caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
c6c7bfc4d2bc37f55f57504c19d47deb7645dd76
clang-p2996/llvm/test/Transforms/LoopUnrollAndJam/dependencies.ll
David Green 963401d2be [UnrollAndJam] New Unroll and Jam pass 
This is a simple implementation of the unroll-and-jam classical loop
optimisation.

The basic idea is that we take an outer loop of the form:

  for i..
    ForeBlocks(i)
    for j..
      SubLoopBlocks(i, j)
    AftBlocks(i)

Instead of doing normal inner or outer unrolling, we unroll as follows:

  for i... i+=2
    ForeBlocks(i)
    ForeBlocks(i+1)
    for j..
      SubLoopBlocks(i, j)
      SubLoopBlocks(i+1, j)
    AftBlocks(i)
    AftBlocks(i+1)
  Remainder Loop

So we have unrolled the outer loop, then jammed the two inner loops into
one. This can lead to a simpler inner loop if memory accesses can be shared
between the now jammed loops.

To do this we have to prove that this is all safe, both for the memory
accesses (using dependence analysis) and that ForeBlocks(i+1) can move before
AftBlocks(i) and SubLoopBlocks(i, j).

Differential Revision: https://reviews.llvm.org/D41953

llvm-svn: 336062
2018-07-01 12:47:30 +00:00

471 lines
14 KiB
LLVM
Raw Blame History

; RUN: opt -basicaa -loop-unroll-and-jam -allow-unroll-and-jam -unroll-and-jam-count=4 < %s -S | FileCheck %s
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
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
}
Reference in New Issue View Git Blame Copy Permalink