[VPlan] Include flags in VectorPointerRecipe::printRecipe #169466
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
The change is non-functional with respect to emitted IR.
Member
| @llvm/pr-subscribers-backend-risc-v Author: Ramkumar Ramachandra (artagnon) ChangesThe change is non-functional with respect to emitted IR. Patch is 56.80 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/169466.diff 18 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp index 54fdec3bcf4a1..e41f67103e096 100644 --- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp +++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp @@ -2661,7 +2661,7 @@ void VPVectorPointerRecipe::printRecipe(raw_ostream &O, const Twine &Indent, O << Indent; printAsOperand(O, SlotTracker); O << " = vector-pointer "; - + printFlags(O); printOperands(O, SlotTracker); } #endif diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll index 444c6dd269425..9891617890625 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll @@ -76,7 +76,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: EMIT [[IV:.*]] = CANONICAL-INDUCTION ir<0>, [[IV_NEXT:.*]] ; CHECK-NEXT: [[STEPS:vp.*]] = SCALAR-STEPS [[IV]], ir<1>, [[VF]] ; CHECK-NEXT: CLONE [[GEP_IDX:.*]] = getelementptr inbounds ir<%indices>, [[STEPS]] -; CHECK-NEXT: [[VECP_IDX:vp.*]] = vector-pointer [[GEP_IDX]] +; CHECK-NEXT: [[VECP_IDX:vp.*]] = vector-pointer inbounds [[GEP_IDX]] ; CHECK-NEXT: WIDEN [[IDX:.*]] = load [[VECP_IDX]] ; CHECK-NEXT: WIDEN-CAST [[EXT_IDX:.*]] = zext [[IDX]] to i64 ; CHECK-NEXT: WIDEN-GEP Inv[Var] [[GEP_BUCKET:.*]] = getelementptr inbounds ir<%buckets>, [[EXT_IDX]] diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll index 6da3c77cd35c1..358c2aa3ed5cb 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll @@ -30,7 +30,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: REPLICATE ir<%call> = call @foo(ir<%load>) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -77,7 +77,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed4_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -129,7 +129,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed2_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXST:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -176,7 +176,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>, ir<true>) (using library function: foo_vector_fixed4_mask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -227,7 +227,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed2_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -274,7 +274,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed4_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll b/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll index 5999707699970..cf035d0b2b2ee 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll @@ -24,7 +24,7 @@ target triple = "arm64-apple-ios" ; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>, vp<[[VF]]> ; CHECK-NEXT: CLONE ir<%gep.src> = getelementptr inbounds ir<%src>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%gep.src> ; CHECK-NEXT: WIDEN ir<%l> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CAST ir<%conv> = fpext ir<%l> to double ; CHECK-NEXT: WIDEN-CALL ir<%s> = call fast @llvm.sin.f64(ir<%conv>) (using library function: __simd_sin_v2f64) @@ -71,7 +71,7 @@ target triple = "arm64-apple-ios" ; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>, vp<[[VF]]> ; CHECK-NEXT: CLONE ir<%gep.src> = getelementptr inbounds ir<%src>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%gep.src> ; CHECK-NEXT: WIDEN ir<%l> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CAST ir<%conv> = fpext ir<%l> to double ; CHECK-NEXT: WIDEN-INTRINSIC ir<%s> = call fast llvm.sin(ir<%conv>) diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll index 4416c0e780eff..64909a7c2fcec 100644 --- a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll @@ -25,7 +25,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 2: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 2: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 18 for VF 2: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 4 for VF 2: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 20 for VF 2: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> @@ -42,7 +42,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 4: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 4: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 2 for