caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
be1294de9dd93ae02002bd1aa4b4a8d62e562c21
clang-p2996/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter.ll
Florian Hahn 95f76bff1c [LV] Create & use VPScalarIVSteps for all scalar users. 
This patch is a follow-up to D115953. It updates optimizeInductions
to also introduce new VPScalarIVStepsRecipes if an IV has both vector
and scalar uses.

It updates all uses that only need scalar values to use the newly
created recipe for the scalar steps.

This completes untangling of VPWidenIntOrFpInductionRecipe
code-generation. Now the recipe *only* creates the widened vector
values, as it says on the tin.

The code to genereate IR has been moved directly to
VPWidenIntOrFpInductionRecipe::execute.

Note that the recipe has been updated to hold a reference to
ScalarEvolution, which is needed to expand the step, until we can place
the corresponding SCEV expansion in the pre-header.

Depends on D120827.

Reviewed By: Ayal

Differential Revision: https://reviews.llvm.org/D120828
2022-03-13 17:15:24 +00:00

382 lines
24 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -force-target-instruction-cost=1 -o - | FileCheck %s
define void @gather_nxv4i32_ind64(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) #0 {
; CHECK-LABEL: @gather_nxv4i32_ind64(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; 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:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i64* [[TMP4]] to <vscale x 4 x i64>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i64>, <vscale x 4 x i64>* [[TMP5]], align 8
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds float, float* [[A:%.*]], <vscale x 4 x i64> [[WIDE_LOAD]]
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> [[TMP6]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float> undef)
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds float, float* [[C:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP8:%.*]] = bitcast float* [[TMP7]] to <vscale x 4 x float>*
; CHECK-NEXT: store <vscale x 4 x float> [[WIDE_MASKED_GATHER]], <vscale x 4 x float>* [[TMP8]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP10:%.*]] = shl nuw nsw i64 [[TMP9]], 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP12:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP13:%.*]] = load float, float* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[C]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store float [[TMP13]], float* [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i64, i64* %b, i64 %indvars.iv
%0 = load i64, i64* %arrayidx, align 8
%arrayidx3 = getelementptr inbounds float, float* %a, i64 %0
%1 = load float, float* %arrayidx3, align 4
%arrayidx5 = getelementptr inbounds float, float* %c, i64 %indvars.iv
store float %1, float* %arrayidx5, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !0
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
; NOTE: I deliberately chose '%b' as an array of i32 indices, since the
; additional 'sext' in the for.body loop exposes additional code paths
; during vectorisation.
define void @scatter_nxv4i32_ind32(float* noalias nocapture %a, i32* noalias nocapture readonly %b, float* noalias nocapture readonly %c, i64 %n) #0 {
; CHECK-LABEL: @scatter_nxv4i32_ind32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; 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:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, float* [[C:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast float* [[TMP4]] to <vscale x 4 x float>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, <vscale x 4 x float>* [[TMP5]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <vscale x 4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[TMP7]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = sext <vscale x 4 x i32> [[WIDE_LOAD1]] to <vscale x 4 x i64>
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds float, float* [[A:%.*]], <vscale x 4 x i64> [[TMP8]]
; CHECK-NEXT: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x float*> [[TMP9]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 2
; 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 [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[C]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP13:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP14:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[IDXPROM4:%.*]] = sext i32 [[TMP14]] to i64
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[IDXPROM4]]
; CHECK-NEXT: store float [[TMP13]], float* [[ARRAYIDX5]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %c, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%1 = load i32, i32* %arrayidx3, align 4
%idxprom4 = sext i32 %1 to i64
%arrayidx5 = getelementptr inbounds float, float* %a, i64 %idxprom4
store float %0, float* %arrayidx5, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !0
for.cond.cleanup: ; preds = %for.body, %entry
ret void
}
define void @scatter_inv_nxv4i32(i32* noalias nocapture %inv, i32* noalias nocapture readonly %b, i64 %n) #0 {
; CHECK-LABEL: @scatter_inv_nxv4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; 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:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[INV:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32*> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32*> 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: [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <vscale x 4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[TMP5]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = icmp ne <vscale x 4 x i32> [[WIDE_LOAD]], zeroinitializer
