mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 04:52:54 +02:00
65848e30b4
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 llvm-svn: 284757
77 lines
3.2 KiB
LLVM
77 lines
3.2 KiB
LLVM
; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s
|
|
; PHI elimination shouldn't break backedge.
|
|
; rdar://8263994
|
|
|
|
%struct.list_data_s = type { i16, i16 }
|
|
%struct.list_head = type { %struct.list_head*, %struct.list_data_s* }
|
|
|
|
define arm_apcscc %struct.list_head* @t1(%struct.list_head* %list) nounwind {
|
|
entry:
|
|
; CHECK-LABEL: t1:
|
|
%0 = icmp eq %struct.list_head* %list, null
|
|
br i1 %0, label %bb2, label %bb
|
|
|
|
bb:
|
|
; CHECK: LBB0_[[LABEL:[0-9]]]:
|
|
; CHECK: bne LBB0_[[LABEL]]
|
|
; CHECK-NOT: b LBB0_[[LABEL]]
|
|
; CHECK: bx lr
|
|
%list_addr.05 = phi %struct.list_head* [ %2, %bb ], [ %list, %entry ]
|
|
%next.04 = phi %struct.list_head* [ %list_addr.05, %bb ], [ null, %entry ]
|
|
%1 = getelementptr inbounds %struct.list_head, %struct.list_head* %list_addr.05, i32 0, i32 0
|
|
%2 = load %struct.list_head*, %struct.list_head** %1, align 4
|
|
store %struct.list_head* %next.04, %struct.list_head** %1, align 4
|
|
%3 = icmp eq %struct.list_head* %2, null
|
|
br i1 %3, label %bb2, label %bb
|
|
|
|
bb2:
|
|
%next.0.lcssa = phi %struct.list_head* [ null, %entry ], [ %list_addr.05, %bb ]
|
|
ret %struct.list_head* %next.0.lcssa
|
|
}
|
|
|
|
; Optimize loop entry, eliminate intra loop branches
|
|
; rdar://8117827
|
|
define i32 @t2(i32 %passes, i32* nocapture %src, i32 %size) nounwind readonly {
|
|
entry:
|
|
; CHECK-LABEL: t2:
|
|
%0 = icmp eq i32 %passes, 0 ; <i1> [#uses=1]
|
|
br i1 %0, label %bb5, label %bb.nph15
|
|
|
|
bb1: ; preds = %bb2.preheader, %bb1
|
|
; CHECK: LBB1_[[BB3:.]]: @ %bb3
|
|
; CHECK: LBB1_[[PREHDR:.]]: @ %bb2.preheader
|
|
; CHECK: blt LBB1_[[BB3]]
|
|
%indvar = phi i32 [ %indvar.next, %bb1 ], [ 0, %bb2.preheader ] ; <i32> [#uses=2]
|
|
%sum.08 = phi i32 [ %2, %bb1 ], [ %sum.110, %bb2.preheader ] ; <i32> [#uses=1]
|
|
%tmp17 = sub i32 %i.07, %indvar ; <i32> [#uses=1]
|
|
%scevgep = getelementptr i32, i32* %src, i32 %tmp17 ; <i32*> [#uses=1]
|
|
%1 = load i32, i32* %scevgep, align 4 ; <i32> [#uses=1]
|
|
%2 = add nsw i32 %1, %sum.08 ; <i32> [#uses=2]
|
|
%indvar.next = add i32 %indvar, 1 ; <i32> [#uses=2]
|
|
%exitcond = icmp eq i32 %indvar.next, %size ; <i1> [#uses=1]
|
|
br i1 %exitcond, label %bb3, label %bb1
|
|
|
|
bb3: ; preds = %bb1, %bb2.preheader
|
|
; CHECK: LBB1_[[BB1:.]]: @ %bb1
|
|
; CHECK: bne LBB1_[[BB1]]
|
|
; CHECK: b LBB1_[[BB3]]
|
|
%sum.0.lcssa = phi i32 [ %sum.110, %bb2.preheader ], [ %2, %bb1 ] ; <i32> [#uses=2]
|
|
%3 = add i32 %pass.011, 1 ; <i32> [#uses=2]
|
|
%exitcond18 = icmp eq i32 %3, %passes ; <i1> [#uses=1]
|
|
br i1 %exitcond18, label %bb5, label %bb2.preheader
|
|
|
|
bb.nph15: ; preds = %entry
|
|
%i.07 = add i32 %size, -1 ; <i32> [#uses=2]
|
|
%4 = icmp sgt i32 %i.07, -1 ; <i1> [#uses=1]
|
|
br label %bb2.preheader
|
|
|
|
bb2.preheader: ; preds = %bb3, %bb.nph15
|
|
%pass.011 = phi i32 [ 0, %bb.nph15 ], [ %3, %bb3 ] ; <i32> [#uses=1]
|
|
%sum.110 = phi i32 [ 0, %bb.nph15 ], [ %sum.0.lcssa, %bb3 ] ; <i32> [#uses=2]
|
|
br i1 %4, label %bb1, label %bb3
|
|
|
|
bb5: ; preds = %bb3, %entry
|
|
%sum.1.lcssa = phi i32 [ 0, %entry ], [ %sum.0.lcssa, %bb3 ] ; <i32> [#uses=1]
|
|
ret i32 %sum.1.lcssa
|
|
}
|