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/Util/assume-builder.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1318 lines
84 KiB
LLVM
Raw Normal View History

[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature
[Utils] Make -assume-builder/-assume-simplify actually work on Old-PM clang w/ old-pm currently would simply crash when -mllvm -enable-knowledge-retention=true is specified. Clearly, these two passes had no Old-PM test coverage, which would have shown the problem - not requiring AssumptionCacheTracker, but then trying to always get it. Also, why try to get domtree only if it's cached, but at the same time marking it as required?
2020-07-05 01:04:28 +08:00
; RUN: opt -assume-builder -verify --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=BASIC
; RUN: opt -assume-builder -verify --enable-knowledge-retention --assume-preserve-all -S %s | FileCheck %s --check-prefixes=ALL
; RUN: opt -assumption-cache-tracker -assume-builder -verify --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=WITH-AC
; RUN: opt -domtree -assumption-cache-tracker -assume-builder -verify --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=CROSS-BLOCK,CROSS-BLOCK-OLDPM
; RUN: opt -assume-builder -domtree -assumption-cache-tracker -assume-simplify -verify --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=FULL-SIMPLIFY
[AssumeBundles] Preserve Information in the inliner Summary: during inling Create and insert an llvm.assume with attributes to preserve them. to prevent any changes for now generation of llvm.assume is under a flag disabled by default. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D75825
2020-03-13 21:14:55 +08:00
; RUN: opt -passes='assume-builder,verify' --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=BASIC
; RUN: opt -passes='assume-builder,verify' --enable-knowledge-retention --assume-preserve-all -S %s | FileCheck %s --check-prefixes=ALL
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; RUN: opt -passes='require<assumptions>,assume-builder,verify' --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=WITH-AC
[Utils] Make -assume-builder/-assume-simplify actually work on Old-PM clang w/ old-pm currently would simply crash when -mllvm -enable-knowledge-retention=true is specified. Clearly, these two passes had no Old-PM test coverage, which would have shown the problem - not requiring AssumptionCacheTracker, but then trying to always get it. Also, why try to get domtree only if it's cached, but at the same time marking it as required?
2020-07-05 01:04:28 +08:00
; RUN: opt -passes='require<domtree>,require<assumptions>,assume-builder,verify' --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=CROSS-BLOCK,CROSS-BLOCK-NEWMP
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; RUN: opt -passes='assume-builder,require<domtree>,require<assumptions>,assume-simplify,verify' --enable-knowledge-retention -S %s | FileCheck %s --check-prefixes=FULL-SIMPLIFY
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
declare void @func(i32*, i32*)
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
declare void @func_cold(i32*) cold willreturn nounwind
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
declare void @func_strbool(i32*) "no-jump-tables"
declare void @func_many(i32*) "no-jump-tables" nounwind "less-precise-fpmad" willreturn norecurse
declare void @func_argattr(i32* align 8, i32* nonnull) nounwind
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
declare void @may_throw()
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
define void @test(i32* %P, i32* %P1, i32* %P2, i32* %P3) {
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-LABEL: define {{[^@]+}}@test
; BASIC-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i32* [[P2:%.*]], i32* [[P3:%.*]])
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P]]), "dereferenceable"(i32* [[P]], i64 16) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; BASIC-NEXT: call void @func(i32* nonnull dereferenceable(16) [[P]], i32* null)
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 12) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; BASIC-NEXT: call void @func(i32* dereferenceable(12) [[P1]], i32* nonnull [[P]])
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]]) #6
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; BASIC-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]])
; BASIC-NEXT: call void @func(i32* [[P1]], i32* [[P]])
; BASIC-NEXT: call void @func_strbool(i32* [[P1]])
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 32) ]
; BASIC-NEXT: call void @func(i32* dereferenceable(32) [[P]], i32* dereferenceable(8) [[P]])
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P1]], i64 8) ]
; BASIC-NEXT: call void @func_many(i32* align 8 [[P1]])
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P2]], i64 8), "nonnull"(i32* [[P3]]) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; BASIC-NEXT: call void @func_argattr(i32* [[P2]], i32* [[P3]])
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P1]]) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; BASIC-NEXT: call void @func(i32* nonnull [[P1]], i32* nonnull [[P]])
; BASIC-NEXT: ret void
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-LABEL: define {{[^@]+}}@test
; ALL-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i32* [[P2:%.*]], i32* [[P3:%.*]])
; ALL-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P]]), "dereferenceable"(i32* [[P]], i64 16) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; ALL-NEXT: call void @func(i32* nonnull dereferenceable(16) [[P]], i32* null)
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 12) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; ALL-NEXT: call void @func(i32* dereferenceable(12) [[P1]], i32* nonnull [[P]])
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "cold"(), "nounwind"(), "willreturn"() ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]]) #6
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "cold"(), "nounwind"(), "willreturn"() ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; ALL-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]])
; ALL-NEXT: call void @func(i32* [[P1]], i32* [[P]])
; ALL-NEXT: call void @func_strbool(i32* [[P1]])
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 32) ]
; ALL-NEXT: call void @func(i32* dereferenceable(32) [[P]], i32* dereferenceable(8) [[P]])
[AssumeBundles] Refactor asssume builder Summary: refactor assume bulider for the next patch. the assume builder now generate only one assume per attribute kind and per value they are on. to do this it takes the highest. this is desirable because currently, for all attributes the higest value is the most valuable. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78013
2020-04-25 04:34:55 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P1]], i64 8), "norecurse"(), "nounwind"(), "willreturn"() ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; ALL-NEXT: call void @func_many(i32* align 8 [[P1]])
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P2]], i64 8), "nonnull"(i32* [[P3]]), "nounwind"() ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; ALL-NEXT: call void @func_argattr(i32* [[P2]], i32* [[P3]])
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P1]]) ]
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
; ALL-NEXT: call void @func(i32* nonnull [[P1]], i32* nonnull [[P]])
; ALL-NEXT: ret void
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-LABEL: define {{[^@]+}}@test
; WITH-AC-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i32* [[P2:%.*]], i32* [[P3:%.*]])
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P]]), "dereferenceable"(i32* [[P]], i64 16) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: call void @func(i32* nonnull dereferenceable(16) [[P]], i32* null)
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 12) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: call void @func(i32* dereferenceable(12) [[P1]], i32* nonnull [[P]])
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]]) #6
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
; WITH-AC-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]])
; WITH-AC-NEXT: call void @func(i32* [[P1]], i32* [[P]])
; WITH-AC-NEXT: call void @func_strbool(i32* [[P1]])
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 32) ]
; WITH-AC-NEXT: call void @func(i32* dereferenceable(32) [[P]], i32* dereferenceable(8) [[P]])
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P1]], i64 8) ]
; WITH-AC-NEXT: call void @func_many(i32* align 8 [[P1]])
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P2]], i64 8), "nonnull"(i32* [[P3]]) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: call void @func_argattr(i32* [[P2]], i32* [[P3]])
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P1]]) ]
; WITH-AC-NEXT: call void @func(i32* nonnull [[P1]], i32* nonnull [[P]])
; WITH-AC-NEXT: ret void
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test
; CROSS-BLOCK-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i32* [[P2:%.*]], i32* [[P3:%.*]])
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P]]), "dereferenceable"(i32* [[P]], i64 16) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: call void @func(i32* nonnull dereferenceable(16) [[P]], i32* null)
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 12) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: call void @func(i32* dereferenceable(12) [[P1]], i32* nonnull [[P]])
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]]) #6
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
; CROSS-BLOCK-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]])
; CROSS-BLOCK-NEXT: call void @func(i32* [[P1]], i32* [[P]])
; CROSS-BLOCK-NEXT: call void @func_strbool(i32* [[P1]])
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 32) ]
; CROSS-BLOCK-NEXT: call void @func(i32* dereferenceable(32) [[P]], i32* dereferenceable(8) [[P]])
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P1]], i64 8) ]
; CROSS-BLOCK-NEXT: call void @func_many(i32* align 8 [[P1]])
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P2]], i64 8), "nonnull"(i32* [[P3]]) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: call void @func_argattr(i32* [[P2]], i32* [[P3]])
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P1]]) ]
; CROSS-BLOCK-NEXT: call void @func(i32* nonnull [[P1]], i32* nonnull [[P]])
; CROSS-BLOCK-NEXT: ret void
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test
; FULL-SIMPLIFY-SAME: (i32* nonnull dereferenceable(16) [[P:%.*]], i32* [[P1:%.*]], i32* [[P2:%.*]], i32* [[P3:%.*]])
; FULL-SIMPLIFY-NEXT: call void @func(i32* nonnull dereferenceable(16) [[P]], i32* null)
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 12) ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: call void @func(i32* dereferenceable(12) [[P1]], i32* nonnull [[P]])
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "cold"() ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]]) #6
; FULL-SIMPLIFY-NEXT: call void @func_cold(i32* dereferenceable(12) [[P1]])
; FULL-SIMPLIFY-NEXT: call void @func(i32* [[P1]], i32* [[P]])
; FULL-SIMPLIFY-NEXT: call void @func_strbool(i32* [[P1]])
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 32) ]
; FULL-SIMPLIFY-NEXT: call void @func(i32* dereferenceable(32) [[P]], i32* dereferenceable(8) [[P]])
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P1]], i64 8), "align"(i32* [[P2]], i64 8), "nonnull"(i32* [[P3]]) ]
; FULL-SIMPLIFY-NEXT: call void @func_many(i32* align 8 [[P1]])
; FULL-SIMPLIFY-NEXT: call void @func_argattr(i32* [[P2]], i32* [[P3]])
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[P1]]) ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: call void @func(i32* nonnull [[P1]], i32* nonnull [[P]])
; FULL-SIMPLIFY-NEXT: ret void
;
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
call void @func(i32* nonnull dereferenceable(16) %P, i32* null)
call void @func(i32* dereferenceable(12) %P1, i32* nonnull %P)
call void @func_cold(i32* dereferenceable(12) %P1) cold
call void @func_cold(i32* dereferenceable(12) %P1)
call void @func(i32* %P1, i32* %P)
call void @func_strbool(i32* %P1)
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
call void @func(i32* dereferenceable(32) %P, i32* dereferenceable(8) %P)
Build assume from call Fix attempt this is part of the implementation of http://lists.llvm.org/pipermail/llvm-dev/2019-December/137632.html this patch gives the basis of building an assume to preserve all information from an instruction and add support for building an assume that preserve the information from a call.