VF 4: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 0 for VF 4: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 2 for VF 4: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> @@ -59,7 +59,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 8: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 8: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 2 for VF 8: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 2 for VF 8: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 36 for VF 8: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll index ab4bb90b55b70..cc76ea04978a3 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll @@ -8,7 +8,7 @@ define void @first_order_recurrence(ptr noalias %A, ptr noalias %B, i64 %TC) { ; IF-EVL: VPlan 'Initial VPlan for VF={1},UF>=1' ; IF-EVL-NOT: EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI ; -; IF-EVL: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' { +; IF-EVL: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' { ; IF-EVL-NEXT: Live-in vp<[[VF:%[0-9]+]]> = VF ; IF-EVL-NEXT: Live-in vp<[[VFUF:%[0-9]+]]> = VF * UF ; IF-EVL-NEXT: Live-in vp<[[VTC:%[0-9]+]]> = vector-trip-count @@ -31,12 +31,12 @@ define void @first_order_recurrence(ptr noalias %A, ptr noalias %B, i64 %TC) { ; IF-EVL-NEXT: EMIT-SCALAR vp<[[EVL]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1> ; IF-EVL-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds nuw ir<%A>, vp<[[ST]] -; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds nuw ir<[[GEP1]]> ; IF-EVL-NEXT: WIDEN ir<[[LD]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[SPLICE:%[0-9]+]]> = call llvm.experimental.vp.splice(ir<[[FOR_PHI]]>, ir<[[LD]]>, ir<-1>, ir<true>, vp<[[PREV_EVL]]>, vp<[[EVL]]>) ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw vp<[[SPLICE]]>, ir<[[LD]]> ; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds nuw ir<%B>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds nuw ir<[[GEP2]]> ; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[ADD]]>, vp<[[EVL]]> ; IF-EVL-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 ; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll index dff4971ffdfa1..642cd467c839f 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll @@ -40,11 +40,11 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; IF-EVL-OUTLOOP-NEXT: EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION ; IF-EVL-OUTLOOP-NEXT: EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI vp<[[EVL_PHI:%[0-9]+]]> = phi ir<0>, vp<[[IV_NEXT:%.+]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, vp<[[RDX_SELECT:%.+]]> -; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[AVL:%.+]]> = phi [ ir<%n>, vector.ph ], [ vp<[[AVL_NEXT:%.+]]>, vector.body ] +; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[AVL:%.+]]> = phi [ ir<%n>, vector.ph ], [ vp<[[AVL_NEXT:%.+]]>, vector.body ] ; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-OUTLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN-INTRINSIC vp<[[RDX_SELECT]]> = call llvm.vp.merge(ir<true>, ir<[[ADD]]>, ir<[[RDX_PHI]]>, vp<[[EVL]]>) @@ -84,7 +84,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; IF-EVL-INLOOP-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-INLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-INLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-INLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-INLOOP-NEXT: REDUCE ir<[[ADD:%.+]]> = ir<[[RDX_PHI]]> + vp.reduce.add (ir<[[LD1]]>, vp<[[EVL]]>) ; IF-EVL-INLOOP-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 @@ -121,7 +121,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; NO-VP-OUTLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, ir<[[RDX_NEXT:%.+]]> ; NO-VP-OUTLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]> ; NO-VP-OUTLOOP-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> @@ -169,7 +169,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; NO-VP-INLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, ir<[[RDX_NEXT:%.+]]> ; NO-VP-INLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-INLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-INLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-INLOOP-NEXT: REDUCE ir<[[ADD:%.+]]> = ir<[[RDX_PHI]]> + reduce.add (ir<[[LD1]]>) ; NO-VP-INLOOP-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll index b3a611eac72fc..3ab090ee46ab4 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll @@ -28,14 +28,14 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) { ; IF-EVL-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP2]]> ; IF-EVL-NEXT: WIDEN ir<[[LD2:%.