Revert r284545 again as the regression in ppc still exists. There is bug in MBPI exposed by th patch.

Also update the section.ll to fix non-x86 failure.

llvm-svn: 284563
This commit is contained in:
Dehao Chen 2016-10-19 01:18:25 +00:00
parent 490fda3366
commit 95fc43143d
11 changed files with 134 additions and 192 deletions

View File

@ -24,7 +24,6 @@
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
#include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
@ -61,15 +60,6 @@ UseBlockFreqInfo("machine-sink-bfi",
cl::desc("Use block frequency info to find successors to sink"),
cl::init(true), cl::Hidden);
static cl::opt<unsigned> SplitEdgeProbabilityThreshold(
"machine-sink-split-probability-threshold",
cl::desc(
"Percentage threshold for splitting single-instruction critical edge. "
"If the branch threshold is higher than this threshold, we allow "
"speculative execution of up to 1 instruction to avoid branching to "
"splitted critical edge"),
cl::init(40), cl::Hidden);
STATISTIC(NumSunk, "Number of machine instructions sunk");
STATISTIC(NumSplit, "Number of critical edges split");
STATISTIC(NumCoalesces, "Number of copies coalesced");
@ -84,7 +74,6 @@ namespace {
MachinePostDominatorTree *PDT; // Machine post dominator tree
MachineLoopInfo *LI;
const MachineBlockFrequencyInfo *MBFI;
const MachineBranchProbabilityInfo *MBPI;
AliasAnalysis *AA;
// Remember which edges have been considered for breaking.
@ -116,7 +105,6 @@ namespace {
AU.addRequired<MachineDominatorTree>();
AU.addRequired<MachinePostDominatorTree>();
AU.addRequired<MachineLoopInfo>();
AU.addRequired<MachineBranchProbabilityInfo>();
AU.addPreserved<MachineDominatorTree>();
AU.addPreserved<MachinePostDominatorTree>();
AU.addPreserved<MachineLoopInfo>();
@ -175,7 +163,6 @@ char MachineSinking::ID = 0;
char &llvm::MachineSinkingID = MachineSinking::ID;
INITIALIZE_PASS_BEGIN(MachineSinking, "machine-sink",
"Machine code sinking", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
@ -296,7 +283,6 @@ bool MachineSinking::runOnMachineFunction(MachineFunction &MF) {
PDT = &getAnalysis<MachinePostDominatorTree>();
LI = &getAnalysis<MachineLoopInfo>();
MBFI = UseBlockFreqInfo ? &getAnalysis<MachineBlockFrequencyInfo>() : nullptr;
MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
bool EverMadeChange = false;
@ -397,10 +383,6 @@ bool MachineSinking::isWorthBreakingCriticalEdge(MachineInstr &MI,
if (!MI.isCopy() && !TII->isAsCheapAsAMove(MI))
return true;
if (MBPI->getEdgeProbability(From, To) <=
BranchProbability(SplitEdgeProbabilityThreshold, 100))
return true;
// MI is cheap, we probably don't want to break the critical edge for it.
// However, if this would allow some definitions of its source operands
// to be sunk then it's probably worth it.