2020-02-02 21:46:59 +08:00
call void @func_many(i32* align 8 %P1)
call void @func_argattr(i32* %P2, i32* %P3)
call void @func(i32* nonnull %P1, i32* nonnull %P)
ret void
}
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
%struct.S = type { i32, i8, i32* }
define i32 @test2(%struct.S* %0, i32* %1, i8* %2) {
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-LABEL: define {{[^@]+}}@test2
; BASIC-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]])
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; BASIC-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; BASIC-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; BASIC-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; BASIC-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; BASIC-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; BASIC-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; BASIC-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
; BASIC-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
; BASIC-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; BASIC-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; BASIC-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
; BASIC-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; BASIC-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; BASIC-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; BASIC-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; BASIC-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 4
; BASIC-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; BASIC-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; BASIC-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; BASIC-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
; BASIC-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; BASIC-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; BASIC-NEXT: ret i32 [[TMP28]]
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-LABEL: define {{[^@]+}}@test2
; ALL-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]])
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; ALL-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; ALL-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; ALL-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; ALL-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; ALL-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; ALL-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; ALL-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
; ALL-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
; ALL-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; ALL-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; ALL-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
; ALL-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; ALL-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; ALL-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; ALL-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; ALL-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 4
; ALL-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; ALL-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; ALL-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; ALL-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
; ALL-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; ALL-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; ALL-NEXT: ret i32 [[TMP28]]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-LABEL: define {{[^@]+}}@test2
; WITH-AC-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]])
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; WITH-AC-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; WITH-AC-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; WITH-AC-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; WITH-AC-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; WITH-AC-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; WITH-AC-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
; WITH-AC-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
; WITH-AC-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; WITH-AC-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; WITH-AC-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
; WITH-AC-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; WITH-AC-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; WITH-AC-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 4
; WITH-AC-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; WITH-AC-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; WITH-AC-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
; WITH-AC-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; WITH-AC-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; WITH-AC-NEXT: ret i32 [[TMP28]]
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test2
; CROSS-BLOCK-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]])
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; CROSS-BLOCK-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; CROSS-BLOCK-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; CROSS-BLOCK-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CROSS-BLOCK-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; CROSS-BLOCK-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; CROSS-BLOCK-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
; CROSS-BLOCK-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
; CROSS-BLOCK-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; CROSS-BLOCK-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; CROSS-BLOCK-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
; CROSS-BLOCK-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; CROSS-BLOCK-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; CROSS-BLOCK-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 4
; CROSS-BLOCK-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; CROSS-BLOCK-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; CROSS-BLOCK-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
; CROSS-BLOCK-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; CROSS-BLOCK-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; CROSS-BLOCK-NEXT: ret i32 [[TMP28]]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test2
; FULL-SIMPLIFY-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]])
; FULL-SIMPLIFY-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; FULL-SIMPLIFY-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; FULL-SIMPLIFY-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; FULL-SIMPLIFY-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
; FULL-SIMPLIFY-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; FULL-SIMPLIFY-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
; FULL-SIMPLIFY-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
; FULL-SIMPLIFY-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; FULL-SIMPLIFY-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
; FULL-SIMPLIFY-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; FULL-SIMPLIFY-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
; FULL-SIMPLIFY-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
; FULL-SIMPLIFY-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; FULL-SIMPLIFY-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; FULL-SIMPLIFY-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8), "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4), "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
; FULL-SIMPLIFY-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; FULL-SIMPLIFY-NEXT: ret i32 [[TMP28]]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
;
%4 = alloca %struct.S*, align 8
%5 = alloca i32*, align 8
%6 = alloca i8*, align 8
%7 = alloca %struct.S, align 8
store %struct.S* %0, %struct.S** %4, align 8
store i32* %1, i32** %5, align 8
store i8* %2, i8** %6
%8 = load i32*, i32** %5, align 8
%9 = load i32, i32* %8, align 4
%10 = trunc i32 %9 to i8
%11 = load i8*, i8** %6, align 8
store i8 %10, i8* %11, align 1
%12 = bitcast %struct.S* %7 to i8*
%13 = load %struct.S*, %struct.S** %4
%14 = bitcast %struct.S* %13 to i8*
%15 = bitcast %struct.S* %7 to i8*
%16 = load %struct.S*, %struct.S** %4, align 8
%17 = getelementptr inbounds %struct.S, %struct.S* %16, i32 0, i32 0
%18 = load i32, i32* %17, align 8
%19 = load %struct.S*, %struct.S** %4, align 8
%20 = getelementptr inbounds %struct.S, %struct.S* %19, i32 0, i32 1
%21 = load i8, i8* %20, align 4
%22 = sext i8 %21 to i32
%23 = add nsw i32 %18, %22
%24 = load %struct.S*, %struct.S** %4, align 8
%25 = getelementptr inbounds %struct.S, %struct.S* %24, i32 0, i32 2
%26 = load i32*, i32** %25, align 8
%27 = load i32, i32* %26, align 4
%28 = add nsw i32 %23, %27
ret i32 %28
}
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
define i32 @test3(%struct.S* %0, i32* %1, i8* %2) "null-pointer-is-valid"="true" {
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-LABEL: define {{[^@]+}}@test3
; BASIC-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]]) #4
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; BASIC-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; BASIC-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; BASIC-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; BASIC-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
; BASIC-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; BASIC-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; BASIC-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; BASIC-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; BASIC-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 32
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: call void @may_throw()
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; BASIC-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; BASIC-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; BASIC-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; BASIC-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
; BASIC-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; BASIC-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; BASIC-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; BASIC-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; BASIC-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; BASIC-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; BASIC-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; BASIC-NEXT: ret i32 [[TMP28]]
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-LABEL: define {{[^@]+}}@test3
; ALL-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]]) #4
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; ALL-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; ALL-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; ALL-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; ALL-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
; ALL-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; ALL-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; ALL-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; ALL-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; ALL-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 32
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: call void @may_throw()
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; ALL-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; ALL-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; ALL-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; ALL-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
; ALL-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; ALL-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; ALL-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; ALL-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; ALL-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
; ALL-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; ALL-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; ALL-NEXT: ret i32 [[TMP28]]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-LABEL: define {{[^@]+}}@test3
; WITH-AC-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]]) #4
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; WITH-AC-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; WITH-AC-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; WITH-AC-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