+]]> = vp.load vp<[[PTR2]]>, vp<[[EVL]]> ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]> ; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]> +; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP3]]> ; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[ADD]]>, vp<[[EVL]]> ; IF-EVL-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 ; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]> @@ -59,14 +59,14 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) { ; NO-VP-NEXT: EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION ; NO-VP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; NO-VP-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP2]]> ; NO-VP-NEXT: WIDEN ir<[[LD2:%.+]]> = load vp<[[PTR2]]> ; NO-VP-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]> ; NO-VP-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]> +; NO-VP-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP3]]> ; NO-VP-NEXT: WIDEN store vp<[[PTR3]]>, ir<[[ADD]]> ; NO-VP-NEXT: EMIT vp<[[IV_NEXT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> ; NO-VP-NEXT: EMIT branch-on-count vp<[[IV_NEXT]]>, vp<[[VTC]]> diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll index 8536b3f0703cd..3c39a1d4e2463 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll @@ -14,7 +14,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst) ; CHECK: Cost of 0 for VF 2: ir<%iv> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<%0> ; CHECK: Cost of 0 for VF 2: vp<%4> = SCALAR-STEPS vp<%3>, ir<1> ; CHECK: Cost of 0 for VF 2: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4> -; CHECK: Cost of 0 for VF 2: vp<%5> = vector-pointer ir<%g.src> +; CHECK: Cost of 0 for VF 2: vp<%5> = vector-pointer inbounds ir<%g.src> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%l> = load vp<%5> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%iv.4> = add ir<%iv>, ir<4> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%c> = icmp ... [truncated] |
Member
| @llvm/pr-subscribers-vectorizers Author: Ramkumar Ramachandra (artagnon) ChangesThe change is non-functional with respect to emitted IR. Patch is 56.80 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/169466.diff 18 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp index 54fdec3bcf4a1..e41f67103e096 100644 --- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp +++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp @@ -2661,7 +2661,7 @@ void VPVectorPointerRecipe::printRecipe(raw_ostream &O, const Twine &Indent, O << Indent; printAsOperand(O, SlotTracker); O << " = vector-pointer "; - + printFlags(O); printOperands(O, SlotTracker); } #endif diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll index 444c6dd269425..9891617890625 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll @@ -76,7 +76,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: EMIT [[IV:.*]] = CANONICAL-INDUCTION ir<0>, [[IV_NEXT:.*]] ; CHECK-NEXT: [[STEPS:vp.*]] = SCALAR-STEPS [[IV]], ir<1>, [[VF]] ; CHECK-NEXT: CLONE [[GEP_IDX:.*]] = getelementptr inbounds ir<%indices>, [[STEPS]] -; CHECK-NEXT: [[VECP_IDX:vp.*]] = vector-pointer [[GEP_IDX]] +; CHECK-NEXT: [[VECP_IDX:vp.*]] = vector-pointer inbounds [[GEP_IDX]] ; CHECK-NEXT: WIDEN [[IDX:.*]] = load [[VECP_IDX]] ; CHECK-NEXT: WIDEN-CAST [[EXT_IDX:.*]] = zext [[IDX]] to i64 ; CHECK-NEXT: WIDEN-GEP Inv[Var] [[GEP_BUCKET:.*]] = getelementptr inbounds ir<%buckets>, [[EXT_IDX]] diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll index 6da3c77cd35c1..358c2aa3ed5cb 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll @@ -30,7 +30,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: REPLICATE ir<%call> = call @foo(ir<%load>) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -77,7 +77,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed4_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -129,7 +129,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed2_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXST:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -176,7 +176,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>, ir<true>) (using library function: foo_vector_fixed4_mask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -227,7 +227,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed2_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -274,7 +274,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed4_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll b/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll index 5999707699970..cf035d0b2b2ee 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll @@ -24,7 +24,7 @@ target triple = "arm64-apple-ios" ; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>, vp<[[VF]]> ; CHECK-NEXT: CLONE ir<%gep.src> = getelementptr inbounds ir<%src>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%gep.src> ; CHECK-NEXT: WIDEN ir<%l> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CAST ir<%conv> = fpext ir<%l> to double ; CHECK-NEXT: WIDEN-CALL ir<%s> = call fast @llvm.sin.f64(ir<%conv>) (using library function: __simd_sin_v2f64) @@ -71,7 +71,7 @@ target triple = "arm64-apple-ios" ; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>, vp<[[VF]]> ; CHECK-NEXT: CLONE ir<%gep.src> = getelementptr inbounds ir<%src>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%gep.src> ; CHECK-NEXT: WIDEN ir<%l> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CAST ir<%conv> = fpext ir<%l> to double ; CHECK-NEXT: WIDEN-INTRINSIC ir<%s> = call fast llvm.sin(ir<%conv>) diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll index 4416c0e780eff..64909a7c2fcec 100644 --- a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll @@ -25,7 +25,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 2: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 2: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 18 for VF 2: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 4 for VF 2: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 20 for VF 2: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> @@ -42,7 +42,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 4: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 4: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 2 for VF 4: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 0 for VF 4: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 2 for VF 4: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> @@ -59,7 +59,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 8: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 8: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 2 for VF 8: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 2 for VF 8: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 36 for VF 8: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll index ab4bb90b55b70..cc76ea04978a3 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll @@ -8,7 +8,7 @@ define void @first_order_recurrence(ptr noalias %A, ptr noalias %B, i64 %TC) { ; IF-EVL: VPlan 'Initial VPlan for VF={1},UF>=1' ; IF-EVL-NOT: EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI ; -; IF-EVL: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' { +; IF-EVL: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' { ; IF-EVL-NEXT: Live-in vp<[[VF:%[0-9]+]]> = VF ; IF-EVL-NEXT: Live-in vp<[[VFUF:%[0-9]+]]> = VF * UF ; IF-EVL-NEXT: Live-in vp<[[VTC:%[0-9]+]]> = vector-trip-count @@ -31,12 +31,12 @@ define void @first_order_recurrence(ptr noalias %A, ptr noalias %B, i64 %TC) { ; IF-EVL-NEXT: EMIT-SCALAR vp<[[EVL]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1> ; IF-EVL-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds nuw ir<%A>, vp<[[ST]] -; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds nuw ir<[[GEP1]]> ; IF-EVL-NEXT: WIDEN ir<[[LD]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[SPLICE:%[0-9]+]]> = call llvm.experimental.vp.splice(ir<[[FOR_PHI]]>, ir<[[LD]]>, ir<-1>, ir<true>, vp<[[PREV_EVL]]>, vp<[[EVL]]>) ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw vp<[[SPLICE]]>, ir<[[LD]]> ; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds nuw ir<%B>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds nuw ir<[[GEP2]]> ; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[ADD]]>, vp<[[EVL]]> ; IF-EVL-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 ; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll index dff4971ffdfa1..642cd467c839f 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll @@ -40,11 +40,11 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; IF-EVL-OUTLOOP-NEXT: EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION ; IF-EVL-OUTLOOP-NEXT: EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI vp<[[EVL_PHI:%[0-9]+]]> = phi ir<0>, vp<[[IV_NEXT:%.