View File

@ -38,14 +38,16 @@ entry:
; CHECK-ARMV6-NEXT: uxtb [[DESIRED:r[0-9]+]], r1
; CHECK-ARMV6-NEXT: [[TRY:.LBB[0-9_]+]]:
; CHECK-ARMV6-NEXT: ldrexb [[LD:r[0-9]+]], [r0]
; CHECK-ARMV6-NEXT: mov [[RES:r[0-9]+]], #0
; CHECK-ARMV6-NEXT: cmp [[LD]], [[DESIRED]]
; CHECK-ARMV6-NEXT: movne [[RES:r[0-9]+]], #0
; CHECK-ARMV6-NEXT: bxne lr
; CHECK-ARMV6-NEXT: bne [[END:.LBB[0-9_]+]]
; CHECK-ARMV6-NEXT: strexb [[SUCCESS:r[0-9]+]], r2, [r0]
; CHECK-ARMV6-NEXT: mov [[RES]], #1
; CHECK-ARMV6-NEXT: cmp [[SUCCESS]], #0
; CHECK-ARMV6-NEXT: moveq [[RES]], #1
; CHECK-ARMV6-NEXT: bxeq lr
; CHECK-ARMV6-NEXT: b [[TRY]]
; CHECK-ARMV6-NEXT: bne [[TRY]]
; CHECK-ARMV6-NEXT: [[END]]:
; CHECK-ARMV6-NEXT: mov r0, [[RES]]
; CHECK-ARMV6-NEXT: bx lr
; CHECK-THUMBV6-LABEL: test_cmpxchg_res_i8:
; CHECK-THUMBV6: mov [[EXPECTED:r[0-9]+]], r1
@ -62,18 +64,20 @@ entry:
; CHECK-ARMV7-LABEL: test_cmpxchg_res_i8:
; CHECK-ARMV7-NEXT: .fnstart
; CHECK-ARMV7-NEXT: uxtb [[DESIRED:r[0-9]+]], r1
; CHECK-ARMV7-NEXT: b [[TRY:.LBB[0-9_]+]]
; CHECK-ARMV7-NEXT: [[HEAD:.LBB[0-9_]+]]:
; CHECK-ARMV7-NEXT: strexb [[SUCCESS:r[0-9]+]], r2, [r0]
; CHECK-ARMV7-NEXT: cmp [[SUCCESS]], #0
; CHECK-ARMV7-NEXT: moveq [[RES:r[0-9]+]], #1
; CHECK-ARMV7-NEXT: bxeq lr
; CHECK-ARMV7-NEXT: [[TRY]]:
; CHECK-ARMV7-NEXT: [[TRY:.LBB[0-9_]+]]:
; CHECK-ARMV7-NEXT: ldrexb [[LD:r[0-9]+]], [r0]
; CHECK-ARMV7-NEXT: cmp [[LD]], [[DESIRED]]
; CHECK-ARMV7-NEXT: beq [[HEAD]]
; CHECK-ARMV7-NEXT: bne [[FAIL:.LBB[0-9_]+]]
; CHECK-ARMV7-NEXT: strexb [[SUCCESS:r[0-9]+]], r2, [r0]
; CHECK-ARMV7-NEXT: mov [[RES:r[0-9]+]], #1
; CHECK-ARMV7-NEXT: cmp [[SUCCESS]], #0
; CHECK-ARMV7-NEXT: bne [[TRY]]
; CHECK-ARMV7-NEXT: b [[END:.LBB[0-9_]+]]
; CHECK-ARMV7-NEXT: [[FAIL]]:
; CHECK-ARMV7-NEXT: clrex
; CHECK-ARMV7-NEXT: mov [[RES]], #0
; CHECK-ARMV7-NEXT: [[END]]:
; CHECK-ARMV7-NEXT: mov r0, [[RES]]
; CHECK-ARMV7-NEXT: bx lr
; CHECK-THUMBV7-LABEL: test_cmpxchg_res_i8:

View File

@ -12,9 +12,9 @@ entry:
br i1 %0, label %bb2, label %bb
bb:
; CHECK: LBB0_[[LABEL:[0-9]]]:
; CHECK: bne LBB0_[[LABEL]]
; CHECK-NOT: b LBB0_[[LABEL]]
; CHECK: LBB0_2:
; CHECK: bne LBB0_2
; CHECK-NOT: b LBB0_2
; 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 ]
@ -34,13 +34,14 @@ bb2:
define i32 @t2(i32 %passes, i32* nocapture %src, i32 %size) nounwind readonly {
entry:
; CHECK-LABEL: t2:
; CHECK: beq LBB1_[[RET:.]]
%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]]
bb1: ; preds = %bb2.preheader, %bb1
; CHECK: LBB1_[[BB1:.]]: @ %bb1
; CHECK: bne LBB1_[[BB1]]
%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]
@ -52,9 +53,9 @@ bb1: ; preds = %bb2.preheader, %bb1
br i1 %exitcond, label %bb3, label %bb1
bb3: ; preds = %bb1, %bb2.preheader
; CHECK: LBB1_[[BB1:.]]: @ %bb1
; CHECK: bne LBB1_[[BB1]]
; CHECK: b LBB1_[[BB3]]
; CHECK: LBB1_[[BB3:.]]: @ %bb3
; CHECK: bne LBB1_[[PREHDR]]
; CHECK-NOT: b LBB1_
%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]
@ -70,6 +71,8 @@ bb2.preheader: ; preds = %bb3, %bb.nph15
%sum.110 = phi i32 [ 0, %bb.nph15 ], [ %sum.0.lcssa, %bb3 ] ; <i32> [#uses=2]
br i1 %4, label %bb1, label %bb3
; CHECK: LBB1_[[RET]]: @ %bb5
; CHECK: pop
bb5: ; preds = %bb3, %entry
%sum.1.lcssa = phi i32 [ 0, %entry ], [ %sum.0.lcssa, %bb3 ] ; <i32> [#uses=1]
ret i32 %sum.1.lcssa