; WITH-AC-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; WITH-AC-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; WITH-AC-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; WITH-AC-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; WITH-AC-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; WITH-AC-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 32
; WITH-AC-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: call void @may_throw()
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; WITH-AC-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; WITH-AC-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
; WITH-AC-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; WITH-AC-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; WITH-AC-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; WITH-AC-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; WITH-AC-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; WITH-AC-NEXT: ret i32 [[TMP28]]
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test3
; CROSS-BLOCK-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]]) #4
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; CROSS-BLOCK-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; CROSS-BLOCK-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; CROSS-BLOCK-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
; CROSS-BLOCK-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; CROSS-BLOCK-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; CROSS-BLOCK-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; CROSS-BLOCK-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; CROSS-BLOCK-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; CROSS-BLOCK-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 32
; CROSS-BLOCK-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; CROSS-BLOCK-NEXT: call void @may_throw()
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; CROSS-BLOCK-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; CROSS-BLOCK-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4) ]
; CROSS-BLOCK-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; CROSS-BLOCK-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; CROSS-BLOCK-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; CROSS-BLOCK-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; CROSS-BLOCK-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; CROSS-BLOCK-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; CROSS-BLOCK-NEXT: ret i32 [[TMP28]]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test3
; FULL-SIMPLIFY-SAME: (%struct.S* [[TMP0:%.*]], i32* [[TMP1:%.*]], i8* [[TMP2:%.*]]) #4
; FULL-SIMPLIFY-NEXT: [[TMP4:%.*]] = alloca %struct.S*, align 8
; FULL-SIMPLIFY-NEXT: [[TMP5:%.*]] = alloca i32*, align 8
; FULL-SIMPLIFY-NEXT: [[TMP6:%.*]] = alloca i8*, align 8
; FULL-SIMPLIFY-NEXT: [[TMP7:%.*]] = alloca [[STRUCT_S:%.*]], align 8
; FULL-SIMPLIFY-NEXT: store %struct.S* [[TMP0]], %struct.S** [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: store i32* [[TMP1]], i32** [[TMP5]], align 8
; FULL-SIMPLIFY-NEXT: store i8* [[TMP2]], i8** [[TMP6]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP5]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP11:%.*]] = load i8*, i8** [[TMP6]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: store i8 [[TMP10]], i8* [[TMP11]], align 1
; FULL-SIMPLIFY-NEXT: [[TMP12:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; FULL-SIMPLIFY-NEXT: [[TMP13:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 32
; FULL-SIMPLIFY-NEXT: [[TMP14:%.*]] = bitcast %struct.S* [[TMP13]] to i8*
; FULL-SIMPLIFY-NEXT: call void @may_throw()
; FULL-SIMPLIFY-NEXT: [[TMP15:%.*]] = bitcast %struct.S* [[TMP7]] to i8*
; FULL-SIMPLIFY-NEXT: [[TMP16:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP16]], i32 0, i32 0
; FULL-SIMPLIFY-NEXT: [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP21:%.*]] = load i8, i8* [[TMP20]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP22:%.*]] = sext i8 [[TMP21]] to i32
; FULL-SIMPLIFY-NEXT: [[TMP23:%.*]] = add nsw i32 [[TMP18]], [[TMP22]]
; FULL-SIMPLIFY-NEXT: [[TMP24:%.*]] = load %struct.S*, %struct.S** [[TMP4]], align 8
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.S* [[TMP16]], i64 4), "nonnull"(%struct.S* [[TMP16]]), "align"(%struct.S* [[TMP16]], i64 8), "dereferenceable"(%struct.S* [[TMP19]], i64 5), "nonnull"(%struct.S* [[TMP19]]), "align"(%struct.S* [[TMP19]], i64 4), "dereferenceable"(%struct.S* [[TMP24]], i64 16), "nonnull"(%struct.S* [[TMP24]]), "align"(%struct.S* [[TMP24]], i64 8) ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP24]], i32 0, i32 2
Infer alignment of unmarked loads in IR/bitcode parsing. For IR generated by a compiler, this is really simple: you just take the datalayout from the beginning of the file, and apply it to all the IR later in the file. For optimization testcases that don't care about the datalayout, this is also really simple: we just use the default datalayout. The complexity here comes from the fact that some LLVM tools allow overriding the datalayout: some tools have an explicit flag for this, some tools will infer a datalayout based on the code generation target. Supporting this properly required plumbing through a bunch of new machinery: we want to allow overriding the datalayout after the datalayout is parsed from the file, but before we use any information from it. Therefore, IR/bitcode parsing now has a callback to allow tools to compute the datalayout at the appropriate time. Not sure if I covered all the LLVM tools that want to use the callback. (clang? lli? Misc IR manipulation tools like llvm-link?). But this is at least enough for all the LLVM regression tests, and IR without a datalayout is not something frontends should generate. This change had some sort of weird effects for certain CodeGen regression tests: if the datalayout is overridden with a datalayout with a different program or stack address space, we now parse IR based on the overridden datalayout, instead of the one written in the file (or the default one, if none is specified). This broke a few AVR tests, and one AMDGPU test. Outside the CodeGen tests I mentioned, the test changes are all just fixing CHECK lines and moving around datalayout lines in weird places. Differential Revision: https://reviews.llvm.org/D78403
2020-05-15 03:59:45 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP26:%.*]] = load i32*, i32** [[TMP25]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP28:%.*]] = add nsw i32 [[TMP23]], [[TMP27]]
; FULL-SIMPLIFY-NEXT: ret i32 [[TMP28]]
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
;
%4 = alloca %struct.S*, align 8
%5 = alloca i32*, align 8
%6 = alloca i8*, align 8
%7 = alloca %struct.S, align 8
store %struct.S* %0, %struct.S** %4, align 8
store i32* %1, i32** %5, align 8
store i8* %2, i8** %6, align 8
%8 = load i32*, i32** %5, align 8
%9 = load i32, i32* %8, align 4
%10 = trunc i32 %9 to i8
%11 = load i8*, i8** %6
store i8 %10, i8* %11, align 1
%12 = bitcast %struct.S* %7 to i8*
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
%13 = load %struct.S*, %struct.S** %4, align 32
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
%14 = bitcast %struct.S* %13 to i8*
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
call void @may_throw()
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
%15 = bitcast %struct.S* %7 to i8*
%16 = load %struct.S*, %struct.S** %4, align 8
%17 = getelementptr inbounds %struct.S, %struct.S* %16, i32 0, i32 0
%18 = load i32, i32* %17, align 8
%19 = load %struct.S*, %struct.S** %4, align 8
%20 = getelementptr inbounds %struct.S, %struct.S* %19, i32 0, i32 1
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
%21 = load i8, i8* %20, align 8
[AssumeBundles] Preserve Information from Load/Store Summary: This patch preserve dereferenceable, nonnull and alignment from loads and stores. Reviewers: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76759
2020-03-26 04:55:35 +08:00
%22 = sext i8 %21 to i32
%23 = add nsw i32 %18, %22
%24 = load %struct.S*, %struct.S** %4, align 8
%25 = getelementptr inbounds %struct.S, %struct.S* %24, i32 0, i32 2
%26 = load i32*, i32** %25
%27 = load i32, i32* %26, align 4
%28 = add nsw i32 %23, %27
ret i32 %28
}
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
define dso_local i32 @_Z6squarePi(i32* %P, i32* %P1, i1 %cond) {
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-LABEL: define {{[^@]+}}@_Z6squarePi
; BASIC-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i1 [[COND:%.*]])
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P]], align 4
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P1]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; BASIC-NEXT: br i1 [[COND]], label [[A:%.*]], label [[B:%.*]]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC: A:
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P]], align 8
; BASIC-NEXT: store i32 0, i32* [[P1]], align 4
; BASIC-NEXT: br i1 [[COND]], label [[C:%.*]], label [[B]]
; BASIC: B:
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P]], align 8
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P1]], align 8
; BASIC-NEXT: br label [[C]]
; BASIC: C:
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 32) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P]], align 32
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; BASIC-NEXT: store i32 0, i32* [[P1]], align 4
; BASIC-NEXT: ret i32 0
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-LABEL: define {{[^@]+}}@_Z6squarePi
; ALL-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i1 [[COND:%.*]])
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P]], align 4
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P1]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; ALL-NEXT: br i1 [[COND]], label [[A:%.*]], label [[B:%.*]]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL: A:
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P]], align 8
; ALL-NEXT: store i32 0, i32* [[P1]], align 4
; ALL-NEXT: br i1 [[COND]], label [[C:%.*]], label [[B]]
; ALL: B:
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P]], align 8
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P1]], align 8
; ALL-NEXT: br label [[C]]
; ALL: C:
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 32) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P]], align 32
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; ALL-NEXT: store i32 0, i32* [[P1]], align 4
; ALL-NEXT: ret i32 0
;
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-LABEL: define {{[^@]+}}@_Z6squarePi
; WITH-AC-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i1 [[COND:%.*]])
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i32 0, i32* [[P]], align 4
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i32 0, i32* [[P1]], align 8
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; WITH-AC-NEXT: br i1 [[COND]], label [[A:%.*]], label [[B:%.*]]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC: A:
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
; WITH-AC-NEXT: store i32 0, i32* [[P]], align 8
; WITH-AC-NEXT: store i32 0, i32* [[P1]], align 4
; WITH-AC-NEXT: br i1 [[COND]], label [[C:%.*]], label [[B]]
; WITH-AC: B:
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i32 0, i32* [[P]], align 8
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i32 0, i32* [[P1]], align 8
; WITH-AC-NEXT: br label [[C]]
; WITH-AC: C:
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 32) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i32 0, i32* [[P]], align 32
[AssumeBundles] Remove non-determinisme from assume builder Summary: The assume builder was non-deterministic when working on unamed values. this patch fixes this. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, mgrang, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78616
2020-05-11 01:26:41 +08:00
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 4) ]
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
; WITH-AC-NEXT: store i32 0, i32* [[P1]], align 4
; WITH-AC-NEXT: ret i32 0
;
[Utils] Make -assume-builder/-assume-simplify actually work on Old-PM clang w/ old-pm currently would simply crash when -mllvm -enable-knowledge-retention=true is specified. Clearly, these two passes had no Old-PM test coverage, which would have shown the problem - not requiring AssumptionCacheTracker, but then trying to always get it. Also, why try to get domtree only if it's cached, but at the same time marking it as required?