+]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, vp<[[RDX_SELECT:%.+]]> -; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[AVL:%.+]]> = phi [ ir<%n>, vector.ph ], [ vp<[[AVL_NEXT:%.+]]>, vector.body ] +; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[AVL:%.+]]> = phi [ ir<%n>, vector.ph ], [ vp<[[AVL_NEXT:%.+]]>, vector.body ] ; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-OUTLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN-INTRINSIC vp<[[RDX_SELECT]]> = call llvm.vp.merge(ir<true>, ir<[[ADD]]>, ir<[[RDX_PHI]]>, vp<[[EVL]]>) @@ -84,7 +84,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; IF-EVL-INLOOP-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-INLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-INLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-INLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-INLOOP-NEXT: REDUCE ir<[[ADD:%.+]]> = ir<[[RDX_PHI]]> + vp.reduce.add (ir<[[LD1]]>, vp<[[EVL]]>) ; IF-EVL-INLOOP-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 @@ -121,7 +121,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; NO-VP-OUTLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, ir<[[RDX_NEXT:%.+]]> ; NO-VP-OUTLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]> ; NO-VP-OUTLOOP-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> @@ -169,7 +169,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; NO-VP-INLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, ir<[[RDX_NEXT:%.+]]> ; NO-VP-INLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-INLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-INLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-INLOOP-NEXT: REDUCE ir<[[ADD:%.+]]> = ir<[[RDX_PHI]]> + reduce.add (ir<[[LD1]]>) ; NO-VP-INLOOP-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll index b3a611eac72fc..3ab090ee46ab4 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll @@ -28,14 +28,14 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) { ; IF-EVL-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP2]]> ; IF-EVL-NEXT: WIDEN ir<[[LD2:%.+]]> = vp.load vp<[[PTR2]]>, vp<[[EVL]]> ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]> ; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]> +; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP3]]> ; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[ADD]]>, vp<[[EVL]]> ; IF-EVL-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 ; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]> @@ -59,14 +59,14 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) { ; NO-VP-NEXT: EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION ; NO-VP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; NO-VP-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP2]]> ; NO-VP-NEXT: WIDEN ir<[[LD2:%.+]]> = load vp<[[PTR2]]> ; NO-VP-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]> ; NO-VP-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]> +; NO-VP-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP3]]> ; NO-VP-NEXT: WIDEN store vp<[[PTR3]]>, ir<[[ADD]]> ; NO-VP-NEXT: EMIT vp<[[IV_NEXT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> ; NO-VP-NEXT: EMIT branch-on-count vp<[[IV_NEXT]]>, vp<[[VTC]]> diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll index 8536b3f0703cd..3c39a1d4e2463 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll @@ -14,7 +14,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst) ; CHECK: Cost of 0 for VF 2: ir<%iv> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<%0> ; CHECK: Cost of 0 for VF 2: vp<%4> = SCALAR-STEPS vp<%3>, ir<1> ; CHECK: Cost of 0 for VF 2: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4> -; CHECK: Cost of 0 for VF 2: vp<%5> = vector-pointer ir<%g.src> +; CHECK: Cost of 0 for VF 2: vp<%5> = vector-pointer inbounds ir<%g.src> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%l> = load vp<%5> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%iv.4> = add ir<%iv>, ir<4> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%c> = icmp ... [truncated] |
Member
