mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 03:53:04 +02:00
3ee10fc280
Summary: Fixes a FIXME in MachineSinking. Instead of using the simple heuristics in isPostDominatedBy, use the real MachinePostDominatorTree and MachineLoopInfo. The old heuristics caused instructions to sink unnecessarily, and might create register pressure. This is the second try of the fix. The first one (D4814) caused a performance regression due to failing to sink instructions out of loops (PR21115). This patch fixes PR21115 by sinking an instruction from a deeper loop to a shallower one regardless of whether the target block post-dominates the source. Thanks Alexey Volkov for reporting PR21115! Test Plan: Added a NVPTX codegen test to verify that our change prevents the backend from over-sinking. It also shows the unnecessary register pressure caused by over-sinking. Added an X86 test to verify we can sink instructions out of loops regardless of the dominance relationship. This test is reduced from Alexey's test in PR21115. Updated an affected test in X86. Also ran SPEC CINT2006 and llvm-test-suite for compilation time and runtime performance. Results are attached separately in the review thread. Reviewers: Jiangning, resistor, hfinkel Reviewed By: hfinkel Subscribers: hfinkel, bruno, volkalexey, llvm-commits, meheff, eliben, jholewinski Differential Revision: http://reviews.llvm.org/D5633 llvm-svn: 219773
76 lines
2.0 KiB
LLVM
76 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=x86_64-apple-darwin < %s | FileCheck %s
|
|
|
|
; A MOV32ri is inside a loop, it has two successors, one successor is inside the
|
|
; same loop, the other successor is outside the loop. We should be able to sink
|
|
; MOV32ri outside the loop.
|
|
; rdar://11980766
|
|
define i32 @sink_succ(i32 %argc, i8** nocapture %argv) nounwind uwtable ssp {
|
|
; CHECK-LABEL: sink_succ
|
|
; CHECK: [[OUTER_LN1:LBB0_[0-9]+]]: ## %preheader
|
|
; CHECK: %exit
|
|
; CHECK-NOT: movl
|
|
; CHECK: jne [[OUTER_LN1]]
|
|
; CHECK: movl
|
|
; CHECK: [[LN2:LBB0_[0-9]+]]: ## %for.body2
|
|
; CHECK: jne [[LN2]]
|
|
; CHECK: ret
|
|
entry:
|
|
br label %preheader
|
|
|
|
preheader:
|
|
%i.127 = phi i32 [ 0, %entry ], [ %inc9, %exit ]
|
|
br label %for.body1.lr
|
|
|
|
for.body1.lr:
|
|
%iv30 = phi i32 [ 1, %preheader ], [ %iv.next31, %for.inc40.i ]
|
|
br label %for.body1
|
|
|
|
for.body1:
|
|
%iv.i = phi i64 [ 0, %for.body1.lr ], [ %iv.next.i, %for.body1 ]
|
|
%iv.next.i = add i64 %iv.i, 1
|
|
%lftr.wideiv32 = trunc i64 %iv.next.i to i32
|
|
%exitcond33 = icmp eq i32 %lftr.wideiv32, %iv30
|
|
br i1 %exitcond33, label %for.inc40.i, label %for.body1
|
|
|
|
for.inc40.i:
|
|
%iv.next31 = add i32 %iv30, 1
|
|
%exitcond49.i = icmp eq i32 %iv.next31, 32
|
|
br i1 %exitcond49.i, label %exit, label %for.body1.lr
|
|
|
|
exit:
|
|
%inc9 = add nsw i32 %i.127, 1
|
|
%exitcond34 = icmp eq i32 %inc9, 10
|
|
br i1 %exitcond34, label %for.body2, label %preheader
|
|
|
|
for.body2:
|
|
%iv = phi i64 [ %iv.next, %for.body2 ], [ 0, %exit ]
|
|
%iv.next = add i64 %iv, 1
|
|
%lftr.wideiv = trunc i64 %iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 2048
|
|
br i1 %exitcond, label %for.end20, label %for.body2
|
|
|
|
for.end20:
|
|
ret i32 0
|
|
}
|
|
|
|
define i32 @sink_out_of_loop(i32 %n, i32* %output) {
|
|
; CHECK-LABEL: sink_out_of_loop:
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i32 [ 0, %entry ], [ %i2, %loop ]
|
|
%j = mul i32 %i, %i
|
|
%addr = getelementptr i32* %output, i32 %i
|
|
store i32 %i, i32* %addr
|
|
%i2 = add i32 %i, 1
|
|
%exit_cond = icmp sge i32 %i2, %n
|
|
br i1 %exit_cond, label %exit, label %loop
|
|
|
|
exit:
|
|
; CHECK: BB#2
|
|
; CHECK: imull %eax, %eax
|
|
; CHECK: retq
|
|
ret i32 %j
|
|
}
|