shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
Philip Reames c416f6700f [IVDescriptors] Add pointer InductionDescriptors with non-constant strides (try 2) 
(JFYI - This has been heavily reframed since original attempt at landing.)

This change updates the InductionDescriptor logic to allow matching a pointer IV with a non-constant stride, but also updates the LoopVectorizer to bailout on such descriptors by default. This preserves the default vectorizer behavior.

In review, it was pointed out that there's multiple unfortunate performance implications which need to be addressed before this can be enabled. Having a flag allows us to exercise the behavior, and write test cases for logic which is otherwise unreachable (or hard to reach).

This will also enable non-constant stride pointer recurrences for other consumers. I've audited said code, and don't see any obvious issues.

Differential Revision: https://reviews.llvm.org/D147336
2023-04-05 09:32:35 -07:00

676 lines
39 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -S | FileCheck --check-prefixes=CHECK,NOSTRIDED %s
; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -lv-strided-pointer-ivs=true -S | FileCheck --check-prefixes=CHECK,STRIDED %s
define void @single_constant_stride_int_scaled(ptr %p) {
; CHECK-LABEL: @single_constant_stride_int_scaled(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ule 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]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i64 [[TMP3]], i64 [[N_MOD_VF]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[TMP5]]
; CHECK-NEXT: [[TMP6:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP7:%.*]] = add <vscale x 4 x i64> [[TMP6]], zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = mul <vscale x 4 x i64> [[TMP7]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP8]]
; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP10:%.*]] = mul i64 [[TMP9]], 4
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 1, [[TMP10]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 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 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP12:%.*]] = mul nuw nsw <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 8, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 4 x i64> [[TMP12]]
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP13]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32> poison)
; CHECK-NEXT: [[TMP14:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP14]], <vscale x 4 x ptr> [[TMP13]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
; CHECK-NEXT: [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP16:%.*]] = mul i64 [[TMP15]], 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP16]]
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 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 [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br 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: [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], 8
; CHECK-NEXT: [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; 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: [[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]
%offset = mul nsw nuw i64 %i, 8
%q0 = getelementptr i32, ptr %p, i64 %offset
%x0 = load i32, ptr %q0
%y0 = add i32 %x0, 1
store i32 %y0, 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 @single_constant_stride_int_iv(ptr %p) {
; CHECK-LABEL: @single_constant_stride_int_iv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; 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]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = mul i64 [[N_VEC]], 64
; CHECK-NEXT: [[TMP4:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP5:%.*]] = add <vscale x 4 x i64> [[TMP4]], zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = mul <vscale x 4 x i64> [[TMP5]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 64, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP6]]
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; CHECK-NEXT: [[TMP9:%.*]] = mul i64 64, [[TMP8]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP9]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 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 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 4 x i64> [[VEC_IND]]