| @llvm/pr-subscribers-llvm-transforms Author: Ramkumar Ramachandra (artagnon) ChangesThe change is non-functional with respect to emitted IR. Patch is 56.80 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/169466.diff 18 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp index 54fdec3bcf4a1..e41f67103e096 100644 --- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp +++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp @@ -2661,7 +2661,7 @@ void VPVectorPointerRecipe::printRecipe(raw_ostream &O, const Twine &Indent, O << Indent; printAsOperand(O, SlotTracker); O << " = vector-pointer "; - + printFlags(O); printOperands(O, SlotTracker); } #endif diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll index 444c6dd269425..9891617890625 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll @@ -76,7 +76,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: EMIT [[IV:.*]] = CANONICAL-INDUCTION ir<0>, [[IV_NEXT:.*]] ; CHECK-NEXT: [[STEPS:vp.*]] = SCALAR-STEPS [[IV]], ir<1>, [[VF]] ; CHECK-NEXT: CLONE [[GEP_IDX:.*]] = getelementptr inbounds ir<%indices>, [[STEPS]] -; CHECK-NEXT: [[VECP_IDX:vp.*]] = vector-pointer [[GEP_IDX]] +; CHECK-NEXT: [[VECP_IDX:vp.*]] = vector-pointer inbounds [[GEP_IDX]] ; CHECK-NEXT: WIDEN [[IDX:.*]] = load [[VECP_IDX]] ; CHECK-NEXT: WIDEN-CAST [[EXT_IDX:.*]] = zext [[IDX]] to i64 ; CHECK-NEXT: WIDEN-GEP Inv[Var] [[GEP_BUCKET:.*]] = getelementptr inbounds ir<%buckets>, [[EXT_IDX]] diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll index 6da3c77cd35c1..358c2aa3ed5cb 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/synthesize-mask-for-call.ll @@ -30,7 +30,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: REPLICATE ir<%call> = call @foo(ir<%load>) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -77,7 +77,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed4_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -129,7 +129,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed2_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXST:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -176,7 +176,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>, ir<true>) (using library function: foo_vector_fixed4_mask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -227,7 +227,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed2_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> @@ -274,7 +274,7 @@ target triple = "aarch64-unknown-linux-gnu" ; CHECK-NEXT: WIDEN ir<%load> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CALL ir<%call> = call @foo(ir<%load>) (using library function: foo_vector_fixed4_nomask) ; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%a>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer ir<%arrayidx> +; CHECK-NEXT: vp<[[VEC_PTR2:%.+]]> = vector-pointer inbounds ir<%arrayidx> ; CHECK-NEXT: WIDEN store vp<[[VEC_PTR2]]>, ir<%call> ; CHECK-NEXT: EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]> ; CHECK-NEXT: EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]> diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll b/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll index 5999707699970..cf035d0b2b2ee 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll @@ -24,7 +24,7 @@ target triple = "arm64-apple-ios" ; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>, vp<[[VF]]> ; CHECK-NEXT: CLONE ir<%gep.src> = getelementptr inbounds ir<%src>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%gep.src> ; CHECK-NEXT: WIDEN ir<%l> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CAST ir<%conv> = fpext ir<%l> to double ; CHECK-NEXT: WIDEN-CALL ir<%s> = call fast @llvm.sin.f64(ir<%conv>) (using library function: __simd_sin_v2f64) @@ -71,7 +71,7 @@ target triple = "arm64-apple-ios" ; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION ; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[CAN_IV]]>, ir<1>, vp<[[VF]]> ; CHECK-NEXT: CLONE ir<%gep.src> = getelementptr inbounds ir<%src>, vp<[[STEPS]]> -; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src> +; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-pointer inbounds ir<%gep.src> ; CHECK-NEXT: WIDEN ir<%l> = load vp<[[VEC_PTR]]> ; CHECK-NEXT: WIDEN-CAST ir<%conv> = fpext ir<%l> to double ; CHECK-NEXT: WIDEN-INTRINSIC ir<%s> = call fast llvm.sin(ir<%conv>) diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll index 4416c0e780eff..64909a7c2fcec 100644 --- a/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-icmpcost.ll @@ -25,7 +25,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 2: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 2: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 2: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 18 for VF 2: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 4 for VF 2: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 20 for VF 2: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> @@ -42,7 +42,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 4: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 4: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 4: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 2 for VF 4: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 0 for VF 4: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 2 for VF 4: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> @@ -59,7 +59,7 @@ target triple = "thumbv8.1m.main-arm-none-eabi" ; CHECK: Cost of 0 for VF 8: EMIT vp<{{.