Flip the new block-placement pass to be on by default.

This is mostly to test the waters. I'd like to get results from FNT
build bots and other bots running on non-x86 platforms.

This feature has been pretty heavily tested over the last few months by
me, and it fixes several of the execution time regressions caused by the
inlining work by preventing inlining decisions from radically impacting
block layout.

I've seen very large improvements in yacr2 and ackermann benchmarks,
along with the expected noise across all of the benchmark suite whenever
code layout changes. I've analyzed all of the regressions and fixed
them, or found them to be impossible to fix. See my email to llvmdev for
more details.

I'd like for this to be in 3.1 as it complements the inliner changes,
but if any failures are showing up or anyone has concerns, it is just
a flag flip and so can be easily turned off.

I'm switching it on tonight to try and get at least one run through
various folks' performance suites in case SPEC or something else has
serious issues with it. I'll watch bots and revert if anything shows up.

llvm-svn: 154816
This commit is contained in:
Chandler Carruth 2012-04-16 13:49:17 +00:00
parent a355e7cf82
commit 4190b507c5
32 changed files with 107 additions and 86 deletions

View File

@ -37,8 +37,9 @@ static cl::opt<bool> DisableTailDuplicate("disable-tail-duplicate", cl::Hidden,
cl::desc("Disable tail duplication"));
static cl::opt<bool> DisableEarlyTailDup("disable-early-taildup", cl::Hidden,
cl::desc("Disable pre-register allocation tail duplication"));
static cl::opt<bool> EnableBlockPlacement("enable-block-placement",
cl::Hidden, cl::desc("Enable probability-driven block placement"));
static cl::opt<bool> DisableBlockPlacement("disable-block-placement",
cl::Hidden, cl::desc("Disable the probability-driven block placement, and "
"re-enable the old code placement pass"));
static cl::opt<bool> EnableBlockPlacementStats("enable-block-placement-stats",
cl::Hidden, cl::desc("Collect probability-driven block placement stats"));
static cl::opt<bool> DisableCodePlace("disable-code-place", cl::Hidden,
@ -610,10 +611,10 @@ void TargetPassConfig::addMachineLateOptimization() {
/// Add standard basic block placement passes.
void TargetPassConfig::addBlockPlacement() {
AnalysisID ID = &NoPassID;
if (EnableBlockPlacement) {
// MachineBlockPlacement is an experimental pass which is disabled by
// default currently. Eventually it should subsume CodePlacementOpt, so
// when enabled, the other is disabled.
if (!DisableBlockPlacement) {
// MachineBlockPlacement is a new pass which subsumes the functionality of
// CodPlacementOpt. The old code placement pass can be restored by
// disabling block placement, but eventually it will be removed.
ID = addPass(MachineBlockPlacementID);
} else {
ID = addPass(CodePlacementOptID);

View File

@ -26,7 +26,7 @@ bb2: ; preds = %bb1, %entry
; CHECK: bb2
; CHECK: subs [[REG:r[0-9]+]], #1
; CHECK: cmp [[REG]], #0
; CHECK: bgt
; CHECK: ble
%indvar = phi i32 [ %indvar.next, %bb1 ], [ 0, %entry ]
%tries.0 = sub i32 2147483647, %indvar
%tmp1 = icmp sgt i32 %tries.0, 0

View File

@ -16,11 +16,11 @@ declare i8* @choose(i8*, i8*)
; CHECK: tail_duplicate_me:
; CHECK: qux
; CHECK: qux
; CHECK: movw r{{[0-9]+}}, :lower16:_GHJK
; CHECK: movt r{{[0-9]+}}, :upper16:_GHJK
; CHECK: str r
; CHECK-NEXT: bx r
; CHECK: qux
; CHECK: movw r{{[0-9]+}}, :lower16:_GHJK
; CHECK: movt r{{[0-9]+}}, :upper16:_GHJK
; CHECK: str r

View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=cellspu -o - | grep brnz
; RUN: llc < %s -march=cellspu -o - | grep brz
; PR3274
target datalayout = "E-p:32:32:128-i1:8:128-i8:8:128-i16:16:128-i32:32:128-i64:32:128-f32:32:128-f64:64:128-v64:64:64-v128:128:128-a0:0:128-s0:128:128"

View File

@ -26,9 +26,9 @@ return: ; preds = %if.else, %if.end6
define void @f1(float %f) nounwind {
entry:
; CHECK: bc1t $BB1_2
; CHECK: bc1f $BB1_1
; CHECK: nop
; CHECK: # BB#1:
; CHECK: # BB#2:
%cmp = fcmp une float %f, 0.000000e+00
br i1 %cmp, label %if.then, label %if.end

