[llvm] [FnSpecialization] Only accept codesize savings if strictly greater than the minimum amount (PR #164867)
Ryan Buchner via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 23 11:21:25 PDT 2025
https://github.com/bababuck created https://github.com/llvm/llvm-project/pull/164867
When `--funcspec-min-function-size` is set to a small value, any small function (provided passed a constant) will be scored favorably in terms of code size savings due to the rounding in integer division in the following statement:
```
auto IsProfitable = [&]() -> bool {
...
if (CodeSizeSavings < MinCodeSizeSavings * FuncSize / 100)
return false;
...
};
```
When MinCodeSizeSavings is set by default to 20, so if `FuncSize < 5` all allowed by the knob, then `MinCodeSizeSavings * FuncSize / 100` evaluates to 0. As a result, a CodeSizeSavings of `0` will pass this check and be possibly considered profitable.
I don't think this is generally an issue in the wild since `--funcspec-min-function-size` is not usually set to small values (it defaults to 500), but might be on inline cases.
Prior to this change, `unprofitable_spec` specializes (with `--funcspec-min-function-size=0`) despite not having any savings.
```
define i32 @main(i32 %y) {
%spec = call i32 @unprofitable_spec(i32 1, i32 %y)
ret i32 %spec
}
define i32 @unprofitable_spec(i32 %x, i32 %y) {
%add = add i32 %x, %y
ret i32 %add
}
```
>From be66439ae2cf4d51651ac80a560ca8416419844a Mon Sep 17 00:00:00 2001
From: bababuck <buchner.ryan at gmail.com>
Date: Thu, 23 Oct 2025 10:39:28 -0700
Subject: [PATCH 1/2] [FunctionSpecialization] Prepare test for
MinCodeSizeSavings change
For some tests, need to explicity list the MinCodeSizeSavings since they
were relying on the bug for their behavior.
Added new test that clearly demonstrates the behavior and will change with the fix.
---
.../FunctionSpecialization/dead-gv-load.ll | 3 +-
.../FunctionSpecialization/maxgrowth.ll | 2 +-
.../min-codesize-savings.ll | 28 +++++++++++++++++++
.../recursive-penalty.ll | 3 +-
4 files changed, 33 insertions(+), 3 deletions(-)
create mode 100644 llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll
diff --git a/llvm/test/Transforms/FunctionSpecialization/dead-gv-load.ll b/llvm/test/Transforms/FunctionSpecialization/dead-gv-load.ll
index 134a79d349035..45e41bd1bdce9 100644
--- a/llvm/test/Transforms/FunctionSpecialization/dead-gv-load.ll
+++ b/llvm/test/Transforms/FunctionSpecialization/dead-gv-load.ll
@@ -1,5 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
-; RUN: opt -passes=ipsccp --funcspec-min-function-size=1 -S < %s | FileCheck %s
+; RUN: opt -passes=ipsccp --funcspec-min-function-size=1 \
+; RUN: -funcspec-min-codesize-savings=1 -S < %s | FileCheck %s
@gv = internal global ptr null
diff --git a/llvm/test/Transforms/FunctionSpecialization/maxgrowth.ll b/llvm/test/Transforms/FunctionSpecialization/maxgrowth.ll
index 82d1f7ae4a6e1..c07948489dd5e 100644
--- a/llvm/test/Transforms/FunctionSpecialization/maxgrowth.ll
+++ b/llvm/test/Transforms/FunctionSpecialization/maxgrowth.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --include-generated-funcs --version 5
; RUN: opt -passes="ipsccp<func-spec>" -funcspec-min-function-size=1 \
; RUN: -funcspec-for-literal-constant=true \
-; RUN: -funcspec-min-codesize-savings=50 \
+; RUN: -funcspec-min-codesize-savings=1 \
; RUN: -funcspec-min-latency-savings=50 \
; RUN: -funcspec-max-codesize-growth=1 \
; RUN: -S < %s | FileCheck %s
diff --git a/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll b/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll
new file mode 100644
index 0000000000000..c92e9dcbb5649
--- /dev/null
+++ b/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll
@@ -0,0 +1,28 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -passes=ipsccp --funcspec-min-function-size=0 -S < %s | FileCheck %s
+
+; Call to unprofitable_spec should not specialize since no folding can occur for the add
+; instruction as only 1 of the values is know. The score for this specialization will be 0.