+}}> = CANONICAL-INDUCTION ir<0>, vp<%index.next> ; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = SCALAR-STEPS vp<{{.+}}>, ir<1> ; CHECK: Cost of 0 for VF 8: CLONE ir<%arrayidx> = getelementptr inbounds ir<%s>, vp<{{.+}}> -; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = vector-pointer ir<%arrayidx> +; CHECK: Cost of 0 for VF 8: vp<{{.+}}> = vector-pointer inbounds ir<%arrayidx> ; CHECK: Cost of 2 for VF 8: WIDEN ir<%1> = load vp<{{.+}}> ; CHECK: Cost of 2 for VF 8: WIDEN-CAST ir<%conv> = sext ir<%1> to i32 ; CHECK: Cost of 36 for VF 8: WIDEN ir<%cmp2> = icmp sgt ir<%conv>, ir<%conv1> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll index ab4bb90b55b70..cc76ea04978a3 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-fixed-order-recurrence.ll @@ -8,7 +8,7 @@ define void @first_order_recurrence(ptr noalias %A, ptr noalias %B, i64 %TC) { ; IF-EVL: VPlan 'Initial VPlan for VF={1},UF>=1' ; IF-EVL-NOT: EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI ; -; IF-EVL: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' { +; IF-EVL: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF={1}' { ; IF-EVL-NEXT: Live-in vp<[[VF:%[0-9]+]]> = VF ; IF-EVL-NEXT: Live-in vp<[[VFUF:%[0-9]+]]> = VF * UF ; IF-EVL-NEXT: Live-in vp<[[VTC:%[0-9]+]]> = vector-trip-count @@ -31,12 +31,12 @@ define void @first_order_recurrence(ptr noalias %A, ptr noalias %B, i64 %TC) { ; IF-EVL-NEXT: EMIT-SCALAR vp<[[EVL]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1> ; IF-EVL-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds nuw ir<%A>, vp<[[ST]] -; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds nuw ir<[[GEP1]]> ; IF-EVL-NEXT: WIDEN ir<[[LD]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-NEXT: WIDEN-INTRINSIC vp<[[SPLICE:%[0-9]+]]> = call llvm.experimental.vp.splice(ir<[[FOR_PHI]]>, ir<[[LD]]>, ir<-1>, ir<true>, vp<[[PREV_EVL]]>, vp<[[EVL]]>) ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw vp<[[SPLICE]]>, ir<[[LD]]> ; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds nuw ir<%B>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds nuw ir<[[GEP2]]> ; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[ADD]]>, vp<[[EVL]]> ; IF-EVL-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 ; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll index dff4971ffdfa1..642cd467c839f 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics-reduction.ll @@ -40,11 +40,11 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; IF-EVL-OUTLOOP-NEXT: EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION ; IF-EVL-OUTLOOP-NEXT: EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI vp<[[EVL_PHI:%[0-9]+]]> = phi ir<0>, vp<[[IV_NEXT:%.+]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, vp<[[RDX_SELECT:%.+]]> -; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[AVL:%.+]]> = phi [ ir<%n>, vector.ph ], [ vp<[[AVL_NEXT:%.+]]>, vector.body ] +; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[AVL:%.+]]> = phi [ ir<%n>, vector.ph ], [ vp<[[AVL_NEXT:%.+]]>, vector.body ] ; IF-EVL-OUTLOOP-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-OUTLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]> ; IF-EVL-OUTLOOP-NEXT: WIDEN-INTRINSIC vp<[[RDX_SELECT]]> = call llvm.vp.merge(ir<true>, ir<[[ADD]]>, ir<[[RDX_PHI]]>, vp<[[EVL]]>) @@ -84,7 +84,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; IF-EVL-INLOOP-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-INLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-INLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-INLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-INLOOP-NEXT: REDUCE ir<[[ADD:%.+]]> = ir<[[RDX_PHI]]> + vp.reduce.add (ir<[[LD1]]>, vp<[[EVL]]>) ; IF-EVL-INLOOP-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 @@ -121,7 +121,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; NO-VP-OUTLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, ir<[[RDX_NEXT:%.