; CHECK-NEXT: call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 3, i32 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i32*> [[BROADCAST_SPLAT]], i32 4, <vscale x 4 x i1> [[TMP6]])
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw nsw i64 [[TMP7]], 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP8]]
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP10:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP10]], 0
; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label [[FOR_INC]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: store i32 3, i32* [[INV]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%tobool.not = icmp eq i32 %0, 0
br i1 %tobool.not, label %for.inc, label %if.then
if.then: ; preds = %for.body
store i32 3, i32* %inv, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !0
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
define void @gather_inv_nxv4i32(i32* noalias nocapture %a, i32* noalias nocapture readonly %inv, i64 %n) #0 {
; CHECK-LABEL: @gather_inv_nxv4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; 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:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[INV:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32*> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32*> 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: [[TMP4:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <vscale x 4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[TMP5]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = icmp sgt <vscale x 4 x i32> [[WIDE_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 3, i32 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[BROADCAST_SPLAT]], i32 4, <vscale x 4 x i1> [[TMP6]], <vscale x 4 x i32> undef)
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[TMP4]] to <vscale x 4 x i32>*
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32>* [[TMP7]], i32 4, <vscale x 4 x i1> [[TMP6]])
; CHECK-NEXT: [[TMP8:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP9:%.*]] = shl nuw nsw i64 [[TMP8]], 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP11:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP2:%.*]] = icmp sgt i32 [[TMP11]], 3
; CHECK-NEXT: br i1 [[CMP2]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP12:%.*]] = load i32, i32* [[INV]], align 4
; CHECK-NEXT: store i32 [[TMP12]], i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp2 = icmp sgt i32 %0, 3
br i1 %cmp2, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %inv, align 4
store i32 %1, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !0
for.cond.cleanup: ; preds = %for.inc, %entry
ret void
}
define void @gather_nxv4i32_ind64_stride2(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 {
; CHECK-LABEL: @gather_nxv4i32_ind64_stride2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 3
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw nsw i64 [[TMP2]], 3
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP4:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP6:%.*]] = shl nuw nsw i64 [[TMP5]], 2
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP6]], 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> [ [[TMP4]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[STEP_ADD:%.*]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT: [[TMP7:%.*]] = shl <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP8:%.*]] = shl <vscale x 4 x i64> [[STEP_ADD]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds float, float* [[B:%.*]], <vscale x 4 x i64> [[TMP7]]
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds float, float* [[B]], <vscale x 4 x i64> [[TMP8]]
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> [[TMP9]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float> undef)
; CHECK-NEXT: [[WIDE_MASKED_GATHER2:%.*]] = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> [[TMP10]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x float> undef)
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP12:%.*]] = bitcast float* [[TMP11]] to <vscale x 4 x float>*
; CHECK-NEXT: store <vscale x 4 x float> [[WIDE_MASKED_GATHER]], <vscale x 4 x float>* [[TMP12]], align 4
; CHECK-NEXT: [[TMP13:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw i32 [[TMP13]], 2
; CHECK-NEXT: [[TMP15:%.*]] = zext i32 [[TMP14]] to i64
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds float, float* [[TMP11]], i64 [[TMP15]]
; CHECK-NEXT: [[TMP17:%.*]] = bitcast float* [[TMP16]] to <vscale x 4 x float>*
; CHECK-NEXT: store <vscale x 4 x float> [[WIDE_MASKED_GATHER2]], <vscale x 4 x float>* [[TMP17]], align 4
; CHECK-NEXT: [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw i64 [[TMP18]], 3
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP19]]
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[STEP_ADD]], [[DOTSPLAT]]
; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[INDVARS_IV_STRIDE2:%.*]] = shl i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[INDVARS_IV_STRIDE2]]
; CHECK-NEXT: [[TMP21:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store float [[TMP21]], float* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%indvars.iv.stride2 = mul i64 %indvars.iv, 2
%arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv.stride2
%0 = load float, float* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %indvars.iv
store float %0, float* %arrayidx2, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
attributes #0 = { vscale_range(1, 16) }
!0 = distinct !{!0, !1, !2, !3, !4, !5}
!1 = !{!"llvm.loop.mustprogress"}
!2 = !{!"llvm.loop.vectorize.width", i32 4}
!3 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
!4 = !{!"llvm.loop.interleave.count", i32 1}
!5 = !{!"llvm.loop.vectorize.enable", i1 true}
Reference in New Issue View Git Blame Copy Permalink