+define i32 @main(i32 %y) {
+; CHECK-LABEL: define i32 @main(
+; CHECK-SAME: i32 [[Y:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[SPEC:%.*]] = call i32 @unprofitable_spec.specialized.1(i32 1, i32 [[Y]])
+; CHECK-NEXT: ret i32 [[SPEC]]
+;
+entry:
+ %spec = call i32 @unprofitable_spec(i32 1, i32 %y)
+ ret i32 %spec
+}
+
+define i32 @unprofitable_spec(i32 %x, i32 %y) {
+; CHECK-LABEL: define i32 @unprofitable_spec(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[ADD:%.*]] = add i32 [[X]], [[Y]]
+; CHECK-NEXT: ret i32 [[ADD]]
+;
+entry:
+ %add = add i32 %x, %y
+ ret i32 %add
+}
diff --git a/llvm/test/Transforms/FunctionSpecialization/recursive-penalty.ll b/llvm/test/Transforms/FunctionSpecialization/recursive-penalty.ll
index fc17387dec94d..409e7b870355d 100644
--- a/llvm/test/Transforms/FunctionSpecialization/recursive-penalty.ll
+++ b/llvm/test/Transforms/FunctionSpecialization/recursive-penalty.ll
@@ -1,7 +1,8 @@
; REQUIRES: asserts
; RUN: opt -passes="ipsccp<func-spec>,inline,instcombine,simplifycfg" -S \
; RUN: -funcspec-min-function-size=23 -funcspec-max-iters=100 \
-; RUN: -debug-only=function-specialization < %s 2>&1 | FileCheck %s
+; RUN: -debug-only=function-specialization -funcspec-min-codesize-savings=1 \
+; RUN: < %s 2>&1 | FileCheck %s
; Make sure the number of specializations created are not
; linear to the number of iterations (funcspec-max-iters).
>From bd4a1ed9ebbbd2881081d8a403ffb892f11e8c5b Mon Sep 17 00:00:00 2001
From: bababuck <buchner.ryan at gmail.com>
Date: Tue, 9 Sep 2025 13:44:37 -0700
Subject: [PATCH 2/2] [FnSpecialization] Only accept codesize savings if
strictly greater than the minimum amount
If the knob for minimum code size is turned down low enough, for small functions:
`MinCodeSizeSavings * FuncSize / 100` will evaluate to `0`, and then with strict
less than we will accept Specialization that doesn't lead to any benefit.
---
llvm/lib/Transforms/IPO/FunctionSpecialization.cpp | 2 +-
.../Transforms/FunctionSpecialization/min-codesize-savings.ll | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Transforms/IPO/FunctionSpecialization.cpp b/llvm/lib/Transforms/IPO/FunctionSpecialization.cpp
index 150a2dc5d48e2..6d4b2fb7e0065 100644
--- a/llvm/lib/Transforms/IPO/FunctionSpecialization.cpp
+++ b/llvm/lib/Transforms/IPO/FunctionSpecialization.cpp
@@ -995,7 +995,7 @@ bool FunctionSpecializer::findSpecializations(Function *F, unsigned FuncSize,
<< (CodeSizeSavings * 100 / FuncSize) << "%)}\n");
// Minimum codesize savings.
- if (CodeSizeSavings < MinCodeSizeSavings * FuncSize / 100)
+ if (CodeSizeSavings <= MinCodeSizeSavings * FuncSize / 100)
return false;
// Lazily compute the Latency, to avoid unnecessarily computing BFI.
diff --git a/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll b/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll
index c92e9dcbb5649..4547e0e009852 100644
--- a/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll
+++ b/llvm/test/Transforms/FunctionSpecialization/min-codesize-savings.ll
@@ -7,7 +7,7 @@ define i32 @main(i32 %y) {
; CHECK-LABEL: define i32 @main(
; CHECK-SAME: i32 [[Y:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
-; CHECK-NEXT: [[SPEC:%.*]] = call i32 @unprofitable_spec.specialized.1(i32 1, i32 [[Y]])
+; CHECK-NEXT: [[SPEC:%.*]] = call i32 @unprofitable_spec(i32 1, i32 [[Y]])
; CHECK-NEXT: ret i32 [[SPEC]]
;
entry:
More information about the llvm-commits
mailing list