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32> poison)
; CHECK-NEXT: [[TMP11:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP11]], <vscale x 4 x ptr> [[TMP10]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
; CHECK-NEXT: [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP13:%.*]] = mul i64 [[TMP12]], 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP13]]
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP14]], 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: [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[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: [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; 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: [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], 64
; 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]
%offset = phi i64 [0, %entry], [%offset.next, %loop]
%q0 = getelementptr i32, ptr %p, i64 %offset
%x0 = load i32, ptr %q0
%y0 = add i32 %x0, 1
store i32 %y0, ptr %q0
%offset.next = add nsw nuw i64 %offset, 64
%nexti = add i64 %i, 1
%done = icmp eq i64 %nexti, 1024
br i1 %done, label %exit, label %loop
exit:
ret void
}
define void @single_constant_stride_ptr_iv(ptr %p) {
; CHECK-LABEL: @single_constant_stride_ptr_iv(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 8128
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[POINTER_PHI:%.*]] = phi ptr [ [[P]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <8 x i64> <i64 0, i64 8, i64 16, i64 24, i64 32, i64 40, i64 48, i64 56>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <8 x ptr> [[TMP0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i32, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_VEC:%.*]] = load <16 x i32>, ptr [[TMP2]], align 4
; CHECK-NEXT: [[STRIDED_VEC:%.*]] = shufflevector <16 x i32> [[WIDE_VEC]], <16 x i32> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
; CHECK-NEXT: [[TMP3:%.*]] = add <8 x i32> [[STRIDED_VEC]], <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT: call void @llvm.masked.scatter.v8i32.v8p0(<8 x i32> [[TMP3]], <8 x ptr> [[TMP0]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 64
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1016
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 1016, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[BC_RESUME_VAL1:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P]], [[ENTRY]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[PTR:%.*]] = phi ptr [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; CHECK-NEXT: [[Y0:%.*]] = add i32 [[X0]], 1
; CHECK-NEXT: store i32 [[Y0]], ptr [[PTR]], align 4
; CHECK-NEXT: [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 8
; 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]
%ptr = phi ptr [%p, %entry], [%ptr.next, %loop]
%x0 = load i32, ptr %ptr
%y0 = add i32 %x0, 1
store i32 %y0, ptr %ptr
%ptr.next = getelementptr inbounds i8, ptr %ptr, i64 8
%nexti = add i64 %i, 1
%done = icmp eq i64 %nexti, 1024
br i1 %done, label %exit, label %loop
exit:
ret void
}
define void @single_stride_int_scaled(ptr %p, i64 %stride) {
; CHECK-LABEL: @single_stride_int_scaled(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
; CHECK-NEXT: br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP5:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP6:%.*]] = mul nuw nsw i64 [[TMP5]], [[STRIDE]]
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![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:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
; CHECK-NEXT: [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; 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: [[NEXTI]] = add i64 [[I]], 1
; CHECK-NEXT: [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
; CHECK-NEXT: br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%i = phi i64 [0, %entry], [%nexti, %loop]
%offset = mul nsw nuw i64 %i, %stride
%q0 = getelementptr i32, ptr %p, i64 %offset
%x0 = load i32, ptr %q0
%y0 = add i32 %x0, 1
store i32 %y0, 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 @single_stride_int_iv(ptr %p, i64 %stride) {
; CHECK-LABEL: @single_stride_int_iv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
