fe69a20cc1
This update follows up on change #112671 and is mostly a NFC, with the following exceptions: - Introduced `-global-merging-skip-no-params` to bypass merging when no parameters are required. - Parameter count is now calculated based on the unique hash count. - Added `-global-merging-inst-overhead` to adjust the instruction overhead, reflecting the machine instruction size. - Costs and benefits are now computed using the double data type. Since the finalization process occurs offline, this should not significantly impact build time. - Moved a sorting operation outside of the loop. This is a patch for https://discourse.llvm.org/t/rfc-global-function-merging/82608.
40 lines
1.5 KiB
LLVM
40 lines
1.5 KiB
LLVM
; This test verifies whether two identical functions, f1 and f2, can be merged
|
|
; locally using the global merge function.
|
|
; The functions, f1.Tgm and f2.Tgm, will be folded by the linker through
|
|
; Identical Code Folding (ICF).
|
|
; While identical functions can already be folded by the linker, creating this
|
|
; canonical form can be beneficial in downstream passes. This merging process
|
|
; can be controlled by the -global-merging-skip-no-params option.
|
|
|
|
; RUN: llc -mtriple=arm64-apple-darwin -enable-global-merge-func=true -global-merging-skip-no-params=false < %s | FileCheck %s --check-prefix=MERGE
|
|
; RUN: llc -mtriple=arm64-apple-darwin -enable-global-merge-func=true -global-merging-skip-no-params=true < %s | FileCheck %s --implicit-check-not=".Tgm"
|
|
|
|
; MERGE: _f1.Tgm
|
|
; MERGE: _f2.Tgm
|
|
|
|
@g = external local_unnamed_addr global [0 x i32], align 4
|
|
@g1 = external global i32, align 4
|
|
@g2 = external global i32, align 4
|
|
|
|
define i32 @f1(i32 %a) {
|
|
entry:
|
|
%idxprom = sext i32 %a to i64
|
|
%arrayidx = getelementptr inbounds [0 x i32], [0 x i32]* @g, i64 0, i64 %idxprom
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%1 = load volatile i32, i32* @g1, align 4
|
|
%mul = mul nsw i32 %1, %0
|
|
%add = add nsw i32 %mul, 1
|
|
ret i32 %add
|
|
}
|
|
|
|
define i32 @f2(i32 %a) {
|
|
entry:
|
|
%idxprom = sext i32 %a to i64
|
|
%arrayidx = getelementptr inbounds [0 x i32], [0 x i32]* @g, i64 0, i64 %idxprom
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%1 = load volatile i32, i32* @g1, align 4
|
|
%mul = mul nsw i32 %1, %0
|
|
%add = add nsw i32 %mul, 1
|
|
ret i32 %add
|
|
}
|