GlobalOpt: Apply fastcc to internal x86_thiscallcc functions

We should apply fastcc whenever profitable.  We can expand this list,
but there are lots of conventions with performance implications that we
don't want to change.

Differential Revision: http://llvm-reviews.chandlerc.com/D2705

llvm-svn: 202293
This commit is contained in:
Reid Kleckner 2014-02-26 19:57:30 +00:00
parent 773a57958c
commit 22869378d9
2 changed files with 60 additions and 5 deletions

View File

@ -1902,6 +1902,16 @@ static void RemoveNestAttribute(Function *F) {
}
}
/// Return true if this is a calling convention that we'd like to change. The
/// idea here is that we don't want to mess with the convention if the user
/// explicitly requested something with performance implications like coldcc,
/// GHC, or anyregcc.
static bool isProfitableToMakeFastCC(Function *F) {
CallingConv::ID CC = F->getCallingConv();
// FIXME: Is it worth transforming x86_stdcallcc and x86_fastcallcc?
return CC == CallingConv::C || CC == CallingConv::X86_ThisCall;
}
bool GlobalOpt::OptimizeFunctions(Module &M) {
bool Changed = false;
// Optimize functions.
@ -1916,11 +1926,10 @@ bool GlobalOpt::OptimizeFunctions(Module &M) {
Changed = true;
++NumFnDeleted;
} else if (F->hasLocalLinkage()) {
if (F->getCallingConv() == CallingConv::C && !F->isVarArg() &&
!F->hasAddressTaken()) {
// If this function has C calling conventions, is not a varargs
// function, and is only called directly, promote it to use the Fast
// calling convention.
if (isProfitableToMakeFastCC(F) && !F->isVarArg() && !F->hasAddressTaken()) {
// If this function has a calling convention worth changing, is not a
// varargs function, and is only called directly, promote it to use the
// Fast calling convention.
F->setCallingConv(CallingConv::Fast);
ChangeCalleesToFastCall(F);
++NumFastCallFns;

View File

@ -0,0 +1,46 @@
; RUN: opt < %s -globalopt -S | FileCheck %s
define internal i32 @f(i32* %m) {
; CHECK-LABEL: define internal fastcc i32 @f
%v = load i32* %m
ret i32 %v
}
define internal x86_thiscallcc i32 @g(i32* %m) {
; CHECK-LABEL: define internal fastcc i32 @g
%v = load i32* %m
ret i32 %v
}
; Leave this one alone, because the user went out of their way to request this
; convention.
define internal coldcc i32 @h(i32* %m) {
; CHECK-LABEL: define internal coldcc i32 @h
%v = load i32* %m
ret i32 %v
}
define internal i32 @j(i32* %m) {
; CHECK-LABEL: define internal i32 @j
%v = load i32* %m
ret i32 %v
}
define void @call_things() {
%m = alloca i32
call i32 @f(i32* %m)
call x86_thiscallcc i32 @g(i32* %m)
call coldcc i32 @h(i32* %m)
call i32 @j(i32* %m)
ret void
}
@llvm.used = appending global [1 x i8*] [
i8* bitcast (i32(i32*)* @j to i8*)
], section "llvm.metadata"
; CHECK-LABEL: define void @call_things()
; CHECK: call fastcc i32 @f
; CHECK: call fastcc i32 @g
; CHECK: call coldcc i32 @h
; CHECK: call i32 @j