mirror of
https://github.com/intel/llvm.git
synced 2026-01-30 22:53:05 +08:00
700cd99061
This restores commitd6ad4f01c3, which was reverted in commit883dbb9c86, along with a fix for gcc 12.2 build errors in the original commit. Support for building, printing, and displaying CallsiteContextGraph which represents the MemProf metadata contexts. Uses CRTP to enable support for both IR (regular LTO) and summary (ThinLTO). This patch includes the support for building it in regular LTO mode (from memprof and callsite metadata), and the next patch will add the handling for building it from ThinLTO summaries. Also includes support for dumping the graph to text and to dot files. Follow-on patches will contain the support for cloning on the graph and in the IR. The graph represents the call contexts in all memprof metadata on allocation calls, with nodes for the allocations themselves, as well as for the calls in each context. The graph is initially built from the allocation memprof metadata (or summary) MIBs. It is then updated to match calls with callsite metadata onto the nodes, updating it to reflect any inlining performed on those calls. Each MIB (representing an allocation's call context with allocation behavior) is assigned a unique context id during the graph build. The edges and nodes in the graph are decorated with the context ids they carry. This is used to correctly update the graph when cloning is performed so that we can uniquify the context for a single (possibly cloned) allocation. Differential Revision: https://reviews.llvm.org/D140908
159 lines
5.8 KiB
LLVM
159 lines
5.8 KiB
LLVM
;; Test callsite context graph generation for simple call graph with
|
|
;; two memprof contexts and no inlining.
|
|
;;
|
|
;; Original code looks like:
|
|
;;
|
|
;; char *bar() {
|
|
;; return new char[10];
|
|
;; }
|
|
;;
|
|
;; char *baz() {
|
|
;; return bar();
|
|
;; }
|
|
;;
|
|
;; char *foo() {
|
|
;; return baz();
|
|
;; }
|
|
;;
|
|
;; int main(int argc, char **argv) {
|
|
;; char *x = foo();
|
|
;; char *y = foo();
|
|
;; memset(x, 0, 10);
|
|
;; memset(y, 0, 10);
|
|
;; delete[] x;
|
|
;; sleep(10);
|
|
;; delete[] y;
|
|
;; return 0;
|
|
;; }
|
|
;;
|
|
;; Code compiled with -mllvm -memprof-min-lifetime-cold-threshold=5 so that the
|
|
;; memory freed after sleep(10) results in cold lifetimes.
|
|
;;
|
|
;; The IR was then reduced using llvm-reduce with the expected FileCheck input.
|
|
|
|
; RUN: opt -passes=memprof-context-disambiguation \
|
|
; RUN: -memprof-verify-ccg -memprof-verify-nodes -memprof-dump-ccg \
|
|
; RUN: -memprof-export-to-dot -memprof-dot-file-path-prefix=%t. \
|
|
; RUN: %s -S 2>&1 | FileCheck %s --check-prefix=DUMP
|
|
|
|
; RUN: cat %t.ccg.postbuild.dot | FileCheck %s --check-prefix=DOT
|
|
|
|
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 noundef ptr @_Z3foov(), !callsite !0
|
|
%call1 = call noundef ptr @_Z3foov(), !callsite !1
|
|
ret i32 0
|
|
}
|
|
|
|
; Function Attrs: nocallback nofree nounwind willreturn memory(argmem: write)
|
|
declare void @llvm.memset.p0.i64(ptr nocapture writeonly, i8, i64, i1 immarg) #1
|
|
|
|
; Function Attrs: nobuiltin
|
|
declare void @_ZdaPv() #2
|
|
|
|
define internal ptr @_Z3barv() #3 {
|
|
entry:
|
|
%call = call noalias noundef nonnull ptr @_Znam(i64 noundef 10) #6, !memprof !2, !callsite !7
|
|
ret ptr null
|
|
}
|
|
|
|
declare ptr @_Znam(i64)
|
|
|
|
define internal ptr @_Z3bazv() #4 {
|
|
entry:
|
|
%call = call noundef ptr @_Z3barv(), !callsite !8
|
|
ret ptr null
|
|
}
|
|
|
|
; Function Attrs: noinline
|
|
define internal ptr @_Z3foov() #5 {
|
|
entry:
|
|
%call = call noundef ptr @_Z3bazv(), !callsite !9
|
|
ret ptr null
|
|
}
|
|
|
|
; uselistorder directives
|
|
uselistorder ptr @_Z3foov, { 1, 0 }
|