2020-07-05 01:04:28 +08:00
; CROSS-BLOCK-OLDPM-LABEL: define {{[^@]+}}@_Z6squarePi
; CROSS-BLOCK-OLDPM-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i1 [[COND:%.*]])
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 4) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P]], align 4
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P1]], align 8
; CROSS-BLOCK-OLDPM-NEXT: br i1 [[COND]], label [[A:%.*]], label [[B:%.*]]
; CROSS-BLOCK-OLDPM: A:
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P]], align 8
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P1]], align 4
; CROSS-BLOCK-OLDPM-NEXT: br i1 [[COND]], label [[C:%.*]], label [[B]]
; CROSS-BLOCK-OLDPM: B:
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 8) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P]], align 8
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P1]], align 8
; CROSS-BLOCK-OLDPM-NEXT: br label [[C]]
; CROSS-BLOCK-OLDPM: C:
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 32) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P]], align 32
; CROSS-BLOCK-OLDPM-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 4) ]
; CROSS-BLOCK-OLDPM-NEXT: store i32 0, i32* [[P1]], align 4
; CROSS-BLOCK-OLDPM-NEXT: ret i32 0
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@_Z6squarePi
; FULL-SIMPLIFY-SAME: (i32* nonnull align 4 dereferenceable(4) [[P:%.*]], i32* nonnull align 8 dereferenceable(4) [[P1:%.*]], i1 [[COND:%.*]])
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P]], align 4
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P1]], align 8
; FULL-SIMPLIFY-NEXT: br i1 [[COND]], label [[A:%.*]], label [[B:%.*]]
; FULL-SIMPLIFY: A:
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P]], align 8
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P1]], align 4
; FULL-SIMPLIFY-NEXT: br i1 [[COND]], label [[C:%.*]], label [[B]]
; FULL-SIMPLIFY: B:
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "ignore"(i32* undef, i64 4), "ignore"(i32* undef), "align"(i32* [[P]], i64 8) ]
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P]], align 8
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P1]], align 8
; FULL-SIMPLIFY-NEXT: br label [[C]]
; FULL-SIMPLIFY: C:
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "ignore"(i32* undef, i64 4), "ignore"(i32* undef), "align"(i32* [[P]], i64 32) ]
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P]], align 32
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[P1]], align 4
; FULL-SIMPLIFY-NEXT: ret i32 0
[Utils] Make -assume-builder/-assume-simplify actually work on Old-PM clang w/ old-pm currently would simply crash when -mllvm -enable-knowledge-retention=true is specified. Clearly, these two passes had no Old-PM test coverage, which would have shown the problem - not requiring AssumptionCacheTracker, but then trying to always get it. Also, why try to get domtree only if it's cached, but at the same time marking it as required?
2020-07-05 01:04:28 +08:00
;
; CROSS-BLOCK-NEWMP-LABEL: define {{[^@]+}}@_Z6squarePi
; CROSS-BLOCK-NEWMP-SAME: (i32* [[P:%.*]], i32* [[P1:%.*]], i1 [[COND:%.*]])
; CROSS-BLOCK-NEWMP-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P]], i64 4), "nonnull"(i32* [[P]]), "align"(i32* [[P]], i64 4) ]
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P]], align 4
; CROSS-BLOCK-NEWMP-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[P1]], i64 4), "nonnull"(i32* [[P1]]), "align"(i32* [[P1]], i64 8) ]
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P1]], align 8
; CROSS-BLOCK-NEWMP-NEXT: br i1 [[COND]], label [[A:%.*]], label [[B:%.*]]
; CROSS-BLOCK-NEWMP: A:
; CROSS-BLOCK-NEWMP-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P]], align 8
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P1]], align 4
; CROSS-BLOCK-NEWMP-NEXT: br i1 [[COND]], label [[C:%.*]], label [[B]]
; CROSS-BLOCK-NEWMP: B:
; CROSS-BLOCK-NEWMP-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 8) ]
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P]], align 8
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P1]], align 8
; CROSS-BLOCK-NEWMP-NEXT: br label [[C]]
; CROSS-BLOCK-NEWMP: C:
; CROSS-BLOCK-NEWMP-NEXT: call void @llvm.assume(i1 true) [ "align"(i32* [[P]], i64 32) ]
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P]], align 32
; CROSS-BLOCK-NEWMP-NEXT: store i32 0, i32* [[P1]], align 4
; CROSS-BLOCK-NEWMP-NEXT: ret i32 0
[AssumeBundles] Prevent generation of some redundant assumes Summary: with this patch the assume salvageKnowledge will not generate assume if all knowledge is already available in an assume with valid context. assume bulider can also in some cases update an existing assume with better information. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D78014
2020-05-11 00:20:34 +08:00
;
store i32 0, i32* %P, align 4
store i32 0, i32* %P1, align 8
br i1 %cond, label %A, label %B
A:
store i32 0, i32* %P, align 8
store i32 0, i32* %P1, align 4
br i1 %cond, label %C, label %B
B:
store i32 0, i32* %P, align 8
store i32 0, i32* %P1, align 8
br label %C
C:
store i32 0, i32* %P, align 32
store i32 0, i32* %P1, align 4
ret i32 0
}
[NFC][DwarfDebug] Add test for variables with a single location which don't span their entire scope. The previous commit (6d1c40c171e) is an older version of the test. Reviewed By: aprantl, vsk Differential Revision: https://reviews.llvm.org/D79573
2020-05-07 19:41:20 +08:00
define dso_local i32 @test4A(i32* %0, i32* %1, i32 %2, i32 %3) {
; BASIC-LABEL: define {{[^@]+}}@test4A
; BASIC-SAME: (i32* [[TMP0:%.*]], i32* [[TMP1:%.*]], i32 [[TMP2:%.*]], i32 [[TMP3:%.*]])
; BASIC-NEXT: [[TMP5:%.*]] = icmp ne i32* [[TMP1]], null
; BASIC-NEXT: br i1 [[TMP5]], label [[TMP6:%.*]], label [[TMP12:%.*]]
; BASIC: 6:
; BASIC-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP3]], [[TMP2]]
; BASIC-NEXT: call void @may_throw()
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP0]], i64 4), "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; BASIC-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP0]], align 4
; BASIC-NEXT: [[TMP9:%.*]] = add nsw i32 [[TMP7]], [[TMP8]]
; BASIC-NEXT: store i32 0, i32* [[TMP0]], align 4
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP1]], i64 4), "nonnull"(i32* [[TMP1]]), "align"(i32* [[TMP1]], i64 4) ]
; BASIC-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP1]], align 4
; BASIC-NEXT: [[TMP11:%.*]] = add nsw i32 [[TMP9]], [[TMP10]]
; BASIC-NEXT: call void @may_throw()
; BASIC-NEXT: store i32 [[TMP11]], i32* [[TMP1]], align 4
