maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/ARM/ParallelDSP/aliasing.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

509 lines
19 KiB
LLVM
Raw Normal View History

[ARM][ParallelDSP] Relax alias checks When deciding the safety of generating smlad, we checked for any writes within the block that may alias with any of the loads that need to be widened. This is overly conservative because it only matters when there's a potential aliasing write to a location accessed by a pair of loads. Now we check for aliasing writes only once, during setup. If two loads are found to have an aliasing write between them, we don't add these loads to LoadPairs. This means that later during the transform, we can safely widened a pair without worrying about aliasing. However, to maintain correctness, we also need to change the way that wide loads are inserted because the order is now important. The MatchSMLAD method has also been changed, absorbing MatchReductions and AddMACCandidate to hopefully improve readability. Differential Revision: https://reviews.llvm.org/D6102 llvm-svn: 360567
2019-05-13 17:23:32 +08:00
; RUN: opt -mtriple=arm-arm-eabi -mcpu=cortex-m33 < %s -arm-parallel-dsp -verify -S | FileCheck %s
;
; Alias check: check that the rewrite isn't triggered when there's a store
; instruction possibly aliasing any mul load operands; arguments are passed
; without 'restrict' enabled.
;
; CHECK-NOT: call i32 @llvm.arm.smlad
;
define dso_local i32 @no_restrict(i32 %arg, i32* nocapture %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
; Store inserted here, aliasing with arrayidx, arrayidx1, arrayidx3
store i16 42, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; Alias check: check that the rewrite isn't triggered when there's a store
; aliasing one of the mul load operands. Arguments are now annotated with
; 'noalias'.
;
; CHECK-NOT: call i32 @llvm.arm.smlad
;
define dso_local i32 @restrict(i32 %arg, i32* noalias %arg1, i16* noalias readonly %arg2, i16* noalias readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
; Store inserted here, aliasing only with loads from 'arrayidx'.
store i16 42, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
; Here the Mul is the LHS, and the Add the RHS.
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_dominates_all
; CHECK: store
; CHECK: load
; CHECK: load
; CHECK: load
; CHECK: load
; CHECK: smlad
define dso_local i32 @store_dominates_all(i32 %arg, i32* nocapture %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
store i16 42, i16* %arrayidx, align 2
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: loads_dominate
; CHECK-NOT: store
; CHECK: load i32
; CHECK-NOT: store
; CHECK: load i32
; CHECK: store
define dso_local i32 @loads_dominate(i32 %arg, i32* nocapture %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
store i16 42, i16* %arrayidx, align 2
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_alias_arg3_legal_1
; CHECK-NOT: store
; CHECK: phi i32
; CHECK: [[IV:%[^ ]+]] = phi i32 [ %add
; CHECK: [[ARG3_GEP:%[^ ]+]] = getelementptr inbounds i16, i16* %arg3, i32 [[IV]]
; CHECK: [[ARG3:%[^ ]+]] = bitcast i16* [[ARG3_GEP]] to i32*
; CHECK: load i32, i32* [[ARG3]]
; CHECK: [[ARG2_GEP:%[^ ]+]] = getelementptr inbounds i16, i16* %arg2, i32 [[IV]]
; CHECK: [[ARG2:%[^ ]+]] = bitcast i16* [[ARG2_GEP]] to i32*
; CHECK: load i32, i32* [[ARG2]]
; CHECK: store
define dso_local i32 @store_alias_arg3_legal_1(i32 %arg, i32* nocapture %arg1, i16* noalias nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
store i16 42, i16* %arrayidx, align 2