View File

@ -26,7 +26,7 @@ entry:
lpad: ; preds = %entry
; CHECK-EL: # %lpad
; CHECK-EL: lw $gp
; CHECK-EL: beq $5
; CHECK-EL: bne $5
%exn.val = landingpad { i8*, i32 } personality i32 (...)* @__gxx_personality_v0
catch i8* bitcast (i8** @_ZTId to i8*)

View File

@ -45,7 +45,7 @@ if.end: ; preds = %if.else, %if.then
define void @func2(float %f2, float %f3) nounwind {
entry:
; CHECK: c.ole.s
; CHECK: bc1f
; CHECK: bc1t
%cmp = fcmp ugt float %f2, %f3
br i1 %cmp, label %if.else, label %if.then
@ -102,7 +102,7 @@ if.end: ; preds = %if.else, %if.then
define void @func5(double %f2, double %f3) nounwind {
entry:
; CHECK: c.ole.d
; CHECK: bc1f
; CHECK: bc1t
%cmp = fcmp ugt double %f2, %f3
br i1 %cmp, label %if.else, label %if.then

View File

@ -58,8 +58,8 @@ define i32 @f4(i32 %a, i32 %b, i32* %v) {
entry:
; CHECK: f4:
; CHECK: blo LBB
%tmp = icmp ult i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp, label %return, label %cond_true
%tmp = icmp uge i32 %a, %b ; <i1> [#uses=1]
br i1 %tmp, label %cond_true, label %return
cond_true: ; preds = %entry
fence seq_cst

View File

@ -29,13 +29,13 @@ declare i32 @bar(...)
define fastcc i32 @CountTree(%struct.quad_struct* %tree) {
entry:
; CHECK: CountTree:
; CHECK: it eq
; CHECK: cmpeq
; CHECK: bne
; CHECK: cmp
; CHECK: itt eq
; CHECK: moveq
; CHECK: popeq
; CHECK: bne
; CHECK: cmp
; CHECK: it eq
; CHECK: cmpeq
br label %tailrecurse
tailrecurse: ; preds = %bb, %entry
@ -83,7 +83,7 @@ define fastcc void @t2() nounwind {
entry:
; CHECK: t2:
; CHECK: cmp r0, #0
; CHECK: beq
; CHECK: bne
br i1 undef, label %bb.i.i3, label %growMapping.exit
bb.i.i3: ; preds = %entry

View File

@ -3,11 +3,19 @@
; Do not use tbb / tbh if any destination is before the jumptable.
; rdar://7102917
define i16 @main__getopt_internal_2E_exit_2E_ce(i32) nounwind {
define i16 @main__getopt_internal_2E_exit_2E_ce(i32, i1 %b) nounwind {
entry:
br i1 %b, label %codeRepl127.exitStub, label %newFuncRoot
newFuncRoot:
br label %_getopt_internal.exit.ce
codeRepl127.exitStub: ; preds = %_getopt_internal.exit.ce
; Add an explicit edge back to before the jump table to ensure this block
; is placed first.
br i1 %b, label %newFuncRoot, label %codeRepl127.exitStub.exit
codeRepl127.exitStub.exit:
ret i16 0
parse_options.exit.loopexit.exitStub: ; preds = %_getopt_internal.exit.ce

View File

@ -6,8 +6,8 @@
define i32 @test(i32 %argc, i8** %argv) nounwind {
entry:
; CHECK: cmpl $2
; CHECK-NEXT: je
; CHECK-NEXT: %entry
; CHECK-NEXT: jne
; CHECK-NEXT: %bb2
switch i32 %argc, label %UnifiedReturnBlock [
i32 1, label %bb

View File

@ -1,4 +1,4 @@
; RUN: llc < %s -enable-unsafe-fp-math -march=x86 | grep jnp
; RUN: llc < %s -enable-unsafe-fp-math -march=x86 | grep jp
; rdar://5902801
declare void @test2()

View File

@ -17,7 +17,7 @@ entry:
; CHECK: andl $150
; CHECK-NEXT: testb
; CHECK-NEXT: jg
; CHECK-NEXT: jle
entry.if.end_crit_edge: ; preds = %entry
%tmp4.pre = load i32* @g_38 ; <i32> [#uses=1]

View File

@ -1,4 +1,4 @@
; RUN: llc -mtriple=i686-linux -enable-block-placement < %s | FileCheck %s
; RUN: llc -mtriple=i686-linux < %s | FileCheck %s
declare void @error(i32 %i, i32 %a, i32 %b)

