8045bf9d0d
The current implementation of Function Specialization does not allow specializing more than one arguments per function call, which is a limitation I am lifting with this patch. My main challenge was to choose the most suitable ADT for storing the specializations. We need an associative container for binding all the actual arguments of a specialization to the function call. We also need a consistent iteration order across executions. Lastly we want to be able to sort the entries by Gain and reject the least profitable ones. MapVector fits the bill but not quite; erasing elements is expensive and using stable_sort messes up the indices to the underlying vector. I am therefore using the underlying vector directly after calculating the Gain. Differential Revision: https://reviews.llvm.org/D119880
62 lines
1.9 KiB
LLVM
62 lines
1.9 KiB
LLVM
; RUN: opt -function-specialization -force-function-specialization \
|
|
; RUN: -func-specialization-max-clones=2 -S < %s | FileCheck %s
|
|
|
|
; RUN: opt -function-specialization -force-function-specialization \
|
|
; RUN: -func-specialization-max-clones=1 -S < %s | FileCheck %s --check-prefix=CONST1
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
@A = external dso_local constant i32, align 4
|
|
@B = external dso_local constant i32, align 4
|
|
@C = external dso_local constant i32, align 4
|
|
@D = external dso_local constant i32, align 4
|
|
|
|
define dso_local i32 @bar(i32 %x, i32 %y) {
|
|
entry:
|
|
%tobool = icmp ne i32 %x, 0
|
|
br i1 %tobool, label %if.then, label %if.else
|
|
|
|
if.then:
|
|
%call = call i32 @foo(i32 %x, i32* @A, i32* @C)
|
|
br label %return
|
|
|
|
if.else:
|
|
%call1 = call i32 @foo(i32 %y, i32* @B, i32* @D)
|
|
br label %return
|
|
|
|
return:
|
|
%retval.0 = phi i32 [ %call, %if.then ], [ %call1, %if.else ]
|
|
ret i32 %retval.0
|
|
}
|
|
|
|
; CHECK-NOT: define internal i32 @foo(
|
|
define internal i32 @foo(i32 %x, i32* %b, i32* %c) {
|
|
entry:
|
|
%0 = load i32, i32* %b, align 4
|
|
%add = add nsw i32 %x, %0
|
|
%1 = load i32, i32* %c, align 4
|
|
%add1 = add nsw i32 %add, %1
|
|
ret i32 %add1
|
|
}
|
|
|
|
; CONST1: define internal i32 @foo.1(i32 %x, i32* %b, i32* %c)
|
|
; CONST1-NOT: define internal i32 @foo.2(i32 %x, i32* %b, i32* %c)
|
|
|
|
; CHECK: define internal i32 @foo.1(i32 %x, i32* %b, i32* %c) {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: %0 = load i32, i32* @A, align 4
|
|
; CHECK-NEXT: %add = add nsw i32 %x, %0
|
|
; CHECK-NEXT: %1 = load i32, i32* @C, align 4
|
|
; CHECK-NEXT: %add1 = add nsw i32 %add, %1
|
|
; CHECK-NEXT: ret i32 %add1
|
|
; CHECK-NEXT: }
|
|
|
|
; CHECK: define internal i32 @foo.2(i32 %x, i32* %b, i32* %c) {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: %0 = load i32, i32* @B, align 4
|
|
; CHECK-NEXT: %add = add nsw i32 %x, %0
|
|
; CHECK-NEXT: %1 = load i32, i32* @D, align 4
|
|
; CHECK-NEXT: %add1 = add nsw i32 %add, %1
|
|
; CHECK-NEXT: ret i32 %add1
|
|
; CHECK-NEXT: }
|