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_alias_arg3_legal_2
; CHECK-NOT: store
; CHECK: [[BITCAST:[^ ]+]] = bitcast i16* %arrayidx to i32*
; CHECK: load i32, i32* [[BITCAST]]
; CHECK: store i16 42, i16* %arrayidx
; CHECK: [[BITCAST3:[^ ]+]] = bitcast i16* %arrayidx3 to i32*
; CHECK: load i32, i32* [[BITCAST3]]
; CHECK: smlad
define dso_local i32 @store_alias_arg3_legal_2(i32 %arg, i32* nocapture %arg1, i16* noalias nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
store i16 42, i16* %arrayidx, align 2
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_alias_arg3_illegal_1
; CHECK-NOT: load i32
define dso_local i32 @store_alias_arg3_illegal_1(i32 %arg, i32* nocapture %arg1, i16* noalias nocapture readonly %arg2, i16* noalias nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
store i16 42, i16* %arrayidx1, align 2
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_alias_arg3_illegal_2
; CHECK-NOT: load i32
define dso_local i32 @store_alias_arg3_illegal_2(i32 %arg, i32* nocapture %arg1, i16* noalias nocapture readonly %arg2, i16* noalias nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
store i16 42, i16* %arrayidx, align 2
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_alias_arg2_illegal_1
; CHECK-NOT: load i32
define dso_local i32 @store_alias_arg2_illegal_1(i32 %arg, i32* nocapture %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
store i16 42, i16* %arrayidx6, align 2
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
; CHECK-LABEL: store_alias_arg2_illegal_2
; CHECK-NOT: load i32
define dso_local i32 @store_alias_arg2_illegal_2(i32 %arg, i32* nocapture %arg1, i16* nocapture readonly %arg2, i16* nocapture readonly %arg3) {
entry:
%cmp24 = icmp sgt i32 %arg, 0
br i1 %cmp24, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%.pre = load i16, i16* %arg3, align 2
%.pre27 = load i16, i16* %arg2, align 2
br label %for.body
for.cond.cleanup:
%mac1.0.lcssa = phi i32 [ 0, %entry ], [ %add11, %for.body ]
ret i32 %mac1.0.lcssa
for.body:
%mac1.026 = phi i32 [ %add11, %for.body ], [ 0, %for.body.preheader ]
%i.025 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %arg3, i32 %i.025
%0 = load i16, i16* %arrayidx, align 2
%add = add nuw nsw i32 %i.025, 1
%arrayidx1 = getelementptr inbounds i16, i16* %arg3, i32 %add
%1 = load i16, i16* %arrayidx1, align 2
%arrayidx3 = getelementptr inbounds i16, i16* %arg2, i32 %i.025
%2 = load i16, i16* %arrayidx3, align 2
%conv = sext i16 %2 to i32
%conv4 = sext i16 %0 to i32
%mul = mul nsw i32 %conv, %conv4
%arrayidx6 = getelementptr inbounds i16, i16* %arg2, i32 %add
store i16 42, i16* %arrayidx3, align 2
%3 = load i16, i16* %arrayidx6, align 2
%conv7 = sext i16 %3 to i32
%conv8 = sext i16 %1 to i32
%mul9 = mul nsw i32 %conv7, %conv8
%add10 = add i32 %mul, %mac1.026
%add11 = add i32 %mul9, %add10
%exitcond = icmp ne i32 %add, %arg
br i1 %exitcond, label %for.body, label %for.cond.cleanup
}
[ARM][ParallelDSP] Change the search for smlads Two functional changes have been made here: - Now search up from any add instruction to find the chains of operations that we may turn into a smlad. This allows the generation of a smlad which doesn't accumulate into a phi. - The search function has been corrected to stop it falsely searching up through an invalid path. The bulk of the changes have been making the Reduction struct a class and making it more C++y with getters and setters. Differential Revision: https://reviews.llvm.org/D61780 llvm-svn: 365740
2019-07-11 15:47:50 +08:00
; TODO: I think we should be able to generate one smlad here. The search fails
; when it finds the alias.