View File

@ -1,7 +1,7 @@
; RUN: llc -march=x86-64 < %s | FileCheck %s
; CHECK: orq
; CHECK-NEXT: jne
; CHECK-NEXT: je
@_ZN11xercesc_2_513SchemaSymbols21fgURI_SCHEMAFORSCHEMAE = external constant [33 x i16], align 32 ; <[33 x i16]*> [#uses=1]
@_ZN11xercesc_2_56XMLUni16fgNotationStringE = external constant [9 x i16], align 16 ; <[9 x i16]*> [#uses=1]

View File

@ -7,8 +7,8 @@ define i32 @decode_byte(%struct.decode_t* %decode) nounwind {
; CHECK: decode_byte:
; CHECK: pushl
; CHECK: popl
; CHECK: popl
; CHECK: jmp
; CHECK: popl
entry:
%tmp2 = getelementptr %struct.decode_t* %decode, i32 0, i32 4 ; <i16*> [#uses=1]
%tmp23 = bitcast i16* %tmp2 to i32* ; <i32*> [#uses=1]

View File

@ -1,7 +1,7 @@
; RUN: llc -asm-verbose=false < %s | FileCheck %s
; RUN: llc -asm-verbose=true < %s | FileCheck %s
; MachineLICM should check dominance before hoisting instructions.
; CHECK: jne LBB0_3
; CHECK: ## in Loop:
; CHECK-NEXT: xorb %al, %al
; CHECK-NEXT: testb %al, %al

View File

@ -41,6 +41,7 @@ done:
; CHECK-NEXT: align
; CHECK-NEXT: .LBB1_4:
; CHECK-NEXT: callq bar99
; CHECK-NEXT: align
; CHECK-NEXT: .LBB1_1:
; CHECK-NEXT: callq body
@ -75,19 +76,21 @@ exit:
; CHECK: yet_more_involved:
; CHECK: jmp .LBB2_1
; CHECK-NEXT: align
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT: callq bar99
; CHECK-NEXT: .LBB2_5:
; CHECK-NEXT: callq block_a_true_func
; CHECK-NEXT: callq block_a_merge_func
; CHECK-NEXT: align
; CHECK-NEXT: .LBB2_1:
; CHECK-NEXT: callq body
;
; LBB2_4
; CHECK: callq bar99
; CHECK-NEXT: callq get
; CHECK-NEXT: cmpl $2999, %eax
; CHECK-NEXT: jle .LBB2_5
; CHECK-NEXT: callq block_a_false_func
; CHECK-NEXT: callq block_a_merge_func
; CHECK-NEXT: jmp .LBB2_1
; CHECK-NEXT: .LBB2_5:
; CHECK-NEXT: callq block_a_true_func
; CHECK-NEXT: callq block_a_merge_func
; CHECK-NEXT: .LBB2_1:
; CHECK-NEXT: callq body
define void @yet_more_involved() nounwind {
entry:
@ -136,17 +139,22 @@ exit:
; CHECK-NEXT: align
; CHECK-NEXT: .LBB3_7:
; CHECK-NEXT: callq bar100
; CHECK-NEXT: jmp .LBB3_1
; CHECK-NEXT: .LBB3_8:
; CHECK-NEXT: callq bar101
; CHECK-NEXT: jmp .LBB3_1
; CHECK-NEXT: .LBB3_9:
; CHECK-NEXT: callq bar102
; CHECK-NEXT: jmp .LBB3_1
; CHECK-NEXT: .LBB3_5:
; CHECK-NEXT: callq loop_latch
; CHECK-NEXT: align
; CHECK-NEXT: .LBB3_1:
; CHECK-NEXT: callq loop_header
; CHECK: jl .LBB3_7
; CHECK: jge .LBB3_3
; CHECK-NEXT: callq bar101
; CHECK-NEXT: jmp .LBB3_1
; CHECK-NEXT: .LBB3_3:
; CHECK: jge .LBB3_4
; CHECK-NEXT: callq bar102
; CHECK-NEXT: jmp .LBB3_1
; CHECK-NEXT: .LBB3_4:
; CHECK: jl .LBB3_6
; CHECK-NEXT: callq loop_latch
; CHECK-NEXT: jmp .LBB3_1
; CHECK-NEXT: .LBB3_6:
define void @cfg_islands() nounwind {
entry:

View File

@ -5,11 +5,11 @@
define i32 @t1(i32 %a, i32 %b) nounwind {
entry:
; CHECK: t1:
; CHECK: jne
; CHECK: je [[LABEL:.*BB.*]]
%cmp1 = icmp eq i32 %b, 0
br i1 %cmp1, label %while.end, label %while.body
; CHECK: BB
; CHECK: [[LABEL]]:
; CHECK-NOT: mov
; CHECK: ret

View File

@ -70,8 +70,8 @@ bb26.preheader: ; preds = %imix_test.exit
bb23: ; preds = %imix_test.exit
unreachable
; Verify that there are no loads inside the loop.
; X86-32: %bb26.preheader
; X86-32: .align 4
; X86-32: %bb28
; X86-32-NOT: (%esp),
; X86-32-NOT: (%ebp),
; X86-32: jmp

View File

@ -18,11 +18,12 @@ forcond.preheader: ; preds = %entry
; CHECK-NOT: xorl
; CHECK-NOT: movl
; CHECK-NOT: LBB
; CHECK: jne
; CHECK: je
; There should be no moves required in the for loop body.
; CHECK: %forbody
; CHECK-NOT: mov
; CHECK: jbe
ifthen: ; preds = %entry
ret i32 0

View File

@ -75,9 +75,9 @@ define void @test6(i32 %C, <4 x float>* %A, <4 x float>* %B) nounwind {
; Verify that the fmul gets sunk into the one part of the diamond where it is
; needed.
; CHECK: test6:
; CHECK: jne
; CHECK: mulps
; CHECK: je
; CHECK: ret
; CHECK: mulps
; CHECK: ret
}

View File

@ -147,7 +147,7 @@ define i32 @t11(i32 %x, i32 %y, i32 %z.0, i32 %z.1, i32 %z.2) nounwind ssp {
; 32: t11:
; 32-NOT: subl ${{[0-9]+}}, %esp
; 32: jne
; 32: je
; 32-NOT: movl
; 32-NOT: addl ${{[0-9]+}}, %esp
; 32: jmp {{_?}}foo5

View File

@ -7,8 +7,9 @@
; CHECK: foo:
; CHECK-NEXT: testb $1, %dil
; CHECK-NEXT: je
; CHECK-NEXT: jne
; CHECK-NEXT: divsd
; CHECK-NEXT: movaps
; CHECK-NEXT: ret
; CHECK: divsd
@ -25,10 +26,10 @@ define double @foo(double %x, double %y, i1 %c) nounwind {
; CHECK: split:
; CHECK-NEXT: testb $1, %dil
; CHECK-NEXT: je
; CHECK-NEXT: divsd
; CHECK-NEXT: jne
; CHECK-NEXT: movaps
; CHECK-NEXT: ret
; CHECK: movaps
; CHECK: divsd
; CHECK-NEXT: ret
define double @split(double %x, double %y, i1 %c) nounwind {
%a = fdiv double %x, 3.2

View File

@ -19,7 +19,7 @@ overflow:
ret i1 false
; CHECK: test1:
; CHECK: imull
; CHECK-NEXT: jo
; CHECK-NEXT: jno
}
define i1 @test2(i32 %v1, i32 %v2) nounwind {

View File

@ -20,7 +20,7 @@ overflow:
; CHECK: func1:
; CHECK: subl 20(%esp)
; CHECK-NEXT: jo
; CHECK-NEXT: jno
}
define i1 @func2(i32 %v1, i32 %v2) nounwind {
@ -40,7 +40,7 @@ carry:
; CHECK: func2:
; CHECK: subl 20(%esp)
; CHECK-NEXT: jb
; CHECK-NEXT: jae
}
declare i32 @printf(i8*, ...) nounwind

View File

@ -5,11 +5,11 @@
; CHECK: movabsq $2305843009482129440, %r
; CHECK-NEXT: btq %rax, %r
; CHECK-NEXT: jb
; CHECK-NEXT: movl $671088640, %e
; CHECK-NEXT: jae
; CHECK: movl $671088640, %e
; CHECK-NEXT: btq %rax, %r
; CHECK-NEXT: jb
; CHECK-NEXT: testq %rax, %r
; CHECK-NEXT: jae
; CHECK: testq %rax, %r
; CHECK-NEXT: j
define void @test(i8* %l) nounwind {
@ -60,7 +60,7 @@ define void @test2(i32 %x) nounwind ssp {
; CHECK-NEXT: movl $91
; CHECK-NOT: movl
; CHECK-NEXT: btl
; CHECK-NEXT: jb
; CHECK-NEXT: jae
entry:
switch i32 %x, label %if.end [
i32 6, label %if.then
@ -85,7 +85,7 @@ define void @test3(i32 %x) nounwind {
; CHECK: cmpl $5
; CHECK: ja
; CHECK: cmpl $4
; CHECK: jne
; CHECK: je
switch i32 %x, label %if.end [
i32 0, label %if.then
i32 1, label %if.then