; BASIC-NEXT: br label [[TMP12]]
; BASIC: 12:
; BASIC-NEXT: ret i32 0
;
; ALL-LABEL: define {{[^@]+}}@test4A
; ALL-SAME: (i32* [[TMP0:%.*]], i32* [[TMP1:%.*]], i32 [[TMP2:%.*]], i32 [[TMP3:%.*]])
; ALL-NEXT: [[TMP5:%.*]] = icmp ne i32* [[TMP1]], null
; ALL-NEXT: br i1 [[TMP5]], label [[TMP6:%.*]], label [[TMP12:%.*]]
; ALL: 6:
; ALL-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP3]], [[TMP2]]
; ALL-NEXT: call void @may_throw()
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP0]], i64 4), "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; ALL-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP0]], align 4
; ALL-NEXT: [[TMP9:%.*]] = add nsw i32 [[TMP7]], [[TMP8]]
; ALL-NEXT: store i32 0, i32* [[TMP0]], align 4
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP1]], i64 4), "nonnull"(i32* [[TMP1]]), "align"(i32* [[TMP1]], i64 4) ]
; ALL-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP1]], align 4
; ALL-NEXT: [[TMP11:%.*]] = add nsw i32 [[TMP9]], [[TMP10]]
; ALL-NEXT: call void @may_throw()
; ALL-NEXT: store i32 [[TMP11]], i32* [[TMP1]], align 4
; ALL-NEXT: br label [[TMP12]]
; ALL: 12:
; ALL-NEXT: ret i32 0
;
; WITH-AC-LABEL: define {{[^@]+}}@test4A
; WITH-AC-SAME: (i32* [[TMP0:%.*]], i32* [[TMP1:%.*]], i32 [[TMP2:%.*]], i32 [[TMP3:%.*]])
; WITH-AC-NEXT: [[TMP5:%.*]] = icmp ne i32* [[TMP1]], null
; WITH-AC-NEXT: br i1 [[TMP5]], label [[TMP6:%.*]], label [[TMP12:%.*]]
; WITH-AC: 6:
; WITH-AC-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP3]], [[TMP2]]
; WITH-AC-NEXT: call void @may_throw()
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP0]], i64 4), "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; WITH-AC-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP0]], align 4
; WITH-AC-NEXT: [[TMP9:%.*]] = add nsw i32 [[TMP7]], [[TMP8]]
; WITH-AC-NEXT: store i32 0, i32* [[TMP0]], align 4
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP1]], i64 4), "nonnull"(i32* [[TMP1]]), "align"(i32* [[TMP1]], i64 4) ]
; WITH-AC-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP1]], align 4
; WITH-AC-NEXT: [[TMP11:%.*]] = add nsw i32 [[TMP9]], [[TMP10]]
; WITH-AC-NEXT: call void @may_throw()
; WITH-AC-NEXT: store i32 [[TMP11]], i32* [[TMP1]], align 4
; WITH-AC-NEXT: br label [[TMP12]]
; WITH-AC: 12:
; WITH-AC-NEXT: ret i32 0
;
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test4A
; CROSS-BLOCK-SAME: (i32* [[TMP0:%.*]], i32* [[TMP1:%.*]], i32 [[TMP2:%.*]], i32 [[TMP3:%.*]])
; CROSS-BLOCK-NEXT: [[TMP5:%.*]] = icmp ne i32* [[TMP1]], null
; CROSS-BLOCK-NEXT: br i1 [[TMP5]], label [[TMP6:%.*]], label [[TMP12:%.*]]
; CROSS-BLOCK: 6:
; CROSS-BLOCK-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP3]], [[TMP2]]
; CROSS-BLOCK-NEXT: call void @may_throw()
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP0]], i64 4), "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; CROSS-BLOCK-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP0]], align 4
; CROSS-BLOCK-NEXT: [[TMP9:%.*]] = add nsw i32 [[TMP7]], [[TMP8]]
; CROSS-BLOCK-NEXT: store i32 0, i32* [[TMP0]], align 4
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP1]], i64 4), "nonnull"(i32* [[TMP1]]), "align"(i32* [[TMP1]], i64 4) ]
; CROSS-BLOCK-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP1]], align 4
; CROSS-BLOCK-NEXT: [[TMP11:%.*]] = add nsw i32 [[TMP9]], [[TMP10]]
; CROSS-BLOCK-NEXT: call void @may_throw()
; CROSS-BLOCK-NEXT: store i32 [[TMP11]], i32* [[TMP1]], align 4
; CROSS-BLOCK-NEXT: br label [[TMP12]]
; CROSS-BLOCK: 12:
; CROSS-BLOCK-NEXT: ret i32 0
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test4A
; FULL-SIMPLIFY-SAME: (i32* [[TMP0:%.*]], i32* [[TMP1:%.*]], i32 [[TMP2:%.*]], i32 [[TMP3:%.*]])
; FULL-SIMPLIFY-NEXT: [[TMP5:%.*]] = icmp ne i32* [[TMP1]], null
; FULL-SIMPLIFY-NEXT: br i1 [[TMP5]], label [[TMP6:%.*]], label [[TMP12:%.*]]
; FULL-SIMPLIFY: 6:
; FULL-SIMPLIFY-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP3]], [[TMP2]]
; FULL-SIMPLIFY-NEXT: call void @may_throw()
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP0]], i64 4), "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4), "dereferenceable"(i32* [[TMP1]], i64 4), "nonnull"(i32* [[TMP1]]), "align"(i32* [[TMP1]], i64 4) ]
; FULL-SIMPLIFY-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP0]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP9:%.*]] = add nsw i32 [[TMP7]], [[TMP8]]
; FULL-SIMPLIFY-NEXT: store i32 0, i32* [[TMP0]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP1]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP11:%.*]] = add nsw i32 [[TMP9]], [[TMP10]]
; FULL-SIMPLIFY-NEXT: call void @may_throw()
; FULL-SIMPLIFY-NEXT: store i32 [[TMP11]], i32* [[TMP1]], align 4
; FULL-SIMPLIFY-NEXT: br label [[TMP12]]
; FULL-SIMPLIFY: 12:
; FULL-SIMPLIFY-NEXT: ret i32 0
;
%5 = icmp ne i32* %1, null
br i1 %5, label %6, label %12
6: ; preds = %4
%7 = add nsw i32 %3, %2
call void @may_throw()
%8 = load i32, i32* %0, align 4
%9 = add nsw i32 %7, %8
store i32 0, i32* %0, align 4
%10 = load i32, i32* %1, align 4
%11 = add nsw i32 %9, %10
call void @may_throw()
store i32 %11, i32* %1, align 4
br label %12
12: ; preds = %6, %4
ret i32 0
}
[AssumeBundles] fix crashes Summary: this patch fixe crash/asserts found in the test-suite. the AssumeptionCache cannot be assumed to have all assumes contrary to what i tought. prevent generation of information for terminators, because this can create broken IR in transfromation where we insert the new terminator before removing the old one. Reviewers: jdoerfert Reviewed By: jdoerfert Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79458
2020-05-11 17:50:35 +08:00
declare void @may_throwv2(i32* %P)
define dso_local i32 @terminator(i32* %P) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
; BASIC-LABEL: define {{[^@]+}}@terminator
; BASIC-SAME: (i32* [[P:%.*]]) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
; BASIC-NEXT: invoke void @may_throwv2(i32* nonnull [[P]])
; BASIC-NEXT: to label [[EXIT:%.*]] unwind label [[CATCH:%.*]]
; BASIC: Catch:
; BASIC-NEXT: [[V:%.*]] = landingpad { i8*, i32 }
; BASIC-NEXT: catch i8* null
; BASIC-NEXT: br label [[EXIT]]
; BASIC: Exit:
; BASIC-NEXT: [[DOT0:%.*]] = phi i32 [ 1, [[TMP0:%.*]] ], [ 0, [[CATCH]] ]
; BASIC-NEXT: ret i32 [[DOT0]]
;
; ALL-LABEL: define {{[^@]+}}@terminator
; ALL-SAME: (i32* [[P:%.*]]) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
; ALL-NEXT: invoke void @may_throwv2(i32* nonnull [[P]])
; ALL-NEXT: to label [[EXIT:%.*]] unwind label [[CATCH:%.*]]
