMP12]], <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), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP13:%.*]] = zext i32 [[TMP6]] to i64
+; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add i64 [[TMP13]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; IF-EVL:       middle.block:
+; IF-EVL-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; IF-EVL:       scalar.ph:
+; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; IF-EVL-NEXT:    br label [[LOOP:%.*]]
+; IF-EVL:       loop:
+; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; IF-EVL-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
+; IF-EVL-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; IF-EVL-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 200
+; IF-EVL-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; IF-EVL-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
+; IF-EVL-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
+; IF-EVL:       exit:
+; IF-EVL-NEXT:    ret void
+;
+; NO-VP-LABEL: @test(
+; NO-VP-NEXT:  entry:
+; NO-VP-NEXT:    br label [[LOOP:%.*]]
+; NO-VP:       loop:
+; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; NO-VP-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[IV]]
+; NO-VP-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; NO-VP-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 200
+; NO-VP-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; NO-VP-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
+; NO-VP-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT:%.*]]
+; NO-VP:       exit:
+; NO-VP-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i64 [0, %entry], [%iv.next, %loop]
+  %a1 = getelementptr i64, ptr %p, i64 %iv
+  %v = load i64, ptr %a1, align 32
+  %offset = add i64 %iv, 200
+  %a2 = getelementptr i64, ptr %p, i64 %offset
+  store i64 %v, ptr %a2, align 32
+  %iv.next = add i64 %iv, 1
+  %cmp = icmp ne i64 %iv, 199
+  br i1 %cmp, label %loop, label %exit
+
+exit:
+  ret void
+}
+
+; Dependence distance is less than trip count, thus we must prove that
+; chosen VF guaranteed to be less than dependence distance.
+define void @test_may_clobber(ptr %p) {
+; IF-EVL-LABEL: @test_may_clobber(
+; IF-EVL-NEXT:  entry:
+; IF-EVL-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; IF-EVL:       vector.ph:
+; IF-EVL-NEXT:    br label [[VECTOR_BODY:%.*]]
+; IF-EVL:       vector.body:
+; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; IF-EVL-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
+; IF-EVL-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[TMP1]], i32 0
+; IF-EVL-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP2]], align 32
+; IF-EVL-NEXT:    [[TMP3:%.*]] = add i64 [[TMP0]], 100
+; IF-EVL-NEXT:    [[TMP4:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP3]]
+; IF-EVL-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[TMP4]], i32 0
+; IF-EVL-NEXT:    store <4 x i64> [[WIDE_LOAD]], ptr [[TMP5]], align 32
+; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; IF-EVL-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
+; IF-EVL-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; IF-EVL:       middle.block:
+; IF-EVL-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; IF-EVL:       scalar.ph:
+; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; IF-EVL-NEXT:    br label [[LOOP:%.*]]
+; IF-EVL:       loop:
+; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; IF-EVL-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
+; IF-EVL-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; IF-EVL-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 100
+; IF-EVL-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; IF-EVL-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
+; IF-EVL-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP5:![0-9]+]]
+; IF-EVL:       exit:
+; IF-EVL-NEXT:    ret void
+;
+; NO-VP-LABEL: @test_may_clobber(
+; NO-VP-NEXT:  entry:
+; NO-VP-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; NO-VP:       vector.ph:
+; NO-VP-NEXT:    br label [[VECTOR_BODY:%.*]]
+; NO-VP:       vector.body:
+; NO-VP-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; NO-VP-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; NO-VP-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
+; NO-VP-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[TMP1]], i32 0
+; NO-VP-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP2]], align 32
+; NO-VP-NEXT:    [[TMP3:%.*]] = add i64 [[TMP0]], 100
+; NO-VP-NEXT:    [[TMP4:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP3]]
+; NO-VP-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[TMP4]], i32 0
+; NO-VP-NEXT:    store <4 x i64> [[WIDE_LOAD]], ptr [[TMP5]], align 32
+; NO-VP-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; NO-VP-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
+; NO-VP-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; NO-VP:       middle.block:
+; NO-VP-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; NO-VP:       scalar.ph:
+; NO-VP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; NO-VP-NEXT:    br label [[LOOP:%.*]]
+; NO-VP:       loop:
+; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; NO-VP-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
+; NO-VP-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; NO-VP-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 100
+; NO-VP-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; NO-VP-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
+; NO-VP-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
+; NO-VP:       exit:
+; NO-VP-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i64 [0, %entry], [%iv.next, %loop]
+  %a1 = getelementptr i64, ptr %p, i64 %iv
+  %v = load i64, ptr %a1, align 32
+  %offset = add i64 %iv, 100
+  %a2 = getelementptr i64, ptr %p, i64 %offset
+  store i64 %v, ptr %a2, align 32
+  %iv.next = add i64 %iv, 1
+  %cmp = icmp ne i64 %iv, 199
+  br i1 %cmp, label %loop, label %exit
+
+exit:
+  ret void
+}
+
+; Trviailly no overlap due to maximum possible value of VLEN and LMUL
+define void @trivial_due_max_vscale(ptr %p) {
+; IF-EVL-LABEL: @trivial_due_max_vscale(
+; IF-EVL-NEXT:  entry:
+; IF-EVL-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; IF-EVL:       vector.ph:
+; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 200, [[TMP2]]
+; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; IF-EVL-NEXT:    br label [[VECTOR_BODY:%.*]]
+; IF-EVL:       vector.body:
+; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[TMP5:%.*]] = sub i64 200, [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[TMP5]], i32 2, i1 true)
+; IF-EVL-NEXT:    [[TMP7:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP7]]
+; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[TMP8]], i32 0
+; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 32 [[TMP9]], <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), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP10:%.*]] = add i64 [[TMP7]], 8192
+; IF-EVL-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP10]]
+; IF-EVL-NEXT:    [[TMP12:%.*]] = getelementptr i64, ptr [[TMP11]], i32 0
+; IF-EVL-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VP_OP_LOAD]], ptr align 32 [[TMP12]], <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), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP13:%.*]] = zext i32 [[TMP6]] to i64
+; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add i64 [[TMP13]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; IF-EVL:       middle.block:
+; IF-EVL-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; IF-EVL:       scalar.ph:
+; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; IF-EVL-NEXT:    br label [[LOOP:%.*]]
+; IF-EVL:       loop:
+; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; IF-EVL-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
+; IF-EVL-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; IF-EVL-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 8192
+; IF-EVL-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; IF-EVL-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
+; IF-EVL-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP7:![0-9]+]]
+; IF-EVL:       exit:
+; IF-EVL-NEXT:    ret void
+;
+; NO-VP-LABEL: @trivial_due_max_vscale(
+; NO-VP-NEXT:  entry:
+; NO-VP-NEXT:    br label [[LOOP:%.*]]
+; NO-VP:       loop:
+; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; NO-VP-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[IV]]
+; NO-VP-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; NO-VP-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 8192
+; NO-VP-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; NO-VP-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
+; NO-VP-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT:%.*]]
+; NO-VP:       exit:
+; NO-VP-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i64 [0, %entry], [%iv.next, %loop]
+  %a1 = getelementptr i64, ptr %p, i64 %iv
+  %v = load i64, ptr %a1, align 32
+  %offset = add i64 %iv, 8192
+  %a2 = getelementptr i64, ptr %p, i64 %offset
+  store i64 %v, ptr %a2, align 32
+  %iv.next = add i64 %iv, 1
+  %cmp = icmp ne i64 %iv, 199
+  br i1 %cmp, label %loop, label %exit
+
+exit:
+  ret void
+}
+
+; Dependence distance could be violated via LMUL>=2 or interleaving
+define void @no_high_lmul_or_interleave(ptr %p) {
+; IF-EVL-LABEL: @no_high_lmul_or_interleave(
+; IF-EVL-NEXT:  entry:
+; IF-EVL-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; IF-EVL:       vector.ph:
+; IF-EVL-NEXT:    br label [[VECTOR_BODY:%.*]]
+; IF-EVL:       vector.body:
+; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[INDEX]], i64 0
+; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
+; IF-EVL-NEXT:    [[VEC_IV:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
+; IF-EVL-NEXT:    [[TMP1:%.*]] = icmp ule <4 x i64> [[VEC_IV]], <i64 3001, i64 3001, i64 3001, i64 3001>
+; IF-EVL-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
+; IF-EVL-NEXT:    [[TMP3:%.*]] = getelementptr i64, ptr [[TMP2]], i32 0
+; IF-EVL-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i64> @llvm.masked.load.v4i64.p0(ptr [[TMP3]], i32 32, <4 x i1> [[TMP1]], <4 x i64> poison)
+; IF-EVL-NEXT:    [[TMP4:%.*]] = add i64 [[TMP0]], 1024
+; IF-EVL-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP4]]
