maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/TailCallElim/dont_reorder_load.ll

83 lines
2.9 KiB
LLVM
Raw Normal View History

[TailCallElim] Preserve DT and PDT Summary: Previously, in the NewPM pipeline, TailCallElim recalculates the DomTree when it modifies any instruction in the Function. For example, ``` CallInst *CI = dyn_cast<CallInst>(&I); ... CI->setTailCall(); Modified = true; ... if (!Modified || ...) return PreservedAnalyses::all(); ``` After applying this patch, the DomTree only recalculates if needed (plus an extra insertEdge() + an extra deleteEdge() call). When optimizing SQLite with `-passes="default<O3>"` pipeline of the newPM, the number of DomTree recalculation decreases by 6.2%, the number of nodes visited by DFS decreases by 2.9%. The time used by DomTree will decrease approximately 1%~2.5% after applying the patch. Statistics: ``` Before the patch: 23010 dom-tree-stats - Number of DomTree recalculations 489264 dom-tree-stats - Number of nodes visited by DFS -- DomTree After the patch: 21581 dom-tree-stats - Number of DomTree recalculations 475088 dom-tree-stats - Number of nodes visited by DFS -- DomTree ``` Reviewers: kuhar, dmgreen, brzycki, grosser, davide Reviewed By: kuhar, brzycki Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D49982 llvm-svn: 338954
2018-08-04 16:13:47 +08:00
; RUN: opt < %s -tailcallelim -verify-dom-info -S | grep call | count 4
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
; PR4323
; Several cases where tail call elimination should not move the load above the
; call, and thus can't eliminate the tail recursion.
@extern_weak_global = extern_weak global i32 ; <i32*> [#uses=1]
; This load can't be safely moved above the call because the load is from an
; extern_weak global and may trap, but the call may unwind before that happens.
define fastcc i32 @no_tailrecelim_1(i32* %a_arg, i32 %a_len_arg, i32 %start_arg) readonly {
entry:
%tmp2 = icmp sge i32 %start_arg, %a_len_arg ; <i1> [#uses=1]
br i1 %tmp2, label %if, label %else
if: ; preds = %entry
Try to eliminate the use of the 'unwind' instruction. llvm-svn: 139046
2011-09-03 06:41:11 +08:00
ret i32 37
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
else: ; preds = %entry
%tmp7 = add i32 %start_arg, 1 ; <i32> [#uses=1]
%tmp8 = call fastcc i32 @no_tailrecelim_1(i32* %a_arg, i32 %a_len_arg, i32 %tmp7) ; <i32> [#uses=1]
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp9 = load i32, i32* @extern_weak_global ; <i32> [#uses=1]
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
%tmp10 = add i32 %tmp9, %tmp8 ; <i32> [#uses=1]
ret i32 %tmp10
}
; This load can't be safely moved above the call because function may write to the pointer.
define fastcc i32 @no_tailrecelim_2(i32* %a_arg, i32 %a_len_arg, i32 %start_arg) nounwind {
entry:
%tmp2 = icmp sge i32 %start_arg, %a_len_arg ; <i1> [#uses=1]
br i1 %tmp2, label %if, label %else
if: ; preds = %entry
Delete useless trailing semicolons. llvm-svn: 92740
2010-01-06 01:55:26 +08:00
store i32 1, i32* %a_arg
ret i32 0
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
else: ; preds = %entry
%tmp7 = add i32 %start_arg, 1 ; <i32> [#uses=1]
%tmp8 = call fastcc i32 @no_tailrecelim_2(i32* %a_arg, i32 %a_len_arg, i32 %tmp7) ; <i32> [#uses=1]
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp9 = load i32, i32* %a_arg ; <i32> [#uses=1]
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
%tmp10 = add i32 %tmp9, %tmp8 ; <i32> [#uses=1]
ret i32 %tmp10
}
; This load can't be safely moved above the call because that would change the
Upgrade syntax of tests using volatile instructions to use 'load volatile' instead of 'volatile load', which is archaic. llvm-svn: 145171
2011-11-27 14:54:59 +08:00
; order in which the load volatiles are performed.
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
define fastcc i32 @no_tailrecelim_3(i32* %a_arg, i32 %a_len_arg, i32 %start_arg) nounwind {
entry:
%tmp2 = icmp sge i32 %start_arg, %a_len_arg ; <i1> [#uses=1]
br i1 %tmp2, label %if, label %else
if: ; preds = %entry
Delete useless trailing semicolons. llvm-svn: 92740
2010-01-06 01:55:26 +08:00
ret i32 0
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
else: ; preds = %entry
%tmp7 = add i32 %start_arg, 1 ; <i32> [#uses=1]
%tmp8 = call fastcc i32 @no_tailrecelim_3(i32* %a_arg, i32 %a_len_arg, i32 %tmp7) ; <i32> [#uses=1]
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp9 = load volatile i32, i32* %a_arg ; <i32> [#uses=1]
Improve tail call elim to move loads above readonly calls when it allows forming a tail call. Patch by Frits van Bommel. This implements PR4323. llvm-svn: 73752
2009-06-19 12:22:16 +08:00
%tmp10 = add i32 %tmp9, %tmp8 ; <i32> [#uses=1]
ret i32 %tmp10
}
Push isDereferenceableAndAlignedPointer down into isSafeToLoadUnconditionally Reviewed By: reames Differential Revision: http://reviews.llvm.org/D16226 llvm-svn: 258010
2016-01-17 20:35:29 +08:00
; This load can NOT be moved above the call because the a_arg is not
; sufficiently dereferenceable.
define fastcc i32 @no_tailrecelim_4(i32* dereferenceable(2) %a_arg, i32 %a_len_arg, i32 %start_arg) readonly {
entry:
%tmp2 = icmp sge i32 %start_arg, %a_len_arg ; <i1> [#uses=1]
br i1 %tmp2, label %if, label %else
if: ; preds = %entry
ret i32 0
else: ; preds = %entry
%tmp7 = add i32 %start_arg, 1 ; <i32> [#uses=1]
%tmp8 = call fastcc i32 @no_tailrecelim_4(i32* %a_arg, i32 %a_len_arg, i32 %tmp7) ; <i32> [#uses=1]
%tmp9 = load i32, i32* %a_arg ; <i32> [#uses=1]
%tmp10 = add i32 %tmp9, %tmp8 ; <i32> [#uses=1]
ret i32 %tmp10
}