1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-18 18:42:46 +02:00

Codegen: LICM Remove check for exactly 1 register def.

When considering whether to split an instruction with a memory operand
into an explicit load and a register-based instruction, we currently
check that the resulting instruction has exactly 1 def. This prevents 2
important LICM optimizations: compares with memory operands, and double
indirect calls. All the tests and the test-suite pass without the check.
My guess as to original intent is to limit the additional register pressure
created by the new instruction, but given that we only split out a single
register, it is already limited.

The licm-dominance test now checks actual memory loads for hoisting instead of
undef, and it tests compares.
hoist-invariant-load.ll now checks for 2 hoists, the intended hoist, and a bonus
from calling a got-relative function in a loop.

llvm-svn: 273616
This commit is contained in:
Kyle Butt 2016-06-23 21:38:49 +00:00
parent 02d9fe2d7a
commit b89a2c2028
3 changed files with 39 additions and 19 deletions

View File

@ -1171,7 +1171,6 @@ MachineInstr *MachineLICM::ExtractHoistableLoad(MachineInstr *MI) {
&LoadRegIndex);
if (NewOpc == 0) return nullptr;
const MCInstrDesc &MID = TII->get(NewOpc);
if (MID.getNumDefs() != 1) return nullptr;
MachineFunction &MF = *MI->getParent()->getParent();
const TargetRegisterClass *RC = TII->getRegClass(MID, LoadRegIndex, TRI, MF);
// Ok, we're unfolding. Create a temporary register and do the unfold.

View File

@ -1,5 +1,7 @@
; REQUIRES: asserts
; RUN: llc < %s -stats -O2 2>&1 | grep "1 machine-licm"
; RUN: llc < %s -stats -O2 2>&1 | grep "2 machine-licm"
; 2 invariant loads, 1 for OBJC_SELECTOR_REFERENCES_
; and 1 for objc_msgSend from the GOT
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.7.2"

View File

@ -1,36 +1,55 @@
; RUN: llc -asm-verbose=true < %s | FileCheck %s
; MachineLICM should check dominance before hoisting instructions.
; only the load of a0 is guaranteed to execute, so only it can be hoisted.
; CHECK: movb (%rdi), [[a0reg:%[a-z0-9]+]]
; CHECK: ## %for.body.i
; CHECK: testb [[a0reg]], [[a0reg]]
; CHECK: ## in Loop:
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK: cmpb $1, ({{%[a-z0-9]+}})
; CHECK: cmpb $2, ({{%[a-z0-9]+}})
; CHECK: cmpb $3, ({{%[a-z0-9]+}})
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-macosx10.7.2"
define void @CMSColorWorldCreateParametricData() nounwind uwtable optsize ssp {
define void @CMSColorWorldCreateParametricData(
i8* dereferenceable(1) %a0,
i8* dereferenceable(1) %a1,
i8* dereferenceable(1) %a2,
i8* dereferenceable(1) %a3,
i64 %count) nounwind uwtable optsize ssp readonly {
entry:
br label %for.body.i
for.body.i:
br i1 undef, label %for.inc.i, label %if.then26.i
for.body.i:
%i = phi i64 [0, %entry], [%i.inc, %for.inc.i]
%0 = load i8, i8* %a0, !invariant.load !0
%cond0 = icmp eq i8 %0, 0
br i1 %cond0, label %for.inc.i, label %if.then26.i
if.then26.i:
br i1 undef, label %if.else.i.i, label %lor.lhs.false.i.i
if.then26.i:
%1 = load i8, i8* %a1, !invariant.load !0
%cond1 = icmp eq i8 %1, 1
br i1 %cond1, label %if.else.i.i, label %lor.lhs.false.i.i
if.else.i.i:
br i1 undef, label %lor.lhs.false.i.i, label %if.then116.i.i
if.else.i.i:
%2 = load i8, i8* %a2, !invariant.load !0
%cond2 = icmp eq i8 %2, 2
br i1 %cond2, label %lor.lhs.false.i.i, label %for.inc.i
lor.lhs.false.i.i:
br i1 undef, label %for.inc.i, label %if.then116.i.i
lor.lhs.false.i.i:
%3 = load i8, i8* %a3, !invariant.load !0
%cond3 = icmp eq i8 %3, 3
br i1 %cond3, label %for.inc.i, label %if.end28.i
if.then116.i.i:
unreachable
for.inc.i:
%cmp17.i = icmp ult i64 undef, undef
for.inc.i:
%i.inc = add nsw i64 %i, 1
%cmp17.i = icmp ult i64 %i.inc, %count
br i1 %cmp17.i, label %for.body.i, label %if.end28.i
if.end28.i:
if.end28.i:
ret void
}
!0 = !{}