+; IF-EVL-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[TMP5]], i32 0
+; IF-EVL-NEXT:    call void @llvm.masked.store.v4i64.p0(<4 x i64> [[WIDE_MASKED_LOAD]], ptr [[TMP6]], i32 32, <4 x i1> [[TMP1]])
+; IF-EVL-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
+; IF-EVL-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 3004
+; IF-EVL-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; IF-EVL:       middle.block:
+; IF-EVL-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; IF-EVL:       scalar.ph:
+; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 3004, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; IF-EVL-NEXT:    br label [[LOOP:%.*]]
+; IF-EVL:       loop:
+; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; IF-EVL-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
+; IF-EVL-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; IF-EVL-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 1024
+; IF-EVL-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; IF-EVL-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; IF-EVL-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; IF-EVL-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 3001
+; IF-EVL-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP9:![0-9]+]]
+; IF-EVL:       exit:
+; IF-EVL-NEXT:    ret void
+;
+; NO-VP-LABEL: @no_high_lmul_or_interleave(
+; NO-VP-NEXT:  entry:
+; NO-VP-NEXT:    br label [[LOOP:%.*]]
+; NO-VP:       loop:
+; NO-VP-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
+; NO-VP-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[IV]]
+; NO-VP-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
+; NO-VP-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 1024
+; NO-VP-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
+; NO-VP-NEXT:    store i64 [[V]], ptr [[A2]], align 32
+; NO-VP-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; NO-VP-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 3001
+; NO-VP-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT:%.*]]
+; NO-VP:       exit:
+; NO-VP-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i64 [0, %entry], [%iv.next, %loop]
+  %a1 = getelementptr i64, ptr %p, i64 %iv
+  %v = load i64, ptr %a1, align 32
+  %offset = add i64 %iv, 1024
+  %a2 = getelementptr i64, ptr %p, i64 %offset
+  store i64 %v, ptr %a2, align 32
+  %iv.next = add i64 %iv, 1
+  %cmp = icmp ne i64 %iv, 3001
+  br i1 %cmp, label %loop, label %exit
+
+exit:
+  ret void
+}
+
+define void @non-power-2-storeloadforward(ptr %A) {
+; IF-EVL-LABEL: @non-power-2-storeloadforward(
+; IF-EVL-NEXT:  entry:
+; IF-EVL-NEXT:    br label [[FOR_BODY:%.*]]
+; IF-EVL:       for.body:
+; IF-EVL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 16, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; IF-EVL-NEXT:    [[TMP0:%.*]] = add nsw i64 [[INDVARS_IV]], -3
+; IF-EVL-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP0]]
+; IF-EVL-NEXT:    [[TMP1:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
+; IF-EVL-NEXT:    [[TMP2:%.*]] = add nsw i64 [[INDVARS_IV]], 4
+; IF-EVL-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP2]]
+; IF-EVL-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
+; IF-EVL-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP3]], [[TMP1]]
+; IF-EVL-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV]]
+; IF-EVL-NEXT:    store i32 [[ADD3]], ptr [[ARRAYIDX5]], align 4
+; IF-EVL-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
+; IF-EVL-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
+; IF-EVL-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[LFTR_WIDEIV]], 128
+; IF-EVL-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; IF-EVL:       for.end:
+; IF-EVL-NEXT:    ret void
+;
+; NO-VP-LABEL: @non-power-2-storeloadforward(
+; NO-VP-NEXT:  entry:
+; NO-VP-NEXT:    br label [[FOR_BODY:%.*]]
+; NO-VP:       for.body:
+; NO-VP-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 16, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; NO-VP-NEXT:    [[TMP0:%.*]] = add nsw i64 [[INDVARS_IV]], -3
+; NO-VP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP0]]
+; NO-VP-NEXT:    [[TMP1:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
+; NO-VP-NEXT:    [[TMP2:%.*]] = add nsw i64 [[INDVARS_IV]], 4
+; NO-VP-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP2]]
+; NO-VP-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
+; NO-VP-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP3]], [[TMP1]]
+; NO-VP-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV]]
+; NO-VP-NEXT:    store i32 [[ADD3]], ptr [[ARRAYIDX5]], align 4
+; NO-VP-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
+; NO-VP-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
+; NO-VP-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[LFTR_WIDEIV]], 128
+; NO-VP-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END:%.*]]
+; NO-VP:       for.end:
+; NO-VP-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 16, %entry ], [ %indvars.iv.next, %for.body ]
----------------
fhahn wrote:

```suggestion
  %iv  = phi i64 [ 16, %entry ], [ %iv.next, %for.body ]
```

https://github.com/llvm/llvm-project/pull/100635


More information about the llvm-commits mailing list