; CHECK-NEXT: br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[STRIDE]]
; CHECK-NEXT: [[TMP5:%.*]] = mul i64 0, [[STRIDE]]
; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![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:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; 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: [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE]]
; 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 [[LOOP11:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%i = phi i64 [0, %entry], [%nexti, %loop]
%offset = phi i64 [0, %entry], [%offset.next, %loop]
%q0 = getelementptr i32, ptr %p, i64 %offset
%x0 = load i32, ptr %q0
%y0 = add i32 %x0, 1
store i32 %y0, ptr %q0
%offset.next = add nsw nuw i64 %offset, %stride
%nexti = add i64 %i, 1
%done = icmp eq i64 %nexti, 1024
br i1 %done, label %exit, label %loop
exit:
ret void
}
define void @single_stride_ptr_iv(ptr %p, i64 %stride) {
; CHECK-LABEL: @single_stride_ptr_iv(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[PTR:%.*]] = phi ptr [ [[P:%.*]], [[ENTRY]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; CHECK-NEXT: [[Y0:%.*]] = add i32 [[X0]], 1
; CHECK-NEXT: store i32 [[Y0]], ptr [[PTR]], align 4
; CHECK-NEXT: [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 [[STRIDE:%.*]]
; 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]
%ptr = phi ptr [%p, %entry], [%ptr.next, %loop]
%x0 = load i32, ptr %ptr
%y0 = add i32 %x0, 1
store i32 %y0, ptr %ptr
%ptr.next = getelementptr inbounds i8, ptr %ptr, i64 %stride
%nexti = add i64 %i, 1
%done = icmp eq i64 %nexti, 1024
br i1 %done, label %exit, label %loop
exit:
ret void
}
define void @double_stride_int_scaled(ptr %p, ptr %p2, i64 %stride) {
; CHECK-LABEL: @double_stride_int_scaled(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[P3:%.*]] = ptrtoint ptr [[P:%.*]] to i64
; CHECK-NEXT: [[P21:%.*]] = ptrtoint ptr [[P2:%.*]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 16, i64 [[TMP1]])
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
; CHECK-NEXT: br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; CHECK-NEXT: [[TMP6:%.*]] = sub i64 [[P21]], [[P3]]
; CHECK-NEXT: [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP6]], [[TMP5]]
; CHECK-NEXT: br i1 [[DIFF_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP8]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP9:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP10:%.*]] = mul nuw nsw i64 [[TMP9]], [[STRIDE]]
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr i32, ptr [[P]], i64 [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP12]], align 4
; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 4 x i32> [[WIDE_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr i32, ptr [[P2]], i64 [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr i32, ptr [[TMP14]], i32 0
; CHECK-NEXT: store <vscale x 4 x i32> [[TMP13]], ptr [[TMP15]], align 4
; CHECK-NEXT: [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP17:%.*]] = mul i64 [[TMP16]], 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP17]]
; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![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:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
; CHECK-NEXT: [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT: [[X0:%.*]] = load i32, ptr [[Q0]], align 4
; CHECK-NEXT: [[Y0:%.*]] = add i32 [[X0]], 1
; CHECK-NEXT: [[Q1:%.*]] = getelementptr i32, ptr [[P2]], i64 [[OFFSET]]
; CHECK-NEXT: store i32 [[Y0]], 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 [[LOOP13:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%i = phi i64 [0, %entry], [%nexti, %loop]
%offset = mul nsw nuw i64 %i, %stride
%q0 = getelementptr i32, ptr %p, i64 %offset
%x0 = load i32, ptr %q0
%y0 = add i32 %x0, 1
%q1 = getelementptr i32, ptr %p2, i64 %offset
store i32 %y0, 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 @double_stride_int_iv(ptr %p, ptr %p2, i64 %stride) {
; CHECK-LABEL: @double_stride_int_iv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
; CHECK-NEXT: br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[STRIDE]]
; CHECK-NEXT: [[TMP5:%.*]] = mul i64 0, [[STRIDE]]
; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![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:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT: [[X0:%.*]] = load i32, ptr [[Q0]], align 4