[ARM][ParallelDSP] Relax alias checks When deciding the safety of generating smlad, we checked for any writes within the block that may alias with any of the loads that need to be widened. This is overly conservative because it only matters when there's a potential aliasing write to a location accessed by a pair of loads. Now we check for aliasing writes only once, during setup. If two loads are found to have an aliasing write between them, we don't add these loads to LoadPairs. This means that later during the transform, we can safely widened a pair without worrying about aliasing. However, to maintain correctness, we also need to change the way that wide loads are inserted because the order is now important. The MatchSMLAD method has also been changed, absorbing MatchReductions and AddMACCandidate to hopefully improve readability. Differential Revision: https://reviews.llvm.org/D6102 llvm-svn: 360567
2019-05-13 17:23:32 +08:00
; CHECK-LABEL: one_pair_alias
[ARM][ParallelDSP] Change the search for smlads Two functional changes have been made here: - Now search up from any add instruction to find the chains of operations that we may turn into a smlad. This allows the generation of a smlad which doesn't accumulate into a phi. - The search function has been corrected to stop it falsely searching up through an invalid path. The bulk of the changes have been making the Reduction struct a class and making it more C++y with getters and setters. Differential Revision: https://reviews.llvm.org/D61780 llvm-svn: 365740
2019-07-11 15:47:50 +08:00
; CHECK-NOT: call i32 @llvm.arm.smlad
[ARM][ParallelDSP] Relax alias checks When deciding the safety of generating smlad, we checked for any writes within the block that may alias with any of the loads that need to be widened. This is overly conservative because it only matters when there's a potential aliasing write to a location accessed by a pair of loads. Now we check for aliasing writes only once, during setup. If two loads are found to have an aliasing write between them, we don't add these loads to LoadPairs. This means that later during the transform, we can safely widened a pair without worrying about aliasing. However, to maintain correctness, we also need to change the way that wide loads are inserted because the order is now important. The MatchSMLAD method has also been changed, absorbing MatchReductions and AddMACCandidate to hopefully improve readability. Differential Revision: https://reviews.llvm.org/D6102 llvm-svn: 360567
2019-05-13 17:23:32 +08:00
define i32 @one_pair_alias(i16* noalias nocapture readonly %b, i16* noalias nocapture readonly %c) {
entry:
br label %for.body
for.cond.cleanup: ; preds = %for.body
ret i32 %add26
for.body: ; preds = %for.body, %entry
%i.050 = phi i32 [ 0, %entry ], [ %add27, %for.body ]
%a.049 = phi i32 [ 0, %entry ], [ %add26, %for.body ]
%add3 = or i32 %i.050, 1
%add11 = or i32 %i.050, 2
%add19 = or i32 %i.050, 3
%arrayidx = getelementptr inbounds i16, i16* %b, i32 %i.050
%arrayidx4 = getelementptr inbounds i16, i16* %b, i32 %add3
%arrayidx12 = getelementptr inbounds i16, i16* %b, i32 %add11
%arrayidx20 = getelementptr inbounds i16, i16* %b, i32 %add19
%arrayidx1 = getelementptr inbounds i16, i16* %c, i32 %i.050
%arrayidx7 = getelementptr inbounds i16, i16* %c, i32 %add3
%arrayidx15 = getelementptr inbounds i16, i16* %c, i32 %add11
%arrayidx23 = getelementptr inbounds i16, i16* %c, i32 %add19
%tmp = load i16, i16* %arrayidx, align 2
%tmp2 = load i16, i16* %arrayidx4, align 2
%tmp4 = load i16, i16* %arrayidx12, align 2
%tmp6 = load i16, i16* %arrayidx20, align 2
%tmp1 = load i16, i16* %arrayidx1, align 2
store i16 43, i16 *%arrayidx7
%tmp3 = load i16, i16* %arrayidx7, align 2
%tmp5 = load i16, i16* %arrayidx15, align 2
%tmp7 = load i16, i16* %arrayidx23, align 2
%conv = sext i16 %tmp to i32
%conv2 = sext i16 %tmp1 to i32
%mul = mul nsw i32 %conv2, %conv
%add = add nsw i32 %mul, %a.049
%conv5 = sext i16 %tmp2 to i32
%conv8 = sext i16 %tmp3 to i32
%mul9 = mul nsw i32 %conv8, %conv5
%add10 = add nsw i32 %add, %mul9
%conv13 = sext i16 %tmp4 to i32
%conv16 = sext i16 %tmp5 to i32
%mul17 = mul nsw i32 %conv16, %conv13
%add18 = add nsw i32 %add10, %mul17
%conv21 = sext i16 %tmp6 to i32
%conv24 = sext i16 %tmp7 to i32
%mul25 = mul nsw i32 %conv24, %conv21
%add26 = add nsw i32 %add18, %mul25
%add27 = add nuw nsw i32 %i.050, 4
%cmp = icmp ult i32 %add27, 100
br i1 %cmp, label %for.body, label %for.cond.cleanup
}