; ALL: Catch:
; ALL-NEXT: [[V:%.*]] = landingpad { i8*, i32 }
; ALL-NEXT: catch i8* null
; ALL-NEXT: br label [[EXIT]]
; ALL: Exit:
; ALL-NEXT: [[DOT0:%.*]] = phi i32 [ 1, [[TMP0:%.*]] ], [ 0, [[CATCH]] ]
; ALL-NEXT: ret i32 [[DOT0]]
;
; WITH-AC-LABEL: define {{[^@]+}}@terminator
; WITH-AC-SAME: (i32* [[P:%.*]]) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
; WITH-AC-NEXT: invoke void @may_throwv2(i32* nonnull [[P]])
; WITH-AC-NEXT: to label [[EXIT:%.*]] unwind label [[CATCH:%.*]]
; WITH-AC: Catch:
; WITH-AC-NEXT: [[V:%.*]] = landingpad { i8*, i32 }
; WITH-AC-NEXT: catch i8* null
; WITH-AC-NEXT: br label [[EXIT]]
; WITH-AC: Exit:
; WITH-AC-NEXT: [[DOT0:%.*]] = phi i32 [ 1, [[TMP0:%.*]] ], [ 0, [[CATCH]] ]
; WITH-AC-NEXT: ret i32 [[DOT0]]
;
; CROSS-BLOCK-LABEL: define {{[^@]+}}@terminator
; CROSS-BLOCK-SAME: (i32* [[P:%.*]]) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
; CROSS-BLOCK-NEXT: invoke void @may_throwv2(i32* nonnull [[P]])
; CROSS-BLOCK-NEXT: to label [[EXIT:%.*]] unwind label [[CATCH:%.*]]
; CROSS-BLOCK: Catch:
; CROSS-BLOCK-NEXT: [[V:%.*]] = landingpad { i8*, i32 }
; CROSS-BLOCK-NEXT: catch i8* null
; CROSS-BLOCK-NEXT: br label [[EXIT]]
; CROSS-BLOCK: Exit:
; CROSS-BLOCK-NEXT: [[DOT0:%.*]] = phi i32 [ 1, [[TMP0:%.*]] ], [ 0, [[CATCH]] ]
; CROSS-BLOCK-NEXT: ret i32 [[DOT0]]
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@terminator
; FULL-SIMPLIFY-SAME: (i32* [[P:%.*]]) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
; FULL-SIMPLIFY-NEXT: invoke void @may_throwv2(i32* nonnull [[P]])
; FULL-SIMPLIFY-NEXT: to label [[EXIT:%.*]] unwind label [[CATCH:%.*]]
; FULL-SIMPLIFY: Catch:
; FULL-SIMPLIFY-NEXT: [[V:%.*]] = landingpad { i8*, i32 }
; FULL-SIMPLIFY-NEXT: catch i8* null
; FULL-SIMPLIFY-NEXT: br label [[EXIT]]
; FULL-SIMPLIFY: Exit:
; FULL-SIMPLIFY-NEXT: [[DOT0:%.*]] = phi i32 [ 1, [[TMP0:%.*]] ], [ 0, [[CATCH]] ]
; FULL-SIMPLIFY-NEXT: ret i32 [[DOT0]]
;
invoke void @may_throwv2(i32* nonnull %P)
to label %Exit unwind label %Catch
Catch: ; preds = %0
%v = landingpad { i8*, i32 }
catch i8* null
br label %Exit
Exit: ; preds = %7, %5
%.0 = phi i32 [ 1, %0 ], [ 0, %Catch ]
ret i32 %.0
}
declare dso_local i32 @__gxx_personality_v0(...)
[AssumeBundles] add cannonicalisation to the assume builder Summary: this reduces significantly the number of assumes generated without aftecting too much the information that is preserved. this improves the compile-time cost of enable-knowledge-retention significantly. Reviewers: jdoerfert, sstefan1 Reviewed By: jdoerfert Subscribers: hiraditya, asbirlea, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79650
2020-06-19 16:32:09 +08:00
define dso_local i32 @test5(i8* %0, i32 %1) {
; BASIC-LABEL: define {{[^@]+}}@test5
; BASIC-SAME: (i8* [[TMP0:%.*]], i32 [[TMP1:%.*]])
; BASIC-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to i64*
; BASIC-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP0]] to i16*
; BASIC-NEXT: [[TMP5:%.*]] = sext i32 [[TMP1]] to i64
; BASIC-NEXT: [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[TMP4]], i64 [[TMP5]]
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i16* [[TMP6]], i64 2), "nonnull"(i8* [[TMP0]]), "align"(i8* [[TMP0]], i64 8) ]
; BASIC-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; BASIC-NEXT: [[A:%.*]] = load i16, i16* [[TMP6]], align 4
; BASIC-NEXT: [[TMP8:%.*]] = sext i16 [[TMP7]] to i64
; BASIC-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, i64* [[TMP3]], i64 [[TMP8]]
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP9]], i64 8) ]
; BASIC-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP9]], align 16
; BASIC-NEXT: [[B:%.*]] = load i64, i64* [[TMP9]], align 32
; BASIC-NEXT: [[TMP11:%.*]] = trunc i64 [[TMP10]] to i32
; BASIC-NEXT: ret i32 [[TMP11]]
;
; ALL-LABEL: define {{[^@]+}}@test5
; ALL-SAME: (i8* [[TMP0:%.*]], i32 [[TMP1:%.*]])
; ALL-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to i64*
; ALL-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP0]] to i16*
; ALL-NEXT: [[TMP5:%.*]] = sext i32 [[TMP1]] to i64
; ALL-NEXT: [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[TMP4]], i64 [[TMP5]]
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i16* [[TMP6]], i64 2), "nonnull"(i8* [[TMP0]]), "align"(i8* [[TMP0]], i64 8) ]
; ALL-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; ALL-NEXT: [[A:%.*]] = load i16, i16* [[TMP6]], align 4
; ALL-NEXT: [[TMP8:%.*]] = sext i16 [[TMP7]] to i64
; ALL-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, i64* [[TMP3]], i64 [[TMP8]]
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP9]], i64 8) ]
; ALL-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP9]], align 16
; ALL-NEXT: [[B:%.*]] = load i64, i64* [[TMP9]], align 32
; ALL-NEXT: [[TMP11:%.*]] = trunc i64 [[TMP10]] to i32
; ALL-NEXT: ret i32 [[TMP11]]
;
; WITH-AC-LABEL: define {{[^@]+}}@test5
; WITH-AC-SAME: (i8* [[TMP0:%.*]], i32 [[TMP1:%.*]])
; WITH-AC-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to i64*
; WITH-AC-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP0]] to i16*
; WITH-AC-NEXT: [[TMP5:%.*]] = sext i32 [[TMP1]] to i64
; WITH-AC-NEXT: [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[TMP4]], i64 [[TMP5]]
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i16* [[TMP6]], i64 2), "nonnull"(i8* [[TMP0]]), "align"(i8* [[TMP0]], i64 8) ]
; WITH-AC-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; WITH-AC-NEXT: [[A:%.*]] = load i16, i16* [[TMP6]], align 4
; WITH-AC-NEXT: [[TMP8:%.*]] = sext i16 [[TMP7]] to i64
; WITH-AC-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, i64* [[TMP3]], i64 [[TMP8]]
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP9]], i64 8) ]
; WITH-AC-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP9]], align 16
; WITH-AC-NEXT: [[B:%.*]] = load i64, i64* [[TMP9]], align 32
; WITH-AC-NEXT: [[TMP11:%.*]] = trunc i64 [[TMP10]] to i32
; WITH-AC-NEXT: ret i32 [[TMP11]]
;
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test5
; CROSS-BLOCK-SAME: (i8* [[TMP0:%.*]], i32 [[TMP1:%.*]])
; CROSS-BLOCK-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to i64*
; CROSS-BLOCK-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP0]] to i16*
; CROSS-BLOCK-NEXT: [[TMP5:%.*]] = sext i32 [[TMP1]] to i64
; CROSS-BLOCK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[TMP4]], i64 [[TMP5]]
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i16* [[TMP6]], i64 2), "nonnull"(i8* [[TMP0]]), "align"(i8* [[TMP0]], i64 8) ]