View File

@ -478,12 +478,12 @@ define void @fpcmp_unanalyzable_branch(i1 %cond) {
; CHECK-LABEL: fpcmp_unanalyzable_branch:
; CHECK: # BB#0: # %entry
; CHECK: # BB#1: # %entry.if.then_crit_edge
; CHECK: .LBB10_5: # %if.then
; CHECK: .LBB10_6: # %if.end
; CHECK: .LBB10_4: # %if.then
; CHECK: .LBB10_5: # %if.end
; CHECK: # BB#3: # %exit
; CHECK: jne .LBB10_4
; CHECK-NEXT: jnp .LBB10_6
; CHECK: jmp .LBB10_5
; CHECK-NEXT: jnp .LBB10_5
; CHECK-NEXT: jmp .LBB10_4
entry:
; Note that this branch must be strongly biased toward

View File

@ -279,32 +279,28 @@ define i64 @ctlz_i64(i64 %x) {
define i8 @ctlz_i8_zero_test(i8 %n) {
; X32-LABEL: ctlz_i8_zero_test:
; X32: # BB#0:
; X32-NEXT: movb {{[0-9]+}}(%esp), %al
; X32-NEXT: testb %al, %al
; X32-NEXT: je .LBB8_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: movzbl %al, %eax
; X32-NEXT: movb {{[0-9]+}}(%esp), %cl
; X32-NEXT: movb $8, %al
; X32-NEXT: testb %cl, %cl
; X32-NEXT: je .LBB8_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: movzbl %cl, %eax
; X32-NEXT: bsrl %eax, %eax
; X32-NEXT: xorl $7, %eax
; X32-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X32-NEXT: retl
; X32-NEXT: .LBB8_1:
; X32-NEXT: movb $8, %al
; X32-NEXT: .LBB8_2: # %cond.end
; X32-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X32-NEXT: retl
;
; X64-LABEL: ctlz_i8_zero_test:
; X64: # BB#0:
; X64-NEXT: movb $8, %al
; X64-NEXT: testb %dil, %dil
; X64-NEXT: je .LBB8_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: je .LBB8_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: movzbl %dil, %eax
; X64-NEXT: bsrl %eax, %eax
; X64-NEXT: xorl $7, %eax
; X64-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X64-NEXT: retq
; X64-NEXT: .LBB8_1:
; X64-NEXT: movb $8, %al
; X64-NEXT: .LBB8_2: # %cond.end
; X64-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X64-NEXT: retq
;
@ -331,30 +327,26 @@ define i8 @ctlz_i8_zero_test(i8 %n) {
define i16 @ctlz_i16_zero_test(i16 %n) {
; X32-LABEL: ctlz_i16_zero_test:
; X32: # BB#0:
; X32-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X32-NEXT: testw %ax, %ax
; X32-NEXT: je .LBB9_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: bsrw %ax, %ax
; X32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movw $16, %ax
; X32-NEXT: testw %cx, %cx
; X32-NEXT: je .LBB9_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: bsrw %cx, %ax
; X32-NEXT: xorl $15, %eax
; X32-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
; X32-NEXT: retl
; X32-NEXT: .LBB9_1:
; X32-NEXT: movw $16, %ax
; X32-NEXT: .LBB9_2: # %cond.end
; X32-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
; X32-NEXT: retl
;
; X64-LABEL: ctlz_i16_zero_test:
; X64: # BB#0:
; X64-NEXT: movw $16, %ax
; X64-NEXT: testw %di, %di
; X64-NEXT: je .LBB9_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: je .LBB9_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: bsrw %di, %ax
; X64-NEXT: xorl $15, %eax
; X64-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
; X64-NEXT: retq
; X64-NEXT: .LBB9_1:
; X64-NEXT: movw $16, %ax
; X64-NEXT: .LBB9_2: # %cond.end
; X64-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
; X64-NEXT: retq
;
@ -375,27 +367,25 @@ define i16 @ctlz_i16_zero_test(i16 %n) {
define i32 @ctlz_i32_zero_test(i32 %n) {
; X32-LABEL: ctlz_i32_zero_test:
; X32: # BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: testl %eax, %eax
; X32-NEXT: je .LBB10_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: bsrl %eax, %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl $32, %eax
; X32-NEXT: testl %ecx, %ecx
; X32-NEXT: je .LBB10_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: bsrl %ecx, %eax
; X32-NEXT: xorl $31, %eax
; X32-NEXT: retl
; X32-NEXT: .LBB10_1:
; X32-NEXT: movl $32, %eax
; X32-NEXT: .LBB10_2: # %cond.end
; X32-NEXT: retl
;
; X64-LABEL: ctlz_i32_zero_test:
; X64: # BB#0:
; X64-NEXT: movl $32, %eax
; X64-NEXT: testl %edi, %edi
; X64-NEXT: je .LBB10_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: je .LBB10_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: bsrl %edi, %eax
; X64-NEXT: xorl $31, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB10_1:
; X64-NEXT: movl $32, %eax
; X64-NEXT: .LBB10_2: # %cond.end
; X64-NEXT: retq
;
; X32-CLZ-LABEL: ctlz_i32_zero_test:
@ -474,30 +464,26 @@ define i64 @ctlz_i64_zero_test(i64 %n) {
define i8 @cttz_i8_zero_test(i8 %n) {
; X32-LABEL: cttz_i8_zero_test:
; X32: # BB#0:
; X32-NEXT: movb {{[0-9]+}}(%esp), %al
; X32-NEXT: testb %al, %al
; X32-NEXT: je .LBB12_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: movzbl %al, %eax
; X32-NEXT: bsfl %eax, %eax
; X32-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X32-NEXT: retl
; X32-NEXT: .LBB12_1
; X32-NEXT: movb {{[0-9]+}}(%esp), %cl
; X32-NEXT: movb $8, %al
; X32-NEXT: testb %cl, %cl
; X32-NEXT: je .LBB12_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: movzbl %cl, %eax
; X32-NEXT: bsfl %eax, %eax
; X32-NEXT: .LBB12_2: # %cond.end
; X32-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X32-NEXT: retl
;
; X64-LABEL: cttz_i8_zero_test:
; X64: # BB#0:
; X64-NEXT: movb $8, %al
; X64-NEXT: testb %dil, %dil
; X64-NEXT: je .LBB12_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: je .LBB12_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: movzbl %dil, %eax
; X64-NEXT: bsfl %eax, %eax
; X64-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X64-NEXT: retq
; X64-NEXT: .LBB12_1:
; X64-NEXT: movb $8, %al
; X64-NEXT: .LBB12_2: # %cond.end
; X64-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
; X64-NEXT: retq
;
@ -524,25 +510,23 @@ define i8 @cttz_i8_zero_test(i8 %n) {
define i16 @cttz_i16_zero_test(i16 %n) {
; X32-LABEL: cttz_i16_zero_test:
; X32: # BB#0:
; X32-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X32-NEXT: testw %ax, %ax
; X32-NEXT: je .LBB13_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: bsfw %ax, %ax
; X32-NEXT: retl
; X32-NEXT: .LBB13_1
; X32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movw $16, %ax
; X32-NEXT: testw %cx, %cx
; X32-NEXT: je .LBB13_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: bsfw %cx, %ax
; X32-NEXT: .LBB13_2: # %cond.end
; X32-NEXT: retl
;
; X64-LABEL: cttz_i16_zero_test:
; X64: # BB#0:
; X64-NEXT: testw %di, %di
; X64-NEXT: je .LBB13_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: bsfw %di, %ax
; X64-NEXT: retq
; X64-NEXT: .LBB13_1:
; X64-NEXT: movw $16, %ax
; X64-NEXT: testw %di, %di
; X64-NEXT: je .LBB13_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: bsfw %di, %ax
; X64-NEXT: .LBB13_2: # %cond.end
; X64-NEXT: retq
;
; X32-CLZ-LABEL: cttz_i16_zero_test:
@ -562,25 +546,23 @@ define i16 @cttz_i16_zero_test(i16 %n) {
define i32 @cttz_i32_zero_test(i32 %n) {
; X32-LABEL: cttz_i32_zero_test:
; X32: # BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: testl %eax, %eax
; X32-NEXT: je .LBB14_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: bsfl %eax, %eax
; X32-NEXT: retl
; X32-NEXT: .LBB14_1
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl $32, %eax
; X32-NEXT: testl %ecx, %ecx
; X32-NEXT: je .LBB14_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: bsfl %ecx, %eax
; X32-NEXT: .LBB14_2: # %cond.end
; X32-NEXT: retl
;
; X64-LABEL: cttz_i32_zero_test:
; X64: # BB#0:
; X64-NEXT: testl %edi, %edi
; X64-NEXT: je .LBB14_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: bsfl %edi, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB14_1:
; X64-NEXT: movl $32, %eax
; X64-NEXT: testl %edi, %edi
; X64-NEXT: je .LBB14_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: bsfl %edi, %eax
; X64-NEXT: .LBB14_2: # %cond.end
; X64-NEXT: retq
;
; X32-CLZ-LABEL: cttz_i32_zero_test:
@ -660,27 +642,25 @@ define i64 @cttz_i64_zero_test(i64 %n) {
define i32 @ctlz_i32_fold_cmov(i32 %n) {
; X32-LABEL: ctlz_i32_fold_cmov:
; X32: # BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: orl $1, %eax
; X32-NEXT: je .LBB16_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: bsrl %eax, %eax
; X32-NEXT: xorl $31, %eax
; X32-NEXT: retl
; X32-NEXT: .LBB16_1
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: orl $1, %ecx
; X32-NEXT: movl $32, %eax
; X32-NEXT: je .LBB16_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: bsrl %ecx, %eax
; X32-NEXT: xorl $31, %eax
; X32-NEXT: .LBB16_2: # %cond.end
; X32-NEXT: retl
;
; X64-LABEL: ctlz_i32_fold_cmov:
; X64: # BB#0:
; X64-NEXT: orl $1, %edi
; X64-NEXT: je .LBB16_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: movl $32, %eax
; X64-NEXT: je .LBB16_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: bsrl %edi, %eax
; X64-NEXT: xorl $31, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB16_1:
; X64-NEXT: movl $32, %eax
; X64-NEXT: .LBB16_2: # %cond.end
; X64-NEXT: retq
;
; X32-CLZ-LABEL: ctlz_i32_fold_cmov:
@ -736,30 +716,26 @@ define i32 @ctlz_bsr(i32 %n) {
define i32 @ctlz_bsr_zero_test(i32 %n) {
; X32-LABEL: ctlz_bsr_zero_test:
; X32: # BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: testl %eax, %eax
; X32-NEXT: je .LBB18_1
; X32-NEXT: # BB#2: # %cond.false
; X32-NEXT: bsrl %eax, %eax
; X32-NEXT: xorl $31, %eax
; X32-NEXT: xorl $31, %eax
; X32-NEXT: retl
; X32-NEXT: .LBB18_1:
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl $32, %eax
; X32-NEXT: testl %ecx, %ecx
; X32-NEXT: je .LBB18_2
; X32-NEXT: # BB#1: # %cond.false
; X32-NEXT: bsrl %ecx, %eax
; X32-NEXT: xorl $31, %eax
; X32-NEXT: .LBB18_2: # %cond.end
; X32-NEXT: xorl $31, %eax
; X32-NEXT: retl
;
; X64-LABEL: ctlz_bsr_zero_test:
; X64: # BB#0:
; X64-NEXT: movl $32, %eax
; X64-NEXT: testl %edi, %edi
; X64-NEXT: je .LBB18_1
; X64-NEXT: # BB#2: # %cond.false
; X64-NEXT: je .LBB18_2
; X64-NEXT: # BB#1: # %cond.false
; X64-NEXT: bsrl %edi, %eax
; X64-NEXT: xorl $31, %eax
; X64-NEXT: xorl $31, %eax
; X64-NEXT: retq
; X64-NEXT: .LBB18_1:
; X64-NEXT: movl $32, %eax
; X64-NEXT: .LBB18_2: # %cond.end
; X64-NEXT: xorl $31, %eax
; X64-NEXT: retq
;

