2fef685363
Many profitable optimizations cannot be performed at -Oz, due to unrotated loops. While this is worse for size (minimally), many of the optimizations significantly reduce code size, such as memcpy optimizations and other patterns found by loop idiom recognition. Related discussion can be found in issue #50308. This patch adds an experimental, backend-only flag to allow loop header duplication, regardless of the optimization level. Downstream consumers can experiment with this flag, and if it is profitable, we can adjust the compiler's defaults accordingly, and expose any useful frontend flags to opt into the new behavior.
36 lines
1.1 KiB
LLVM
36 lines
1.1 KiB
LLVM
; REQUIRES: asserts
|
|
; RUN: opt < %s -S -Os -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OS
|
|
; RUN: opt < %s -S -Oz -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OZ
|
|
; RUN: opt < %s -S -passes='default<Os>' -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OS
|
|
; RUN: opt < %s -S -passes='default<Oz>' -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OZ
|
|
|
|
;; Make sure -allow-loop-header-duplication overrides the default behavior at Oz
|
|
; RUN: opt < %s -S -passes='default<Oz>' -enable-loop-header-duplication -debug -debug-only=loop-rotate 2>&1 | FileCheck %s -check-prefix=OS
|
|
|
|
; Loop should be rotated for -Os but not for -Oz.
|
|
; OS: rotating Loop at depth 1
|
|
; OZ-NOT: rotating Loop at depth 1
|
|
|
|
@e = global i32 10
|
|
|
|
declare void @use(i32)
|
|
|
|
define void @test() {
|
|
entry:
|
|
%end = load i32, ptr @e
|
|
br label %loop
|
|
|
|
loop:
|
|
%n.phi = phi i32 [ %n, %loop.fin ], [ 0, %entry ]
|
|
%cond = icmp eq i32 %n.phi, %end
|
|
br i1 %cond, label %exit, label %loop.fin
|
|
|
|
loop.fin:
|
|
%n = add i32 %n.phi, 1
|
|
call void @use(i32 %n)
|
|
br label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|