; CHECK-NEXT: [[Y0:%.*]] = add i32 [[X0]], 1
; CHECK-NEXT: [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT: store i32 [[Y0]], ptr [[Q1]], align 4
; CHECK-NEXT: [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE]]
; 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 [[LOOP15:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%i = phi i64 [0, %entry], [%nexti, %loop]
%offset = phi i64 [0, %entry], [%offset.next, %loop]
%q0 = getelementptr i32, ptr %p, i64 %offset
%x0 = load i32, ptr %q0
%y0 = add i32 %x0, 1
%q1 = getelementptr i32, ptr %p, i64 %offset
store i32 %y0, ptr %q1
%offset.next = add nsw nuw i64 %offset, %stride
%nexti = add i64 %i, 1
%done = icmp eq i64 %nexti, 1024
br i1 %done, label %exit, label %loop
exit:
ret void
}
define void @double_stride_ptr_iv(ptr %p, ptr %p2, i64 %stride) {
; NOSTRIDED-LABEL: @double_stride_ptr_iv(
; NOSTRIDED-NEXT: entry:
; NOSTRIDED-NEXT: br label [[LOOP:%.*]]
; NOSTRIDED: loop:
; NOSTRIDED-NEXT: [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; NOSTRIDED-NEXT: [[PTR:%.*]] = phi ptr [ [[P:%.*]], [[ENTRY]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; NOSTRIDED-NEXT: [[PTR2:%.*]] = phi ptr [ [[P2:%.*]], [[ENTRY]] ], [ [[PTR2_NEXT:%.*]], [[LOOP]] ]
; NOSTRIDED-NEXT: [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; NOSTRIDED-NEXT: [[Y0:%.*]] = add i32 [[X0]], 1
; NOSTRIDED-NEXT: store i32 [[Y0]], ptr [[PTR2]], align 4
; NOSTRIDED-NEXT: [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 [[STRIDE:%.*]]
; NOSTRIDED-NEXT: [[PTR2_NEXT]] = getelementptr inbounds i8, ptr [[PTR2]], i64 [[STRIDE]]
; NOSTRIDED-NEXT: [[NEXTI]] = add i64 [[I]], 1
; NOSTRIDED-NEXT: [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
; NOSTRIDED-NEXT: br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
; NOSTRIDED: exit:
; NOSTRIDED-NEXT: ret void
;
; STRIDED-LABEL: @double_stride_ptr_iv(
; STRIDED-NEXT: entry:
; STRIDED-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; STRIDED-NEXT: [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
; STRIDED-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
; STRIDED-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; STRIDED: vector.scevcheck:
; STRIDED-NEXT: [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
; STRIDED-NEXT: br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
; STRIDED: vector.memcheck:
; STRIDED-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P2:%.*]], i64 1027
; STRIDED-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 1027
; STRIDED-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[P2]], [[SCEVGEP1]]
; STRIDED-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[P]], [[SCEVGEP]]
; STRIDED-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; STRIDED-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; STRIDED: vector.ph:
; STRIDED-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
; STRIDED-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; STRIDED-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; STRIDED-NEXT: [[TMP5:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
; STRIDED-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP5]]
; STRIDED-NEXT: [[TMP6:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
; STRIDED-NEXT: [[IND_END3:%.*]] = getelementptr i8, ptr [[P2]], i64 [[TMP6]]
; STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; STRIDED: vector.body:
; STRIDED-NEXT: [[POINTER_PHI:%.*]] = phi ptr [ [[P]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
; STRIDED-NEXT: [[POINTER_PHI7:%.*]] = phi ptr [ [[P2]], [[VECTOR_PH]] ], [ [[PTR_IND8:%.*]], [[VECTOR_BODY]] ]
; STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; STRIDED-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; STRIDED-NEXT: [[TMP9:%.*]] = mul i64 [[TMP8]], 1
; STRIDED-NEXT: [[TMP10:%.*]] = mul i64 [[STRIDE]], [[TMP9]]
; STRIDED-NEXT: [[TMP11:%.*]] = mul i64 [[TMP8]], 0
; STRIDED-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
; STRIDED-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; STRIDED-NEXT: [[TMP12:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; STRIDED-NEXT: [[TMP13:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT]], [[TMP12]]