|
|
|
attributes #0 = { "tune-cpu"="generic" }
|
|
attributes #1 = { nocallback nofree nounwind willreturn memory(argmem: write) }
|
|
attributes #2 = { nobuiltin }
|
|
attributes #3 = { "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" }
|
|
attributes #4 = { "stack-protector-buffer-size"="8" }
|
|
attributes #5 = { noinline }
|
|
attributes #6 = { builtin }
|
|
|
|
!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}
|
|
|
|
|
|
; DUMP: CCG before cloning:
|
|
; DUMP: Callsite Context Graph:
|
|
; DUMP: Node [[BAR:0x[a-z0-9]+]]
|
|
; DUMP: %call = call noalias noundef nonnull ptr @_Znam(i64 noundef 10) #6 (clone 0)
|
|
; DUMP: AllocTypes: NotColdCold
|
|
; DUMP: ContextIds: 1 2
|
|
; DUMP: CalleeEdges:
|
|
; DUMP: CallerEdges:
|
|
; DUMP: Edge from Callee [[BAR]] to Caller: [[BAZ:0x[a-z0-9]+]] AllocTypes: NotColdCold ContextIds: 1 2
|
|
|
|
; DUMP: Node [[BAZ]]
|
|
; DUMP: %call = call noundef ptr @_Z3barv() (clone 0)
|
|
; DUMP: AllocTypes: NotColdCold
|
|
; DUMP: ContextIds: 1 2
|
|
; DUMP: CalleeEdges:
|
|
; DUMP: Edge from Callee [[BAR]] to Caller: [[BAZ]] AllocTypes: NotColdCold ContextIds: 1 2
|
|
; DUMP: CallerEdges:
|
|
; DUMP: Edge from Callee [[BAZ]] to Caller: [[FOO:0x[a-z0-9]+]] AllocTypes: NotColdCold ContextIds: 1 2
|
|
|
|
; DUMP: Node [[FOO]]
|
|
; DUMP: %call = call noundef ptr @_Z3bazv() (clone 0)
|
|
; DUMP: AllocTypes: NotColdCold
|
|
; DUMP: ContextIds: 1 2
|
|
; DUMP: CalleeEdges:
|
|
; DUMP: Edge from Callee [[BAZ]] to Caller: [[FOO]] AllocTypes: NotColdCold ContextIds: 1 2
|
|
; DUMP: CallerEdges:
|
|
; DUMP: Edge from Callee [[FOO]] to Caller: [[MAIN1:0x[a-z0-9]+]] AllocTypes: NotCold ContextIds: 1
|
|
; DUMP: Edge from Callee [[FOO]] to Caller: [[MAIN2:0x[a-z0-9]+]] AllocTypes: Cold ContextIds: 2
|
|
|
|
; DUMP: Node [[MAIN1]]
|
|
; DUMP: %call = call noundef ptr @_Z3foov() (clone 0)
|
|
; DUMP: AllocTypes: NotCold
|
|
; DUMP: ContextIds: 1
|
|
; DUMP: CalleeEdges:
|
|
; DUMP: Edge from Callee [[FOO]] to Caller: [[MAIN1]] AllocTypes: NotCold ContextIds: 1
|
|
; DUMP: CallerEdges:
|
|
|
|
; DUMP: Node [[MAIN2]]
|
|
; DUMP: %call1 = call noundef ptr @_Z3foov() (clone 0)
|
|
; DUMP: AllocTypes: Cold
|
|
; DUMP: ContextIds: 2
|
|
; DUMP: CalleeEdges:
|
|
; DUMP: Edge from Callee [[FOO]] to Caller: [[MAIN2]] AllocTypes: Cold ContextIds: 2
|
|
; DUMP: CallerEdges:
|
|
|
|
|
|
; DOT: digraph "postbuild" {
|
|
; DOT: label="postbuild";
|
|
; DOT: Node[[BAR:0x[a-z0-9]+]] [shape=record,tooltip="N[[BAR]] ContextIds: 1 2",fillcolor="mediumorchid1",style="filled",style="filled",label="{OrigId: Alloc0\n_Z3barv -\> _Znam}"];
|
|
; DOT: Node[[BAZ:0x[a-z0-9]+]] [shape=record,tooltip="N[[BAZ]] ContextIds: 1 2",fillcolor="mediumorchid1",style="filled",style="filled",label="{OrigId: 12481870273128938184\n_Z3bazv -\> _Z3barv}"];
|
|
; DOT: Node[[BAZ]] -> Node[[BAR]][tooltip="ContextIds: 1 2",fillcolor="mediumorchid1"];
|
|
; DOT: Node[[FOO:0x[a-z0-9]+]] [shape=record,tooltip="N[[FOO]] ContextIds: 1 2",fillcolor="mediumorchid1",style="filled",style="filled",label="{OrigId: 2732490490862098848\n_Z3foov -\> _Z3bazv}"];
|
|
; DOT: Node[[FOO]] -> Node[[BAZ]][tooltip="ContextIds: 1 2",fillcolor="mediumorchid1"];
|
|
; DOT: Node[[MAIN1:0x[a-z0-9]+]] [shape=record,tooltip="N[[MAIN1]] ContextIds: 1",fillcolor="brown1",style="filled",style="filled",label="{OrigId: 8632435727821051414\nmain -\> _Z3foov}"];
|
|
; DOT: Node[[MAIN1]] -> Node[[FOO]][tooltip="ContextIds: 1",fillcolor="brown1"];
|
|
; DOT: Node[[MAIN2:0x[a-z0-9]+]] [shape=record,tooltip="N[[MAIN2]] ContextIds: 2",fillcolor="cyan",style="filled",style="filled",label="{OrigId: 15025054523792398438\nmain -\> _Z3foov}"];
|
|
; DOT: Node[[MAIN2]] -> Node[[FOO]][tooltip="ContextIds: 2",fillcolor="cyan"];
|
|
; DOT: }
|