mirror of
https://github.com/RPCSX/llvm.git
synced 2025-01-27 07:12:06 +00:00
0872bb248f
Summary: The original heuristic to break critical edge during machine sink is relatively conservertive: when there is only one instruction sinkable to the critical edge, it is likely that the machine sink pass will not break the critical edge. This leads to many speculative instructions executed at runtime. However, with profile info, we could model the splitting benefits: if the critical edge has 50% taken rate, it would always be beneficial to split the critical edge to avoid the speculated runtime instructions. This patch uses profile to guide critical edge splitting in machine sink pass. The performance impact on speccpu2006 on Intel sandybridge machines: spec/2006/fp/C++/444.namd 25.3 +0.26% spec/2006/fp/C++/447.dealII 45.96 -0.10% spec/2006/fp/C++/450.soplex 41.97 +1.49% spec/2006/fp/C++/453.povray 36.83 -0.96% spec/2006/fp/C/433.milc 23.81 +0.32% spec/2006/fp/C/470.lbm 41.17 +0.34% spec/2006/fp/C/482.sphinx3 48.13 +0.69% spec/2006/int/C++/471.omnetpp 22.45 +3.25% spec/2006/int/C++/473.astar 21.35 -2.06% spec/2006/int/C++/483.xalancbmk 36.02 -2.39% spec/2006/int/C/400.perlbench 33.7 -0.17% spec/2006/int/C/401.bzip2 22.9 +0.52% spec/2006/int/C/403.gcc 32.42 -0.54% spec/2006/int/C/429.mcf 39.59 +0.19% spec/2006/int/C/445.gobmk 26.98 -0.00% spec/2006/int/C/456.hmmer 24.52 -0.18% spec/2006/int/C/458.sjeng 28.26 +0.02% spec/2006/int/C/462.libquantum 55.44 +3.74% spec/2006/int/C/464.h264ref 46.67 -0.39% geometric mean +0.20% Manually checked 473 and 471 to verify the diff is in the noise range. Reviewers: rengolin, davidxl Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D24818 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@284757 91177308-0d34-0410-b5e6-96231b3b80d8
67 lines
2.4 KiB
LLVM
67 lines
2.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s
|
|
|
|
; This test comes from PR27136
|
|
; We should hoist loop constant invariant
|
|
|
|
define zeroext i1 @search(i32 %needle, i32* nocapture readonly %haystack, i32 %count) {
|
|
; CHECK-LABEL: search:
|
|
; CHECK: ## BB#0: ## %entry
|
|
; CHECK-NEXT: testl %edx, %edx
|
|
; CHECK-NEXT: jle LBB0_1
|
|
; CHECK-NEXT: ## BB#4: ## %for.body.preheader
|
|
; CHECK-NEXT: movslq %edx, %rax
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: .p2align 4, 0x90
|
|
; CHECK-NEXT: LBB0_5: ## %for.body
|
|
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: cmpl %edi, (%rsi,%rcx,4)
|
|
; CHECK-NEXT: je LBB0_6
|
|
; CHECK-NEXT: ## BB#2: ## %for.cond
|
|
; CHECK-NEXT: ## in Loop: Header=BB0_5 Depth=1
|
|
; CHECK-NEXT: incq %rcx
|
|
; CHECK-NEXT: cmpq %rax, %rcx
|
|
; CHECK-NEXT: jl LBB0_5
|
|
; ### FIXME: BB#3 and LBB0_1 should be merged
|
|
; CHECK-NEXT: ## BB#3:
|
|
; CHECK-NEXT: xorl %eax, %eax
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: LBB0_1:
|
|
; CHECK-NEXT: xorl %eax, %eax
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: LBB0_6:
|
|
; CHECK-NEXT: movb $1, %al
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
;
|
|
entry:
|
|
%cmp5 = icmp sgt i32 %count, 0
|
|
br i1 %cmp5, label %for.body.preheader, label %cleanup
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
%0 = sext i32 %count to i64
|
|
br label %for.body
|
|
|
|
for.cond: ; preds = %for.body
|
|
%cmp = icmp slt i64 %indvars.iv.next, %0
|
|
br i1 %cmp, label %for.body, label %cleanup.loopexit
|
|
|
|
for.body: ; preds = %for.body.preheader, %for.cond
|
|
%indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.cond ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %haystack, i64 %indvars.iv
|
|
%1 = load i32, i32* %arrayidx, align 4
|
|
%cmp1 = icmp eq i32 %1, %needle
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
br i1 %cmp1, label %cleanup.loopexit, label %for.cond
|
|
|
|
cleanup.loopexit: ; preds = %for.cond, %for.body
|
|
%.ph = phi i1 [ false, %for.cond ], [ true, %for.body ]
|
|
br label %cleanup
|
|
|
|
cleanup: ; preds = %cleanup.loopexit, %entry
|
|
%2 = phi i1 [ false, %entry ], [ %.ph, %cleanup.loopexit ]
|
|
ret i1 %2
|
|
}
|