aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/ThinLTO
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/ThinLTO')
-rw-r--r--llvm/test/ThinLTO/X86/memprof-basic.ll11
-rw-r--r--llvm/test/ThinLTO/X86/memprof-icp.ll1
-rw-r--r--llvm/test/ThinLTO/X86/memprof_func_assign_fix.ll145
3 files changed, 155 insertions, 2 deletions
diff --git a/llvm/test/ThinLTO/X86/memprof-basic.ll b/llvm/test/ThinLTO/X86/memprof-basic.ll
index 72d282f..757f6e9 100644
--- a/llvm/test/ThinLTO/X86/memprof-basic.ll
+++ b/llvm/test/ThinLTO/X86/memprof-basic.ll
@@ -52,6 +52,7 @@
; RUN: cat %t.ccg.postbuild.dot | FileCheck %s --check-prefix=DOT
;; We should have cloned bar, baz, and foo, for the cold memory allocation.
; RUN: cat %t.ccg.cloned.dot | FileCheck %s --check-prefix=DOTCLONED
+; RUN: cat %t.ccg.clonefuncassign.dot | FileCheck %s --check-prefix=DOTFUNCASSIGN
; RUN: llvm-dis %t.out.1.4.opt.bc -o - | FileCheck %s --check-prefix=IR
@@ -143,13 +144,14 @@ attributes #0 = { noinline optnone }
!12 = !{i64 789, i64 300}
!13 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14, file: !14, producer: "clang version 21.0.0git (git@github.com:llvm/llvm-project.git e391301e0e4d9183fe06e69602e87b0bc889aeda)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, splitDebugInlining: false, nameTableKind: None)
!14 = !DIFile(filename: "basic.cc", directory: "", checksumkind: CSK_MD5, checksum: "8636c46e81402013b9d54e8307d2f149")
-!15 = distinct !DISubprogram(name: "bar", linkageName: "_Z3barv", scope: !14, file: !14, line: 1, type: !16, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !13)
+!15 = distinct !DISubprogram(name: "bar", linkageName: "_Z3barv", scope: !14, file: !14, line: 1, type: !16, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !13, declaration: !22)
!16 = !DISubroutineType(types: !17)
!17 = !{!18}
!18 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !19, size: 64)
!19 = !DIBasicType(name: "char", size: 8, encoding: DW_ATE_signed_char)
!20 = !{i32 7, !"Dwarf Version", i32 5}
!21 = !{i32 2, !"Debug Info Version", i32 3}
+!22 = !DISubprogram(name: "bar", linkageName: "_Z3barv", scope: !14, file: !14, line: 1, type: !16, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagOptimized)
; DUMP: CCG before cloning:
; DUMP: Callsite Context Graph:
@@ -321,7 +323,8 @@ attributes #0 = { noinline optnone }
; IR: attributes #[[NOTCOLD]] = { "memprof"="notcold" }
; IR: attributes #[[COLD]] = { "memprof"="cold" }
;; Make sure the clone's linkageName was updated.
-; IR: ![[SP]] = distinct !DISubprogram(name: "bar", linkageName: "_Z3barv.memprof.1"
+; IR: ![[SP]] = distinct !DISubprogram(name: "bar", linkageName: "_Z3barv.memprof.1", {{.*}} declaration: ![[SP2:[0-9]+]])
+; IR: ![[SP2]] = !DISubprogram(name: "bar", linkageName: "_Z3barv.memprof.1"
; STATS: 1 memprof-context-disambiguation - Number of cold static allocations (possibly cloned)
@@ -368,6 +371,10 @@ attributes #0 = { noinline optnone }
; DOTCLONED: Node[[BAR2]] [shape=record,tooltip="N[[BAR2]] ContextIds: 2",fillcolor="cyan",color="blue",style="filled,bold,dashed",label="{OrigId: Alloc0\n_Z3barv -\> alloc}"];
; DOTCLONED: }
+;; Here we are just ensuring that the post-function assign dot graph includes
+;; clone information for both the caller and callee in the node labels.
+; DOTFUNCASSIGN: _Z3bazv.memprof.1 -\> _Z3barv.memprof.1
+; DOTFUNCASSIGN: _Z3barv.memprof.1 -\> alloc
; DISTRIB: ^[[BAZ:[0-9]+]] = gv: (guid: 1807954217441101578, {{.*}} callsites: ((callee: ^[[BAR:[0-9]+]], clones: (0, 1)
; DISTRIB: ^[[FOO:[0-9]+]] = gv: (guid: 8107868197919466657, {{.*}} callsites: ((callee: ^[[BAZ]], clones: (0, 1)
diff --git a/llvm/test/ThinLTO/X86/memprof-icp.ll b/llvm/test/ThinLTO/X86/memprof-icp.ll
index dbc532e..3a68cd8 100644
--- a/llvm/test/ThinLTO/X86/memprof-icp.ll
+++ b/llvm/test/ThinLTO/X86/memprof-icp.ll
@@ -229,6 +229,7 @@
; RUN: llvm-lto2 run %t/main.o %t/foo.o -enable-memprof-context-disambiguation \
; RUN: -import-instr-limit=0 \
; RUN: -memprof-require-definition-for-promotion \
+; RUN: -icp-allow-decls=false \
; RUN: -enable-memprof-indirect-call-support=true \
; RUN: -supports-hot-cold-new \
; RUN: -r=%t/foo.o,_Z3fooR2B0j,plx \
diff --git a/llvm/test/ThinLTO/X86/memprof_func_assign_fix.ll b/llvm/test/ThinLTO/X86/memprof_func_assign_fix.ll
new file mode 100644
index 0000000..8303d6d
--- /dev/null
+++ b/llvm/test/ThinLTO/X86/memprof_func_assign_fix.ll
@@ -0,0 +1,145 @@
+;; Make sure we assign the original callsite to a function clone (which will be
+;; the original function clone), even when we cannot update its caller (due to
+;; missing metadata e.g. from mismatched profiles). Otherwise we will try to use
+;; the original function for a different clone, leading to confusion later when
+;; rewriting the calls.
