maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[CodeGen] Split -enable-global-merge into ARM and AArch64 options. 

Currently, there's a single flag, checked by the pass itself.
It can't force-enable the pass (and is on by default), because it
might not even have been created, as that's the targets decision.
Instead, have separate explicit flags, so that the decision is
consistently made in the target.

Keep the flag as a last-resort "force-disable GlobalMerge" for now,
for backwards compatibility.

llvm-svn: 234666
This commit is contained in:
Ahmed Bougacha 2015-04-11 00:06:36 +00:00
parent 241982c380
commit b96444efd1
8 changed files with 37 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/CodeGen/GlobalMerge.cpp
View File

@ -73,9 +73,10 @@ using namespace llvm;
#define DEBUG_TYPE "global-merge" #define DEBUG_TYPE "global-merge"
// FIXME: This is only useful as a last-resort way to disable the pass.
static cl::opt<bool> static cl::opt<bool>
EnableGlobalMerge("enable-global-merge", cl::Hidden, EnableGlobalMerge("enable-global-merge", cl::Hidden,
cl::desc("Enable global merge pass"), cl::desc("Enable the global merge pass"),
cl::init(true)); cl::init(true));
static cl::opt<bool> static cl::opt<bool>

9
llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
View File

@ -87,6 +87,11 @@ EnableGEPOpt("aarch64-gep-opt", cl::Hidden,
cl::desc("Enable optimizations on complex GEPs"), cl::desc("Enable optimizations on complex GEPs"),
cl::init(true)); cl::init(true));
// FIXME: Unify control over GlobalMerge.
static cl::opt<cl::boolOrDefault>
EnableGlobalMerge("aarch64-global-merge", cl::Hidden,
cl::desc("Enable the global merge pass"));
extern "C" void LLVMInitializeAArch64Target() { extern "C" void LLVMInitializeAArch64Target() {
// Register the target. // Register the target.
RegisterTargetMachine<AArch64leTargetMachine> X(TheAArch64leTarget); RegisterTargetMachine<AArch64leTargetMachine> X(TheAArch64leTarget);
@ -245,7 +250,9 @@ bool AArch64PassConfig::addPreISel() {
// FIXME: On AArch64, this depends on the type. // FIXME: On AArch64, this depends on the type.
// Basically, the addressable offsets are up to 4095 * Ty.getSizeInBytes(). // Basically, the addressable offsets are up to 4095 * Ty.getSizeInBytes().
// and the offset has to be a multiple of the related size in bytes. // and the offset has to be a multiple of the related size in bytes.
if (TM->getOptLevel() == CodeGenOpt::Aggressive) if ((TM->getOptLevel() == CodeGenOpt::Aggressive &&
EnableGlobalMerge == cl::BOU_UNSET) ||
EnableGlobalMerge == cl::BOU_TRUE)
addPass(createGlobalMergePass(TM, 4095)); addPass(createGlobalMergePass(TM, 4095));
if (TM->getOptLevel() != CodeGenOpt::None) if (TM->getOptLevel() != CodeGenOpt::None)
addPass(createAArch64AddressTypePromotionPass()); addPass(createAArch64AddressTypePromotionPass());

9
llvm/lib/Target/ARM/ARMTargetMachine.cpp
View File

@ -42,6 +42,11 @@ EnableARMLoadStoreOpt("arm-load-store-opt", cl::Hidden,
cl::desc("Enable ARM load/store optimization pass"), cl::desc("Enable ARM load/store optimization pass"),
cl::init(true)); cl::init(true));
// FIXME: Unify control over GlobalMerge.
static cl::opt<cl::boolOrDefault>
EnableGlobalMerge("arm-global-merge", cl::Hidden,
cl::desc("Enable the global merge pass"));
extern "C" void LLVMInitializeARMTarget() { extern "C" void LLVMInitializeARMTarget() {
// Register the target. // Register the target.
RegisterTargetMachine<ARMLETargetMachine> X(TheARMLETarget); RegisterTargetMachine<ARMLETargetMachine> X(TheARMLETarget);
@ -332,7 +337,9 @@ void ARMPassConfig::addIRPasses() {
} }
bool ARMPassConfig::addPreISel() { bool ARMPassConfig::addPreISel() {
if (TM->getOptLevel() == CodeGenOpt::Aggressive) if ((TM->getOptLevel() == CodeGenOpt::Aggressive &&
EnableGlobalMerge == cl::BOU_UNSET) ||
EnableGlobalMerge == cl::BOU_TRUE)
// FIXME: This is using the thumb1 only constant value for // FIXME: This is using the thumb1 only constant value for
// maximal global offset for merging globals. We may want // maximal global offset for merging globals. We may want
// to look into using the old value for non-thumb1 code of // to look into using the old value for non-thumb1 code of