; CROSS-BLOCK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; CROSS-BLOCK-NEXT: [[A:%.*]] = load i16, i16* [[TMP6]], align 4
; CROSS-BLOCK-NEXT: [[TMP8:%.*]] = sext i16 [[TMP7]] to i64
; CROSS-BLOCK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, i64* [[TMP3]], i64 [[TMP8]]
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP9]], i64 8) ]
; CROSS-BLOCK-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP9]], align 16
; CROSS-BLOCK-NEXT: [[B:%.*]] = load i64, i64* [[TMP9]], align 32
; CROSS-BLOCK-NEXT: [[TMP11:%.*]] = trunc i64 [[TMP10]] to i32
; CROSS-BLOCK-NEXT: ret i32 [[TMP11]]
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test5
; FULL-SIMPLIFY-SAME: (i8* nonnull align 8 [[TMP0:%.*]], i32 [[TMP1:%.*]])
; FULL-SIMPLIFY-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP0]] to i64*
; FULL-SIMPLIFY-NEXT: [[TMP4:%.*]] = bitcast i8* [[TMP0]] to i16*
; FULL-SIMPLIFY-NEXT: [[TMP5:%.*]] = sext i32 [[TMP1]] to i64
; FULL-SIMPLIFY-NEXT: [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[TMP4]], i64 [[TMP5]]
; FULL-SIMPLIFY-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; FULL-SIMPLIFY-NEXT: [[A:%.*]] = load i16, i16* [[TMP6]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP8:%.*]] = sext i16 [[TMP7]] to i64
; FULL-SIMPLIFY-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, i64* [[TMP3]], i64 [[TMP8]]
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i16* [[TMP6]], i64 2), "dereferenceable"(i64* [[TMP9]], i64 8) ]
; FULL-SIMPLIFY-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP9]], align 16
; FULL-SIMPLIFY-NEXT: [[B:%.*]] = load i64, i64* [[TMP9]], align 32
; FULL-SIMPLIFY-NEXT: [[TMP11:%.*]] = trunc i64 [[TMP10]] to i32
; FULL-SIMPLIFY-NEXT: ret i32 [[TMP11]]
;
%3 = bitcast i8* %0 to i64*
%4 = bitcast i8* %0 to i16*
%5 = sext i32 %1 to i64
%6 = getelementptr inbounds i16, i16* %4, i64 %5
%7 = load i16, i16* %6, align 2
%A = load i16, i16* %6, align 4
%8 = sext i16 %7 to i64
%9 = getelementptr inbounds i64, i64* %3, i64 %8
%10 = load i64, i64* %9, align 16
%B = load i64, i64* %9, align 32
%11 = trunc i64 %10 to i32
ret i32 %11
}
define i32 @test6(i32* %0, i32 %1, i32* %2) {
; BASIC-LABEL: define {{[^@]+}}@test6
; BASIC-SAME: (i32* [[TMP0:%.*]], i32 [[TMP1:%.*]], i32* [[TMP2:%.*]])
; BASIC-NEXT: br label [[TMP4:%.*]]
; BASIC: 4:
; BASIC-NEXT: [[DOT0:%.*]] = phi i32 [ 0, [[TMP3:%.*]] ], [ [[TMP16:%.*]], [[TMP6:%.*]] ]
; BASIC-NEXT: [[TMP5:%.*]] = icmp slt i32 [[DOT0]], [[TMP1]]
; BASIC-NEXT: br i1 [[TMP5]], label [[TMP6]], label [[TMP17:%.*]]
; BASIC: 6:
; BASIC-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP1]], [[DOT0]]
; BASIC-NEXT: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; BASIC-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP8]]
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; BASIC-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
; BASIC-NEXT: [[TMP11:%.*]] = mul nsw i32 [[DOT0]], [[TMP10]]
; BASIC-NEXT: [[TMP12:%.*]] = sext i32 [[DOT0]] to i64
; BASIC-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP12]]
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP13]], i64 4) ]
; BASIC-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
; BASIC-NEXT: [[TMP15:%.*]] = add nsw i32 [[TMP14]], [[TMP11]]
; BASIC-NEXT: store i32 [[TMP15]], i32* [[TMP13]], align 4
; BASIC-NEXT: [[TMP16]] = add nsw i32 [[DOT0]], 1
; BASIC-NEXT: br label [[TMP4]]
; BASIC: 17:
; BASIC-NEXT: [[TMP18:%.*]] = sext i32 [[TMP1]] to i64
; BASIC-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 [[TMP18]]
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP2]]), "align"(i32* [[TMP2]], i64 4) ]
; BASIC-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
; BASIC-NEXT: ret i32 [[TMP20]]
;
; ALL-LABEL: define {{[^@]+}}@test6
; ALL-SAME: (i32* [[TMP0:%.*]], i32 [[TMP1:%.*]], i32* [[TMP2:%.*]])
; ALL-NEXT: br label [[TMP4:%.*]]
; ALL: 4:
; ALL-NEXT: [[DOT0:%.*]] = phi i32 [ 0, [[TMP3:%.*]] ], [ [[TMP16:%.*]], [[TMP6:%.*]] ]
; ALL-NEXT: [[TMP5:%.*]] = icmp slt i32 [[DOT0]], [[TMP1]]
; ALL-NEXT: br i1 [[TMP5]], label [[TMP6]], label [[TMP17:%.*]]
; ALL: 6:
; ALL-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP1]], [[DOT0]]
; ALL-NEXT: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; ALL-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP8]]
; ALL-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; ALL-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
; ALL-NEXT: [[TMP11:%.*]] = mul nsw i32 [[DOT0]], [[TMP10]]
; ALL-NEXT: [[TMP12:%.*]] = sext i32 [[DOT0]] to i64
; ALL-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP12]]
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP13]], i64 4) ]
; ALL-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
; ALL-NEXT: [[TMP15:%.*]] = add nsw i32 [[TMP14]], [[TMP11]]
; ALL-NEXT: store i32 [[TMP15]], i32* [[TMP13]], align 4
; ALL-NEXT: [[TMP16]] = add nsw i32 [[DOT0]], 1
; ALL-NEXT: br label [[TMP4]]
; ALL: 17:
; ALL-NEXT: [[TMP18:%.*]] = sext i32 [[TMP1]] to i64
; ALL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 [[TMP18]]
; ALL-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP2]]), "align"(i32* [[TMP2]], i64 4) ]
; ALL-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
; ALL-NEXT: ret i32 [[TMP20]]
;
; WITH-AC-LABEL: define {{[^@]+}}@test6
; WITH-AC-SAME: (i32* [[TMP0:%.*]], i32 [[TMP1:%.*]], i32* [[TMP2:%.*]])
; WITH-AC-NEXT: br label [[TMP4:%.*]]
; WITH-AC: 4:
; WITH-AC-NEXT: [[DOT0:%.*]] = phi i32 [ 0, [[TMP3:%.*]] ], [ [[TMP16:%.*]], [[TMP6:%.*]] ]
; WITH-AC-NEXT: [[TMP5:%.*]] = icmp slt i32 [[DOT0]], [[TMP1]]
; WITH-AC-NEXT: br i1 [[TMP5]], label [[TMP6]], label [[TMP17:%.*]]
; WITH-AC: 6:
; WITH-AC-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP1]], [[DOT0]]
; WITH-AC-NEXT: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; WITH-AC-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP8]]
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; WITH-AC-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
; WITH-AC-NEXT: [[TMP11:%.*]] = mul nsw i32 [[DOT0]], [[TMP10]]
; WITH-AC-NEXT: [[TMP12:%.*]] = sext i32 [[DOT0]] to i64
; WITH-AC-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP12]]
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP13]], i64 4) ]
; WITH-AC-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
; WITH-AC-NEXT: [[TMP15:%.*]] = add nsw i32 [[TMP14]], [[TMP11]]
; WITH-AC-NEXT: store i32 [[TMP15]], i32* [[TMP13]], align 4
; WITH-AC-NEXT: [[TMP16]] = add nsw i32 [[DOT0]], 1
; WITH-AC-NEXT: br label [[TMP4]]
; WITH-AC: 17:
; WITH-AC-NEXT: [[TMP18:%.*]] = sext i32 [[TMP1]] to i64