View File

@ -10,17 +10,19 @@ define zeroext i1 @search(i32 %needle, i32* nocapture readonly %haystack, i32 %c
; 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: movslq %edx, %rcx
; CHECK-NEXT: xorl %edx, %edx
; 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)
; ### FIXME: This loop invariant should be hoisted
; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: cmpl %edi, (%rsi,%rdx,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: incq %rdx
; CHECK-NEXT: cmpq %rcx, %rdx
; CHECK-NEXT: jl LBB0_5
; ### FIXME: BB#3 and LBB0_1 should be merged
; CHECK-NEXT: ## BB#3:
@ -31,8 +33,7 @@ define zeroext i1 @search(i32 %needle, i32* nocapture readonly %haystack, i32 %c
; 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: LBB0_6: ## %cleanup
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
; CHECK-NEXT: retq
;

View File

@ -1,21 +0,0 @@
; RUN: llc < %s -mtriple=x86_64-pc-linux | FileCheck %s
; Checks if movl $1 is sinked to critical edge.
; CHECK-NOT: movl $1
; CHECK: jbe
; CHECK: movl $1
define i32 @test(i32 %n, i32 %k) nounwind {
entry:
%cmp = icmp ugt i32 %k, %n
br i1 %cmp, label %ifthen, label %ifend, !prof !1
ifthen:
%y = add i32 %k, 2
br label %ifend
ifend:
%ret = phi i32 [ 1, %entry ] , [ %y, %ifthen]
ret i32 %ret
}
!1 = !{!"branch_weights", i32 100, i32 1}

View File

@ -14,9 +14,7 @@ forcond.preheader: ; preds = %entry
ifthen: ; preds = %entry
ret i32 0
; CHECK: forbody{{$}}
; There should be no mov instruction in the for body.
; CHECK-NOT: mov
; CHECK: jbe
forbody: ; preds = %forbody, %forcond.preheader
%indvar = phi i32 [ 0, %forcond.preheader ], [ %divisor.02, %forbody ] ; <i32> [#uses=3]
%accumulator.01 = phi i32 [ 1, %forcond.preheader ], [ %div, %forbody ] ; <i32> [#uses=1]

View File

@ -14,7 +14,7 @@ forcond.preheader: ; preds = %entry
br i1 %cmp44, label %afterfor, label %forbody
; CHECK: %forcond.preheader
; CHECK: testl
; CHECK: movl $1
; CHECK-NOT: xorl
; CHECK-NOT: movl
; CHECK-NOT: LBB
@ -24,7 +24,6 @@ forcond.preheader: ; preds = %entry
; CHECK: %forbody{{$}}
; CHECK-NOT: mov
; CHECK: jbe
; CHECK: movl $1
ifthen: ; preds = %entry
ret i32 0

View File

@ -37,11 +37,11 @@
; ASM-LABEL: loop_csr: # @loop_csr
; ASM: #DEBUG_VALUE: loop_csr:o [bit_piece offset=0 size=32] <- 0
; ASM: #DEBUG_VALUE: loop_csr:o [bit_piece offset=32 size=32] <- 0
; ASM: # BB#2: # %for.body.preheader
; ASM: # BB#1: # %for.body.preheader
; ASM: xorl %edi, %edi
; ASM: xorl %esi, %esi
; ASM: .p2align 4, 0x90
; ASM: .LBB0_3: # %for.body
; ASM: .LBB0_2: # %for.body
; ASM: [[ox_start:\.Ltmp[0-9]+]]:
; ASM: #DEBUG_VALUE: loop_csr:o [bit_piece offset=0 size=32] <- %EDI
; ASM: .cv_loc 0 1 13 11 # t.c:13:11
@ -57,7 +57,7 @@
; ASM: movl %eax, %esi
; ASM: #DEBUG_VALUE: loop_csr:o [bit_piece offset=32 size=32] <- %ESI
; ASM: cmpl n(%rip), %eax
; ASM: jl .LBB0_3
; ASM: jl .LBB0_2
; ASM: [[oy_end:\.Ltmp[0-9]+]]:
; ASM: addl %edi, %esi
; ASM: movl %esi, %eax

View File

@ -1,5 +1,5 @@
; RUN: opt < %s -codegenprepare -S | FileCheck --check-prefixes=CHECK-OPT %s
; RUN: llc < %s -mtriple=x86_64-pc-linux-gnu -o - | FileCheck --check-prefixes=CHECK-LLC %s
; RUN: llc < %s -o - | FileCheck --check-prefixes=CHECK-LLC %s
target triple = "x86_64-pc-linux-gnu"