12
llvm/test/CodeGen/AArch64/global-merge-1.ll
View File

@ -1,11 +1,11 @@
; RUN: llc %s -mtriple=aarch64-none-linux-gnu -O3 -enable-global-merge -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-none-linux-gnu -aarch64-global-merge -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-none-linux-gnu -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-none-linux-gnu -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-linux-gnuabi -O3 -enable-global-merge -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-linux-gnuabi -aarch64-global-merge -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-linux-gnuabi -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-linux-gnuabi -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-apple-ios -O3 -enable-global-merge -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS ; RUN: llc %s -mtriple=aarch64-apple-ios -aarch64-global-merge -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
; RUN: llc %s -mtriple=aarch64-apple-ios -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS ; RUN: llc %s -mtriple=aarch64-apple-ios -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
@m = internal global i32 0, align 4 @m = internal global i32 0, align 4
@n = internal global i32 0, align 4 @n = internal global i32 0, align 4

6
llvm/test/CodeGen/AArch64/global-merge-2.ll
View File

@ -1,6 +1,6 @@
; RUN: llc %s -mtriple=aarch64-none-linux-gnu -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-none-linux-gnu -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-linux-gnuabi -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-linux-gnuabi -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-apple-ios -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS ; RUN: llc %s -mtriple=aarch64-apple-ios -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
@x = global i32 0, align 4 @x = global i32 0, align 4
@y = global i32 0, align 4 @y = global i32 0, align 4

6
llvm/test/CodeGen/AArch64/global-merge-3.ll
View File

@ -1,6 +1,6 @@
; RUN: llc %s -mtriple=aarch64-none-linux-gnu -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-none-linux-gnu -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-linux-gnuabi -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-linux-gnuabi -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s
; RUN: llc %s -mtriple=aarch64-apple-ios -O3 -enable-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS ; RUN: llc %s -mtriple=aarch64-apple-ios -aarch64-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
@x = global [1000 x i32] zeroinitializer, align 1 @x = global [1000 x i32] zeroinitializer, align 1
@y = global [1000 x i32] zeroinitializer, align 1 @y = global [1000 x i32] zeroinitializer, align 1

2
llvm/test/CodeGen/AArch64/global-merge-4.ll
View File

@ -1,4 +1,4 @@
; RUN: llc %s -mtriple=aarch64-linux-gnuabi -O3 -enable-global-merge -o - | FileCheck %s ; RUN: llc %s -mtriple=aarch64-linux-gnuabi -aarch64-global-merge -o - | FileCheck %s
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-n32:64-S128" 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-n32:64-S128"
target triple = "arm64-apple-ios7.0.0" target triple = "arm64-apple-ios7.0.0"

10
llvm/test/CodeGen/ARM/global-merge-1.ll
View File

@ -1,10 +1,12 @@
; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s ; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s
; RUN: llc %s -O0 -o - -arm-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
; RUN: llc %s -O0 -o - -arm-global-merge=true | FileCheck -check-prefix=MERGE %s
; RUN: llc %s -O1 -o - | FileCheck -check-prefix=NO-MERGE %s ; RUN: llc %s -O1 -o - | FileCheck -check-prefix=NO-MERGE %s
; RUN: llc %s -O1 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s ; RUN: llc %s -O1 -o - -arm-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
; RUN: llc %s -O1 -o - -enable-global-merge=true | FileCheck -check-prefix=NO-MERGE %s ; RUN: llc %s -O1 -o - -arm-global-merge=true | FileCheck -check-prefix=MERGE %s
; RUN: llc %s -O3 -o - | FileCheck -check-prefix=MERGE %s ; RUN: llc %s -O3 -o - | FileCheck -check-prefix=MERGE %s
; RUN: llc %s -O3 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s ; RUN: llc %s -O3 -o - -arm-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
; RUN: llc %s -O3 -o - -enable-global-merge=true | FileCheck -check-prefix=MERGE %s ; RUN: llc %s -O3 -o - -arm-global-merge=true | FileCheck -check-prefix=MERGE %s
; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2 ; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2 ; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2