68469a80cb
This patch adds metadata to disable runtime unrolling to the vectorized loop. If runtime unrolling/interleaving is considered profitable, LV will interleave the loop directly. There should be no need to perform runtime unrolling at a later stage. Note that we already add metadata to disable runtime unrolling to the scalar loop after vectorization. The additional unrolling unnecessarily increases code size and compile time. In addition to that we have several bug reports of unncessary runtime unrolling for vectorized loops, e.g. PR40961 Compile-time improvements: NewPM-O3: -1.04% NewPM-ReleaseThinLTO: -0.59% NewPM-ReleaseLTO-g: -0.97% https://llvm-compile-time-tracker.com/compare.php?from=ce1be13a868d0f8afa367975558c1a6175cce33a&to=78bc2e67f22e9e10e61cdb6cdac4bb857d95eb1b&stat=instructions:u Fixes #40306. Reviewed By: lebedev.ri, nikic Differential Revision: https://reviews.llvm.org/D115261
45 lines
1.9 KiB
LLVM
45 lines
1.9 KiB
LLVM
; RUN: opt -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S < %s | FileCheck %s
|
|
;
|
|
; Check that the followup loop attributes are applied.
|
|
;
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
define void @followup(ptr nocapture %a, i32 %n) {
|
|
entry:
|
|
%cmp4 = icmp sgt i32 %n, 0
|
|
br i1 %cmp4, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
|
|
%0 = trunc i64 %indvars.iv to i32
|
|
store i32 %0, ptr %arrayidx, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %n
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!0 = distinct !{!0, !3, !4, !5}
|
|
!3 = !{!"llvm.loop.vectorize.followup_vectorized", !{!"FollowupVectorized"}}
|
|
!4 = !{!"llvm.loop.vectorize.followup_epilogue", !{!"FollowupEpilogue"}}
|
|
!5 = !{!"llvm.loop.vectorize.followup_all", !{!"FollowupAll"}}
|
|
|
|
|
|
; CHECK-LABEL: @followup(
|
|
|
|
; CHECK-LABEL: vector.body:
|
|
; CHECK: br i1 %{{[0-9]*}}, label %middle.block, label %vector.body, !llvm.loop ![[LOOP_VECTOR:[0-9]+]]
|
|
; CHECK-LABEL: for.body:
|
|
; CHECK: br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop ![[LOOP_EPILOGUE:[0-9]+]]
|
|
|
|
; CHECK: ![[LOOP_VECTOR]] = distinct !{![[LOOP_VECTOR]], ![[FOLLOWUP_ALL:[0-9]+]], ![[FOLLOWUP_VECTORIZED:[0-9]+]], ![[RT_UNROLL_DIS:[0-9]+]]}
|
|
; CHECK: ![[FOLLOWUP_ALL]] = !{!"FollowupAll"}
|
|
; CHECK: ![[FOLLOWUP_VECTORIZED:[0-9]+]] = !{!"FollowupVectorized"}
|
|
; CHECK: ![[RT_UNROLL_DIS]] = !{!"llvm.loop.unroll.runtime.disable"}
|
|
; CHECK: ![[LOOP_EPILOGUE]] = distinct !{![[LOOP_EPILOGUE]], ![[FOLLOWUP_ALL]], ![[FOLLOWUP_EPILOGUE:[0-9]+]]}
|
|
; CHECK: ![[FOLLOWUP_EPILOGUE]] = !{!"FollowupEpilogue"}
|