derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
117 lines
4.9 KiB
LLVM
117 lines
4.9 KiB
LLVM
;; Test to ensure a call to a different callee but with the same debug info
|
|
;; (and therefore callsite metadata) as a subsequent call in the alloc context
|
|
;; does not cause missing or incorrect cloning. This test is otherwise the same
|
|
;; as memprof-basic.ll.
|
|
|
|
;; -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,main,plx \
|
|
; RUN: -r=%t.o,blah, \
|
|
; RUN: -r=%t.o,_Znam, \
|
|
; RUN: -memprof-verify-ccg -memprof-verify-nodes \
|
|
; RUN: -stats -pass-remarks=memprof-context-disambiguation -save-temps \
|
|
; RUN: -o %t.out 2>&1 | FileCheck %s \
|
|
; RUN: --check-prefix=STATS --check-prefix=STATS-BE --check-prefix=REMARKS
|
|
|
|
; RUN: llvm-dis %t.out.1.4.opt.bc -o - | FileCheck %s --check-prefix=IR
|
|
|
|
source_filename = "memprof-aliased-location2.ll"
|
|
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
define i32 @main() #0 {
|
|
entry:
|
|
%call = call ptr @_Z3foov(), !callsite !0
|
|
%call1 = call ptr @_Z3foov(), !callsite !1
|
|
ret i32 0
|
|
}
|
|
|
|
declare void @blah()
|
|
|
|
define internal ptr @_Z3barv() #0 {
|
|
entry:
|
|
%call = call ptr @_Znam(i64 0), !memprof !2, !callsite !7
|
|
ret ptr null
|
|
}
|
|
|
|
declare ptr @_Znam(i64)
|
|
|
|
define internal ptr @_Z3bazv() #0 {
|
|
entry:
|
|
%call = call ptr @_Z3barv(), !callsite !8
|
|
;; Subsequent call to another callee but with the same debug location / callsite id
|
|
call void @blah(), !callsite !8
|
|
ret ptr null
|
|
}
|
|
|
|
define internal ptr @_Z3foov() #0 {
|
|
entry:
|
|
%call = call ptr @_Z3bazv(), !callsite !9
|
|
ret ptr null
|
|
}
|
|
|
|
; uselistorder directives
|
|
uselistorder ptr @_Z3foov, { 1, 0 }
|
|
|
|
attributes #0 = { noinline optnone }
|
|
|
|
!0 = !{i64 8632435727821051414}
|
|
!1 = !{i64 -3421689549917153178}
|
|
!2 = !{!3, !5}
|
|
!3 = !{!4, !"notcold"}
|
|
!4 = !{i64 9086428284934609951, i64 -5964873800580613432, i64 2732490490862098848, i64 8632435727821051414}
|
|
!5 = !{!6, !"cold"}
|
|
!6 = !{i64 9086428284934609951, i64 -5964873800580613432, i64 2732490490862098848, i64 -3421689549917153178}
|
|
!7 = !{i64 9086428284934609951}
|
|
!8 = !{i64 -5964873800580613432}
|
|
!9 = !{i64 2732490490862098848}
|
|
|
|
; REMARKS: call in clone main assigned to call function clone _Z3foov.memprof.1
|
|
; REMARKS: created clone _Z3barv.memprof.1
|
|
; REMARKS: call in clone _Z3barv marked with memprof allocation attribute notcold
|
|
; REMARKS: call in clone _Z3barv.memprof.1 marked with memprof allocation attribute cold
|
|
; REMARKS: created clone _Z3bazv.memprof.1
|
|
; REMARKS: call in clone _Z3bazv.memprof.1 assigned to call function clone _Z3barv.memprof.1
|
|
; REMARKS: created clone _Z3foov.memprof.1
|
|
; REMARKS: call in clone _Z3foov.memprof.1 assigned to call function clone _Z3bazv.memprof.1
|
|
|
|
|
|
; IR: define {{.*}} @main
|
|
;; The first call to foo does not allocate cold memory. It should call the
|
|
;; original functions, which ultimately call the original allocation decorated
|
|
;; with a "notcold" attribute.
|
|
; IR: call {{.*}} @_Z3foov()
|
|
;; The second call to foo allocates cold memory. It should call cloned functions
|
|
;; which ultimately call a cloned allocation decorated with a "cold" attribute.
|
|
; IR: call {{.*}} @_Z3foov.memprof.1()
|
|
; IR: define internal {{.*}} @_Z3barv()
|
|
; IR: call {{.*}} @_Znam(i64 0) #[[NOTCOLD:[0-9]+]]
|
|
; IR: define internal {{.*}} @_Z3bazv()
|
|
; IR: call {{.*}} @_Z3barv()
|
|
; IR: define internal {{.*}} @_Z3foov()
|
|
; IR: call {{.*}} @_Z3bazv()
|
|
; IR: define internal {{.*}} @_Z3barv.memprof.1()
|
|
; IR: call {{.*}} @_Znam(i64 0) #[[COLD:[0-9]+]]
|
|
; IR: define internal {{.*}} @_Z3bazv.memprof.1()
|
|
; IR: call {{.*}} @_Z3barv.memprof.1()
|
|
; IR: define internal {{.*}} @_Z3foov.memprof.1()
|
|
; IR: call {{.*}} @_Z3bazv.memprof.1()
|
|
; IR: attributes #[[NOTCOLD]] = { "memprof"="notcold" }
|
|
; IR: attributes #[[COLD]] = { "memprof"="cold" }
|
|
|
|
|
|
; STATS: 1 memprof-context-disambiguation - Number of cold static allocations (possibly cloned)
|
|
; STATS-BE: 1 memprof-context-disambiguation - Number of cold static allocations (possibly cloned) during ThinLTO backend
|
|
; STATS: 1 memprof-context-disambiguation - Number of not cold static allocations (possibly cloned)
|
|
; STATS-BE: 1 memprof-context-disambiguation - Number of not cold static allocations (possibly cloned) during ThinLTO backend
|
|
; STATS-BE: 2 memprof-context-disambiguation - Number of allocation versions (including clones) during ThinLTO backend
|
|
; STATS: 3 memprof-context-disambiguation - Number of function clones created during whole program analysis
|
|
; STATS-BE: 3 memprof-context-disambiguation - Number of function clones created during ThinLTO backend
|
|
; STATS-BE: 3 memprof-context-disambiguation - Number of functions that had clones created during ThinLTO backend
|
|
; STATS-BE: 2 memprof-context-disambiguation - Maximum number of allocation versions created for an original allocation during ThinLTO backend
|
|
; STATS-BE: 1 memprof-context-disambiguation - Number of original (not cloned) allocations with memprof profiles during ThinLTO backend
|