+
+;; -stats requires asserts
+; REQUIRES: asserts
+
+; RUN: opt -thinlto-bc %s >%t.o
+; RUN: llvm-lto2 run %t.o -enable-memprof-context-disambiguation \
+; RUN: -supports-hot-cold-new \
+; RUN: -r=%t.o,A,plx \
+; RUN: -r=%t.o,B,plx \
+; RUN: -r=%t.o,C,plx \
+; RUN: -r=%t.o,D,plx \
+; RUN: -r=%t.o,E,plx \
+; RUN: -r=%t.o,F,plx \
+; RUN: -r=%t.o,G,plx \
+; RUN: -r=%t.o,A1,plx \
+; RUN: -r=%t.o,B1,plx \
+; RUN: -r=%t.o,_Znwm, \
+; RUN: -memprof-verify-ccg -memprof-verify-nodes -debug-only=memprof-context-disambiguation \
+; RUN: -stats -pass-remarks=memprof-context-disambiguation -save-temps \
+; RUN: -o %t.out 2>&1 | FileCheck %s \
+; RUN: --implicit-check-not="Mismatch in call clone assignment" \
+; RUN: --implicit-check-not="Number of callsites assigned to call multiple non-matching clones"
+
+; RUN: llvm-dis %t.out.1.4.opt.bc -o - | FileCheck %s --check-prefix=IR
+
+; ModuleID = '<stdin>'
+source_filename = "reduced.ll"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; IR-LABEL: define dso_local void @A()
+define void @A() #0 {
+ ; IR: call void @C()
+ call void @C()
+ ret void
+}
+
+; IR-LABEL: define dso_local void @B()
+define void @B() #0 {
+ ; IR: call void @C.memprof.1()
+ call void @C(), !callsite !1
+ ret void
+}
+
+; IR-LABEL: define dso_local void @C()
+define void @C() #0 {
+ ; IR: call void @F()
+ call void @F(), !callsite !16
+ ; IR: call void @D()
+ call void @D(), !callsite !2
+ ret void
+}
+
+; IR-LABEL: define dso_local void @D()
+define void @D() #0 {
+ ; IR: call void @E()
+ call void @E(), !callsite !3
+ ; IR: call void @G()
+ call void @G(), !callsite !17
+ ret void
+}
+
+; IR-LABEL: define dso_local void @E()
+define void @E() #0 {
+ ; IR: call ptr @_Znwm(i64 0) #[[NOTCOLD:[0-9]+]]
+ %1 = call ptr @_Znwm(i64 0), !memprof !4, !callsite !9
+ ret void
+}
+
+; IR-LABEL: define dso_local void @F()
+define void @F() #0 {
+ ; IR: call void @G()
+ call void @G(), !callsite !17
+ ret void
+}
+
+; IR-LABEL: define dso_local void @G()
+define void @G() #0 {
+ ; IR: call ptr @_Znwm(i64 0) #[[NOTCOLD]]
+ %2 = call ptr @_Znwm(i64 0), !memprof !10, !callsite !15
+ ret void
+}
+
+; IR-LABEL: define dso_local void @A1()
+define void @A1() #0 {
+ ; IR: call void @C()
+ call void @C(), !callsite !18
+ ret void
+}
+
+; IR-LABEL: define dso_local void @B1()
+define void @B1() #0 {
+ ; IR: call void @C.memprof.1()
+ call void @C(), !callsite !19
+ ret void
+}
+
+; IR-LABEL: define dso_local void @C.memprof.1()
+ ; IR: call void @F.memprof.1()
+ ; IR: call void @D.memprof.1()
+
+; IR-LABEL: define dso_local void @D.memprof.1()
+ ; IR: call void @E.memprof.1()
+ ; IR: call void @G()
+
+; IR-LABEL: define dso_local void @E.memprof.1()
+ ; IR: call ptr @_Znwm(i64 0) #[[COLD:[0-9]+]]
+
+; IR-LABEL: define dso_local void @F.memprof.1()
+ ; IR: call void @G.memprof.1()
+
+; IR-LABEL: define dso_local void @G.memprof.1()
+ ; IR: call ptr @_Znwm(i64 0) #[[COLD]]
+
+declare ptr @_Znwm(i64)
+
+attributes #0 = { noinline optnone }
+; IR: attributes #[[NOTCOLD]] = { "memprof"="notcold" }
+; IR: attributes #[[COLD]] = { "memprof"="cold" }
+
+!0 = !{i64 123}
+!1 = !{i64 234}
+!2 = !{i64 345}
+!3 = !{i64 456}
+!4 = !{!5, !7}
+!5 = !{!6, !"notcold"}
+!6 = !{i64 567, i64 456, i64 345, i64 123}
+!7 = !{!8, !"cold"}
+!8 = !{i64 567, i64 456, i64 345, i64 234}
+!9 = !{i64 567}
+!10 = !{!11, !13}
+!11 = !{!12, !"notcold"}
+!12 = !{i64 678, i64 891, i64 789, i64 912}
+!13 = !{!14, !"cold"}
+!14 = !{i64 678, i64 891, i64 789, i64 812}
+!15 = !{i64 678}
+!16 = !{i64 789}
+!17 = !{i64 891}
+!18 = !{i64 912}
+!19 = !{i64 812}
generated by cgit v1.1 at 2025-07-30 20:15:45 +0000