maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopUnrollAndJam/dependencies.ll

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

474 lines
14 KiB
LLVM
Raw Normal View History

Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
; RUN: opt -basicaa -loop-unroll-and-jam -allow-unroll-and-jam -unroll-and-jam-count=4 < %s -S | FileCheck %s
[NFCI][LoopUnrollAndJam] Changing LoopUnrollAndJamPass to a function pass. Summary: This patch changes LoopUnrollAndJamPass to a function pass, and keeps the loops traversal order same as defined in FunctionToLoopPassAdaptor LoopPassManager.h. The next patch will change the loop traversal to outer to inner order, so more loops can be transform. Discussion in llvm-dev mailing list: https://groups.google.com/forum/#!topic/llvm-dev/LF4rUjkVI2g Reviewer: dmgreen, jdoerfert, Meinersbur, kbarton, bmahjour, etiotto Reviewed By: dmgreen Subscribers: hiraditya, zzheng, llvm-commits Tag: LLVM Differential Revision: https://reviews.llvm.org/D72230
2020-01-10 00:15:53 +08:00
; RUN: opt -aa-pipeline=basic-aa -passes='unroll-and-jam' -allow-unroll-and-jam -unroll-and-jam-count=4 < %s -S | FileCheck %s
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
; CHECK-LABEL: fore_aft_less
; CHECK: %j = phi
; CHECK: %j.1 = phi
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
define void @fore_aft_less(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%add72 = add nuw nsw i32 %i, -1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: fore_aft_eq
; CHECK: %j = phi
; CHECK: %j.1 = phi
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
define void @fore_aft_eq(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%add72 = add nuw nsw i32 %i, 0
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %i
store i32 %add, i32* %arrayidx8, align 4
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: fore_aft_more
; CHECK: %j = phi
; CHECK-NOT: %j.1 = phi
define void @fore_aft_more(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%add72 = add nuw nsw i32 %i, 1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: fore_sub_less
; CHECK: %j = phi
; CHECK: %j.1 = phi
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
define void @fore_sub_less(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add72 = add nuw nsw i32 %i, -1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%add6 = add nuw nsw i32 %j, 1
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: fore_sub_eq
; CHECK: %j = phi
; CHECK: %j.1 = phi
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
define void @fore_sub_eq(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add72 = add nuw nsw i32 %i, 0
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%add6 = add nuw nsw i32 %j, 1
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: fore_sub_more
; CHECK: %j = phi
; CHECK-NOT: %j.1 = phi
define void @fore_sub_more(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add72 = add nuw nsw i32 %i, 1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%add6 = add nuw nsw i32 %j, 1
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: sub_aft_less
; CHECK: %j = phi
; CHECK: %j.1 = phi
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
define void @sub_aft_less(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%add72 = add nuw nsw i32 %i, -1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: sub_aft_eq
; CHECK: %j = phi
; CHECK: %j.1 = phi
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
define void @sub_aft_eq(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%add72 = add nuw nsw i32 %i, 0
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %i
store i32 %add, i32* %arrayidx8, align 4
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: sub_aft_more
; CHECK: %j = phi
; CHECK-NOT: %j.1 = phi
define void @sub_aft_more(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%add72 = add nuw nsw i32 %i, 1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: sub_sub_less
; CHECK: %j = phi
; CHECK-NOT: %j.1 = phi
define void @sub_sub_less(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
%add72 = add nuw nsw i32 %i, -1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: sub_sub_eq
; CHECK: %j = phi
; CHECK: %j.1 = phi
[LoopUnrollAndJam] Changed safety checks to consider more than 2-levels loop nest. Summary: As discussed in https://reviews.llvm.org/D73129. Example Before unroll and jam: for A for B for C D E After unroll and jam (currently): for A A' for B for C D B' for C' D' E E' After unroll and jam (Ideal): for A A' for B B' for C C' D D' E E' This is the first patch to change unroll and jam to work in the ideal way. This patch change the safety checks needed to make sure is safe to unroll and jam in the ideal way. Reviewer: dmgreen, jdoerfert, Meinersbur, kbarton, bmahjour, etiotto Reviewed By: Meinersbur Subscribers: fhahn, hiraditya, zzheng, llvm-commits, anhtuyen, prithayan Tag: LLVM Differential Revision: https://reviews.llvm.org/D76132
2020-05-07 05:42:47 +08:00
; CHECK: %j.2 = phi
; CHECK: %j.3 = phi
Revert "Temporarily Revert "Add basic loop fusion pass."" The reversion apparently deleted the test/Transforms directory. Will be re-reverting again. llvm-svn: 358552
2019-04-17 12:52:47 +08:00
define void @sub_sub_eq(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
%add72 = add nuw nsw i32 %i, 0
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}
; CHECK-LABEL: sub_sub_more
; CHECK: %j = phi
; CHECK-NOT: %j.1 = phi
define void @sub_sub_more(i32* noalias nocapture %A, i32 %N, i32* noalias nocapture readonly %B) {
entry:
%cmp = icmp sgt i32 %N, 0
br i1 %cmp, label %for.outer, label %cleanup
for.outer:
%i = phi i32 [ %add7, %for.latch ], [ 0, %entry ]
br label %for.inner
for.inner:
%j = phi i32 [ %add6, %for.inner ], [ 0, %for.outer ]
%sum = phi i32 [ %add, %for.inner ], [ 0, %for.outer ]
%arrayidx5 = getelementptr inbounds i32, i32* %B, i32 %j
%0 = load i32, i32* %arrayidx5, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add6 = add nuw nsw i32 %j, 1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i
store i32 1, i32* %arrayidx, align 4
%add72 = add nuw nsw i32 %i, 1
%arrayidx8 = getelementptr inbounds i32, i32* %A, i32 %add72
store i32 %add, i32* %arrayidx8, align 4
%exitcond = icmp eq i32 %add6, %N
br i1 %exitcond, label %for.latch, label %for.inner
for.latch:
%add7 = add nuw nsw i32 %i, 1
%exitcond29 = icmp eq i32 %add7, %N
br i1 %exitcond29, label %cleanup, label %for.outer
cleanup:
ret void
}