View File

@ -113,15 +113,16 @@ altret:
; CHECK-NEXT: jbe .LBB2_3
; CHECK-NEXT: ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
; CHECK-NEXT: ja .LBB2_4
; CHECK-NEXT: .LBB2_2:
; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: ret
; CHECK-NEXT: jmp .LBB2_2
; CHECK-NEXT: .LBB2_3:
; CHECK-NEXT: ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
; CHECK-NEXT: jbe .LBB2_2
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT: xorb %al, %al
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB2_2:
; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: ret
define i1 @dont_merge_oddly(float* %result) nounwind {
entry:
@ -336,10 +337,10 @@ return:
; CHECK: two:
; CHECK-NOT: XYZ
; CHECK: ret
; CHECK: movl $0, XYZ(%rip)
; CHECK: movl $1, XYZ(%rip)
; CHECK-NOT: XYZ
; CHECK: ret
define void @two() nounwind optsize {
entry:

View File

@ -7,13 +7,14 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
target triple = "x86_64-apple-darwin10.0.0"
; CHECK: testq %rdi, %rdi
; CHECK-NEXT: jns LBB0_2
; CHECK-NEXT: js LBB0_1
; CHECK: cvtsi2ss
; CHECK-NEXT: ret
; CHECK: LBB0_1
; CHECK: shrq
; CHECK-NEXT: andq
; CHECK-NEXT: orq
; CHECK-NEXT: cvtsi2ss
; CHECK: LBB0_2
; CHECK-NEXT: cvtsi2ss
define float @test(i64 %a) {
entry:
%b = uitofp i64 %a to float

View File

@ -9,13 +9,13 @@ entry:
; X32-NOT: andb
; X32-NOT: shrb
; X32: testb $64
; X32: jne
; X32: je
; X64: t:
; X64-NOT: setne
; X64: xorl
; X64: testb $64
; X64: jne
; X64: je
%0 = and i32 %a, 16384
%1 = icmp ne i32 %0, 0
%2 = and i32 %b, 16384
@ -43,7 +43,7 @@ define i32 @t2(i32 %x, i32 %y) nounwind ssp {
; X32: cmpl
; X32: sete
; X32-NOT: xor
; X32: jne
; X32: je
; X64: t2:
; X64: testl
@ -51,7 +51,7 @@ define i32 @t2(i32 %x, i32 %y) nounwind ssp {
; X64: testl
; X64: sete
; X64-NOT: xor
; X64: jne
; X64: je
entry:
%0 = icmp eq i32 %x, 0 ; <i1> [#uses=1]
%1 = icmp eq i32 %y, 0 ; <i1> [#uses=1]

View File

@ -30,7 +30,7 @@ not_less:
}
; CHECK: f1:
; CHECK-NEXT: ashr r0, r0, 32
; CHECK-NEXT: bf r0
; CHECK-NEXT: bt r0
define i32 @f2(i32 %a) {
%1 = icmp sge i32 %a, 0
@ -51,9 +51,9 @@ define i32 @f3(i32 %a) {
}
; CHECK: f3:
; CHECK-NEXT: ashr r0, r0, 32
; CHECK-NEXT: bf r0
; CHECK-NEXT: ldc r0, 10
; CHECK: ldc r0, 17
; CHECK-NEXT: bt r0
; CHECK-NEXT: ldc r0, 17
; CHECK: ldc r0, 10
define i32 @f4(i32 %a) {
%1 = icmp sge i32 %a, 0
@ -62,9 +62,9 @@ define i32 @f4(i32 %a) {
}
; CHECK: f4:
; CHECK-NEXT: ashr r0, r0, 32
; CHECK-NEXT: bf r0
; CHECK-NEXT: ldc r0, 17
; CHECK: ldc r0, 10
; CHECK-NEXT: bt r0
; CHECK-NEXT: ldc r0, 10
; CHECK: ldc r0, 17
define i32 @f5(i32 %a) {
%1 = icmp sge i32 %a, 0

View File

@ -61,7 +61,7 @@ exit: ; preds = %cond.true29.i, %cond.true.i
; CHECK: @test2
; CHECK: %entry
; CHECK-NOT: mov
; CHECK: jne
; CHECK: je
define void @test2(i32 %n) nounwind uwtable {
entry:
br i1 undef, label %while.end, label %for.cond468