mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 20:23:11 +01:00
3f021fa672
This patch marks the induction increment of the main induction variable of the vector loop as NUW when not folding the tail. If the tail is not folded, we know that End - Start >= Step (either statically or through the minimum iteration checks). We also know that both Start % Step == 0 and End % Step == 0. We exit the vector loop if %IV + %Step == %End. Hence we must exit the loop before %IV + %Step unsigned overflows and we can mark the induction increment as NUW. This should make SCEV return more precise bounds for the created vector loops, used by later optimizations, like late unrolling. At the moment quite a few tests still need to be updated, but before doing so I'd like to get initial feedback to make sure I am not missing anything. Note that this could probably be further improved by using information from the original IV. Attempt of modeling of the assumption in Alive2: https://alive2.llvm.org/ce/z/H_DL_g Part of a set of fixes required for PR50412. Reviewed By: mkazantsev Differential Revision: https://reviews.llvm.org/D103255
83 lines
3.8 KiB
LLVM
83 lines
3.8 KiB
LLVM
; extern int arr[8][8];
|
|
; extern int arr2[8];
|
|
;
|
|
; void foo(int n)
|
|
; {
|
|
; int i1, i2;
|
|
;
|
|
; #pragma clang loop vectorize(enable) vectorize_width(4)
|
|
; for (i1 = 0; i1 < 8; i1++) {
|
|
; arr2[i1] = i1;
|
|
; for (i2 = 0; i2 < 8; i2++)
|
|
; arr[i2][i1] = i1 + n;
|
|
; }
|
|
; }
|
|
;
|
|
; RUN: opt -S -loop-vectorize -enable-vplan-native-path < %s | FileCheck %s
|
|
; CHECK-LABEL: vector.ph:
|
|
; CHECK: %[[SplatVal:.*]] = insertelement <4 x i32> poison, i32 %n, i32 0
|
|
; CHECK: %[[Splat:.*]] = shufflevector <4 x i32> %[[SplatVal]], <4 x i32> poison, <4 x i32> zeroinitializer
|
|
|
|
; CHECK-LABEL: vector.body:
|
|
; CHECK: %[[Ind:.*]] = phi i64 [ 0, %vector.ph ], [ %[[IndNext:.*]], %[[ForInc:.*]] ]
|
|
; CHECK: %[[VecInd:.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %vector.ph ], [ %[[VecIndNext:.*]], %[[ForInc]] ]
|
|
; CHECK: %[[AAddr:.*]] = getelementptr inbounds [8 x i32], [8 x i32]* @arr2, i64 0, <4 x i64> %[[VecInd]]
|
|
; CHECK: %[[VecIndTr:.*]] = trunc <4 x i64> %[[VecInd]] to <4 x i32>
|
|
; CHECK: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %[[VecIndTr]], <4 x i32*> %[[AAddr]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
|
|
; CHECK: %[[VecIndTr2:.*]] = trunc <4 x i64> %[[VecInd]] to <4 x i32>
|
|
; CHECK: %[[StoreVal:.*]] = add nsw <4 x i32> %[[VecIndTr2]], %[[Splat]]
|
|
; CHECK: br label %[[InnerLoop:.+]]
|
|
|
|
; CHECK: [[InnerLoop]]:
|
|
; CHECK: %[[InnerPhi:.*]] = phi <4 x i64> [ zeroinitializer, %vector.body ], [ %[[InnerPhiNext:.*]], %[[InnerLoop]] ]
|
|
; CHECK: %[[AAddr2:.*]] = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* @arr, i64 0, <4 x i64> %[[InnerPhi]], <4 x i64> %[[VecInd]]
|
|
; CHECK: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %[[StoreVal]], <4 x i32*> %[[AAddr2]], i32 4, <4 x i1> <i1 true, i1 true, i1 true
|
|
; CHECK: %[[InnerPhiNext]] = add nuw nsw <4 x i64> %[[InnerPhi]], <i64 1, i64 1, i64 1, i64 1>
|
|
; CHECK: %[[VecCond:.*]] = icmp eq <4 x i64> %[[InnerPhiNext]], <i64 8, i64 8, i64 8, i64 8>
|
|
; CHECK: %[[InnerCond:.*]] = extractelement <4 x i1> %[[VecCond]], i32 0
|
|
; CHECK: br i1 %[[InnerCond]], label %[[ForInc]], label %[[InnerLoop]]
|
|
|
|
; CHECK: [[ForInc]]:
|
|
; CHECK: %[[IndNext]] = add nuw i64 %[[Ind]], 4
|
|
; CHECK: %[[VecIndNext]] = add <4 x i64> %[[VecInd]], <i64 4, i64 4, i64 4, i64 4>
|
|
; CHECK: %[[Cmp:.*]] = icmp eq i64 %[[IndNext]], 8
|
|
; CHECK: br i1 %[[Cmp]], label %middle.block, label %vector.body
|
|
|
|
@arr2 = external global [8 x i32], align 16
|
|
@arr = external global [8 x [8 x i32]], align 16
|
|
|
|
; Function Attrs: norecurse nounwind uwtable
|
|
define void @foo(i32 %n) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.inc8, %entry
|
|
%indvars.iv21 = phi i64 [ 0, %entry ], [ %indvars.iv.next22, %for.inc8 ]
|
|
%arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* @arr2, i64 0, i64 %indvars.iv21
|
|
%0 = trunc i64 %indvars.iv21 to i32
|
|
store i32 %0, i32* %arrayidx, align 4
|
|
%1 = trunc i64 %indvars.iv21 to i32
|
|
%add = add nsw i32 %1, %n
|
|
br label %for.body3
|
|
|
|
for.body3: ; preds = %for.body3, %for.body
|
|
%indvars.iv = phi i64 [ 0, %for.body ], [ %indvars.iv.next, %for.body3 ]
|
|
%arrayidx7 = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* @arr, i64 0, i64 %indvars.iv, i64 %indvars.iv21
|
|
store i32 %add, i32* %arrayidx7, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 8
|
|
br i1 %exitcond, label %for.inc8, label %for.body3
|
|
|
|
for.inc8: ; preds = %for.body3
|
|
%indvars.iv.next22 = add nuw nsw i64 %indvars.iv21, 1
|
|
%exitcond23 = icmp eq i64 %indvars.iv.next22, 8
|
|
br i1 %exitcond23, label %for.end10, label %for.body, !llvm.loop !1
|
|
|
|
for.end10: ; preds = %for.inc8
|
|
ret void
|
|
}
|
|
|
|
!1 = distinct !{!1, !2, !3}
|
|
!2 = !{!"llvm.loop.vectorize.width", i32 4}
|
|
!3 = !{!"llvm.loop.vectorize.enable", i1 true}
|