+]]> ; NO-VP-OUTLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-OUTLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-OUTLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-OUTLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-OUTLOOP-NEXT: WIDEN ir<[[ADD:%.+]]> = add ir<[[LD1]]>, ir<[[RDX_PHI]]> ; NO-VP-OUTLOOP-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> @@ -169,7 +169,7 @@ define i32 @reduction(ptr %a, i64 %n, i32 %start) { ; NO-VP-INLOOP-NEXT: WIDEN-REDUCTION-PHI ir<[[RDX_PHI:%.+]]> = phi vp<[[RDX_START]]>, ir<[[RDX_NEXT:%.+]]> ; NO-VP-INLOOP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-INLOOP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-INLOOP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-INLOOP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-INLOOP-NEXT: REDUCE ir<[[ADD:%.+]]> = ir<[[RDX_PHI]]> + reduce.add (ir<[[LD1]]>) ; NO-VP-INLOOP-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll index b3a611eac72fc..3ab090ee46ab4 100644 --- a/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll +++ b/llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-intrinsics.ll @@ -28,14 +28,14 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) { ; IF-EVL-NEXT: EMIT-SCALAR vp<[[EVL:%.+]]> = EXPLICIT-VECTOR-LENGTH vp<[[AVL]]> ; IF-EVL-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[EVL_PHI]]>, ir<1>, vp<[[EVL]]> ; IF-EVL-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; IF-EVL-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; IF-EVL-NEXT: WIDEN ir<[[LD1:%.+]]> = vp.load vp<[[PTR1]]>, vp<[[EVL]]> ; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP2]]> ; IF-EVL-NEXT: WIDEN ir<[[LD2:%.+]]> = vp.load vp<[[PTR2]]>, vp<[[EVL]]> ; IF-EVL-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]> ; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]> +; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP3]]> ; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[ADD]]>, vp<[[EVL]]> ; IF-EVL-NEXT: EMIT-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64 ; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]> @@ -59,14 +59,14 @@ define void @foo(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) { ; NO-VP-NEXT: EMIT vp<[[IV:%[0-9]+]]> = CANONICAL-INDUCTION ; NO-VP-NEXT: vp<[[ST:%[0-9]+]]> = SCALAR-STEPS vp<[[IV]]>, ir<1>, vp<[[VF]]> ; NO-VP-NEXT: CLONE ir<[[GEP1:%.+]]> = getelementptr inbounds ir<%b>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer ir<[[GEP1]]> +; NO-VP-NEXT: vp<[[PTR1:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP1]]> ; NO-VP-NEXT: WIDEN ir<[[LD1:%.+]]> = load vp<[[PTR1]]> ; NO-VP-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%c>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]> +; NO-VP-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP2]]> ; NO-VP-NEXT: WIDEN ir<[[LD2:%.+]]> = load vp<[[PTR2]]> ; NO-VP-NEXT: WIDEN ir<[[ADD:%.+]]> = add nsw ir<[[LD2]]>, ir<[[LD1]]> ; NO-VP-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]> -; NO-VP-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]> +; NO-VP-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer inbounds ir<[[GEP3]]> ; NO-VP-NEXT: WIDEN store vp<[[PTR3]]>, ir<[[ADD]]> ; NO-VP-NEXT: EMIT vp<[[IV_NEXT:%.+]]> = add nuw vp<[[IV]]>, vp<[[VFUF]]> ; NO-VP-NEXT: EMIT branch-on-count vp<[[IV_NEXT]]>, vp<[[VTC]]> diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll index 8536b3f0703cd..3c39a1d4e2463 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/vpinstruction-cost.ll @@ -14,7 +14,7 @@ define void @wide_or_replaced_with_add_vpinstruction(ptr %src, ptr noalias %dst) ; CHECK: Cost of 0 for VF 2: ir<%iv> = WIDEN-INDUCTION nuw nsw ir<0>, ir<1>, vp<%0> ; CHECK: Cost of 0 for VF 2: vp<%4> = SCALAR-STEPS vp<%3>, ir<1> ; CHECK: Cost of 0 for VF 2: CLONE ir<%g.src> = getelementptr inbounds ir<%src>, vp<%4> -; CHECK: Cost of 0 for VF 2: vp<%5> = vector-pointer ir<%g.src> +; CHECK: Cost of 0 for VF 2: vp<%5> = vector-pointer inbounds ir<%g.src> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%l> = load vp<%5> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%iv.4> = add ir<%iv>, ir<4> ; CHECK: Cost of 1 for VF 2: WIDEN ir<%c> = icmp ... [truncated] |
artagnon changed the title 
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
The change is non-functional with respect to emitted IR.