; STRIDED-NEXT: [[DOTSPLATINSERT5:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[STRIDE]], i64 0
; STRIDED-NEXT: [[DOTSPLAT6:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT5]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; STRIDED-NEXT: [[VECTOR_GEP:%.*]] = mul <vscale x 4 x i64> [[TMP13]], [[DOTSPLAT6]]
; STRIDED-NEXT: [[TMP14:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <vscale x 4 x i64> [[VECTOR_GEP]]
; STRIDED-NEXT: [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT: [[TMP16:%.*]] = mul i64 [[TMP15]], 4
; STRIDED-NEXT: [[TMP17:%.*]] = mul i64 [[TMP16]], 1
; STRIDED-NEXT: [[TMP18:%.*]] = mul i64 [[STRIDE]], [[TMP17]]
; STRIDED-NEXT: [[TMP19:%.*]] = mul i64 [[TMP16]], 0
; STRIDED-NEXT: [[DOTSPLATINSERT9:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP19]], i64 0
; STRIDED-NEXT: [[DOTSPLAT10:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT9]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; STRIDED-NEXT: [[TMP20:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; STRIDED-NEXT: [[TMP21:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT10]], [[TMP20]]
; STRIDED-NEXT: [[VECTOR_GEP13:%.*]] = mul <vscale x 4 x i64> [[TMP21]], [[DOTSPLAT6]]
; STRIDED-NEXT: [[TMP22:%.*]] = getelementptr i8, ptr [[POINTER_PHI7]], <vscale x 4 x i64> [[VECTOR_GEP13]]
; STRIDED-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP14]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32> poison), !alias.scope !16
; STRIDED-NEXT: [[TMP23:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; STRIDED-NEXT: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP23]], <vscale x 4 x ptr> [[TMP22]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)), !alias.scope !19, !noalias !16
; STRIDED-NEXT: [[TMP24:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT: [[TMP25:%.*]] = mul i64 [[TMP24]], 4
; STRIDED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP25]]
; STRIDED-NEXT: [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 [[TMP10]]
; STRIDED-NEXT: [[PTR_IND8]] = getelementptr i8, ptr [[POINTER_PHI7]], i64 [[TMP18]]
; STRIDED-NEXT: [[TMP26:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; STRIDED-NEXT: br i1 [[TMP26]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP21:![0-9]+]]
; STRIDED: middle.block:
; STRIDED-NEXT: [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
; STRIDED-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; STRIDED: scalar.ph:
; STRIDED-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; STRIDED-NEXT: [[BC_RESUME_VAL2:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P]], [[ENTRY]] ], [ [[P]], [[VECTOR_SCEVCHECK]] ], [ [[P]], [[VECTOR_MEMCHECK]] ]
; STRIDED-NEXT: [[BC_RESUME_VAL4:%.*]] = phi ptr [ [[IND_END3]], [[MIDDLE_BLOCK]] ], [ [[P2]], [[ENTRY]] ], [ [[P2]], [[VECTOR_SCEVCHECK]] ], [ [[P2]], [[VECTOR_MEMCHECK]] ]
; STRIDED-NEXT: br label [[LOOP:%.*]]
; STRIDED: loop:
; STRIDED-NEXT: [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; STRIDED-NEXT: [[PTR:%.*]] = phi ptr [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; STRIDED-NEXT: [[PTR2:%.*]] = phi ptr [ [[BC_RESUME_VAL4]], [[SCALAR_PH]] ], [ [[PTR2_NEXT:%.*]], [[LOOP]] ]
; STRIDED-NEXT: [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; STRIDED-NEXT: [[Y0:%.*]] = add i32 [[X0]], 1
; STRIDED-NEXT: store i32 [[Y0]], ptr [[PTR2]], align 4
; STRIDED-NEXT: [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 [[STRIDE]]
; STRIDED-NEXT: [[PTR2_NEXT]] = getelementptr inbounds i8, ptr [[PTR2]], i64 [[STRIDE]]
; STRIDED-NEXT: [[NEXTI]] = add i64 [[I]], 1
; STRIDED-NEXT: [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
; STRIDED-NEXT: br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP22:![0-9]+]]
; STRIDED: exit:
; STRIDED-NEXT: ret void
;
entry:
br label %loop
loop:
%i = phi i64 [0, %entry], [%nexti, %loop]
%ptr = phi ptr [%p, %entry], [%ptr.next, %loop]
%ptr2 = phi ptr [%p2, %entry], [%ptr2.next, %loop]
%x0 = load i32, ptr %ptr
%y0 = add i32 %x0, 1
store i32 %y0, ptr %ptr2
%ptr.next = getelementptr inbounds i8, ptr %ptr, i64 %stride
%ptr2.next = getelementptr inbounds i8, ptr %ptr2, i64 %stride
%nexti = add i64 %i, 1
%done = icmp eq i64 %nexti, 1024
br i1 %done, label %exit, label %loop
exit:
ret void
}
Reference in New Issue View Git Blame Copy Permalink