; WITH-AC-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 [[TMP18]]
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP2]]), "align"(i32* [[TMP2]], i64 4) ]
; WITH-AC-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
; WITH-AC-NEXT: ret i32 [[TMP20]]
;
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test6
; CROSS-BLOCK-SAME: (i32* [[TMP0:%.*]], i32 [[TMP1:%.*]], i32* [[TMP2:%.*]])
; CROSS-BLOCK-NEXT: br label [[TMP4:%.*]]
; CROSS-BLOCK: 4:
; CROSS-BLOCK-NEXT: [[DOT0:%.*]] = phi i32 [ 0, [[TMP3:%.*]] ], [ [[TMP16:%.*]], [[TMP6:%.*]] ]
; CROSS-BLOCK-NEXT: [[TMP5:%.*]] = icmp slt i32 [[DOT0]], [[TMP1]]
; CROSS-BLOCK-NEXT: br i1 [[TMP5]], label [[TMP6]], label [[TMP17:%.*]]
; CROSS-BLOCK: 6:
; CROSS-BLOCK-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP1]], [[DOT0]]
; CROSS-BLOCK-NEXT: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; CROSS-BLOCK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP8]]
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4) ]
; CROSS-BLOCK-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
; CROSS-BLOCK-NEXT: [[TMP11:%.*]] = mul nsw i32 [[DOT0]], [[TMP10]]
; CROSS-BLOCK-NEXT: [[TMP12:%.*]] = sext i32 [[DOT0]] to i64
; CROSS-BLOCK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP12]]
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i32* [[TMP13]], i64 4) ]
; CROSS-BLOCK-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
; CROSS-BLOCK-NEXT: [[TMP15:%.*]] = add nsw i32 [[TMP14]], [[TMP11]]
; CROSS-BLOCK-NEXT: store i32 [[TMP15]], i32* [[TMP13]], align 4
; CROSS-BLOCK-NEXT: [[TMP16]] = add nsw i32 [[DOT0]], 1
; CROSS-BLOCK-NEXT: br label [[TMP4]]
; CROSS-BLOCK: 17:
; CROSS-BLOCK-NEXT: [[TMP18:%.*]] = sext i32 [[TMP1]] to i64
; CROSS-BLOCK-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 [[TMP18]]
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP2]]), "align"(i32* [[TMP2]], i64 4) ]
; CROSS-BLOCK-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
; CROSS-BLOCK-NEXT: ret i32 [[TMP20]]
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test6
; FULL-SIMPLIFY-SAME: (i32* [[TMP0:%.*]], i32 [[TMP1:%.*]], i32* [[TMP2:%.*]])
; FULL-SIMPLIFY-NEXT: br label [[TMP4:%.*]]
; FULL-SIMPLIFY: 4:
; FULL-SIMPLIFY-NEXT: [[DOT0:%.*]] = phi i32 [ 0, [[TMP3:%.*]] ], [ [[TMP16:%.*]], [[TMP6:%.*]] ]
; FULL-SIMPLIFY-NEXT: [[TMP5:%.*]] = icmp slt i32 [[DOT0]], [[TMP1]]
; FULL-SIMPLIFY-NEXT: br i1 [[TMP5]], label [[TMP6]], label [[TMP17:%.*]]
; FULL-SIMPLIFY: 6:
; FULL-SIMPLIFY-NEXT: [[TMP7:%.*]] = add nsw i32 [[TMP1]], [[DOT0]]
; FULL-SIMPLIFY-NEXT: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; FULL-SIMPLIFY-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP8]]
; FULL-SIMPLIFY-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP11:%.*]] = mul nsw i32 [[DOT0]], [[TMP10]]
; FULL-SIMPLIFY-NEXT: [[TMP12:%.*]] = sext i32 [[DOT0]] to i64
; FULL-SIMPLIFY-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 [[TMP12]]
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP0]]), "align"(i32* [[TMP0]], i64 4), "dereferenceable"(i32* [[TMP13]], i64 4) ]
; FULL-SIMPLIFY-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP15:%.*]] = add nsw i32 [[TMP14]], [[TMP11]]
; FULL-SIMPLIFY-NEXT: store i32 [[TMP15]], i32* [[TMP13]], align 4
; FULL-SIMPLIFY-NEXT: [[TMP16]] = add nsw i32 [[DOT0]], 1
; FULL-SIMPLIFY-NEXT: br label [[TMP4]]
; FULL-SIMPLIFY: 17:
; FULL-SIMPLIFY-NEXT: [[TMP18:%.*]] = sext i32 [[TMP1]] to i64
; FULL-SIMPLIFY-NEXT: [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i64 [[TMP18]]
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "nonnull"(i32* [[TMP2]]), "align"(i32* [[TMP2]], i64 4) ]
; FULL-SIMPLIFY-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
; FULL-SIMPLIFY-NEXT: ret i32 [[TMP20]]
;
br label %4
4: ; preds = %6, %3
%.0 = phi i32 [ 0, %3 ], [ %16, %6 ]
%5 = icmp slt i32 %.0, %1
br i1 %5, label %6, label %17
6: ; preds = %4
%7 = add nsw i32 %1, %.0
%8 = sext i32 %7 to i64
%9 = getelementptr inbounds i32, i32* %0, i64 %8
%10 = load i32, i32* %9, align 4
%11 = mul nsw i32 %.0, %10
%12 = sext i32 %.0 to i64
%13 = getelementptr inbounds i32, i32* %0, i64 %12
%14 = load i32, i32* %13, align 4
%15 = add nsw i32 %14, %11
store i32 %15, i32* %13, align 4
%16 = add nsw i32 %.0, 1
br label %4
17: ; preds = %4
%18 = sext i32 %1 to i64
%19 = getelementptr inbounds i32, i32* %2, i64 %18
%20 = load i32, i32* %19, align 4
ret i32 %20
}
%struct.A = type { i8*, i64*, [4 x [4 x %struct.D]], i64 }
%struct.D = type { i64, i64 }
define i32 @test7(%struct.A* nonnull %0, i32 %1) {
; BASIC-LABEL: define {{[^@]+}}@test7
; BASIC-SAME: (%struct.A* nonnull [[TMP0:%.*]], i32 [[TMP1:%.*]])
; BASIC-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; BASIC-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_A:%.*]], %struct.A* [[TMP0]], i64 0, i32 3
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.A* [[TMP0]], i64 280), "align"(%struct.A* [[TMP0]], i64 16) ]
; BASIC-NEXT: [[TMP5:%.*]] = load i64, i64* [[TMP4]], align 8
; BASIC-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 2, i64 [[TMP3]], i64 [[TMP5]], i32 0
; BASIC-NEXT: [[TMP7:%.*]] = load i64, i64* [[TMP6]], align 32
; BASIC-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 1
; BASIC-NEXT: [[TMP9:%.*]] = load i64*, i64** [[TMP8]], align 8
; BASIC-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP9]], i64 [[TMP5]]
; BASIC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP10]], i64 8), "nonnull"(i64* [[TMP9]]), "align"(i64* [[TMP9]], i64 8) ]
; BASIC-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; BASIC-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; BASIC-NEXT: [[TMP11:%.*]] = bitcast %struct.A* [[TMP0]] to i32**
; BASIC-NEXT: [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
; BASIC-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; BASIC-NEXT: ret i32 [[TMP13]]
;
; ALL-LABEL: define {{[^@]+}}@test7
; ALL-SAME: (%struct.A* nonnull [[TMP0:%.*]], i32 [[TMP1:%.*]])
; ALL-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; ALL-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_A:%.*]], %struct.A* [[TMP0]], i64 0, i32 3
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.A* [[TMP0]], i64 280), "align"(%struct.A* [[TMP0]], i64 16) ]
; ALL-NEXT: [[TMP5:%.*]] = load i64, i64* [[TMP4]], align 8
; ALL-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 2, i64 [[TMP3]], i64 [[TMP5]], i32 0
; ALL-NEXT: [[TMP7:%.*]] = load i64, i64* [[TMP6]], align 32
; ALL-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 1
; ALL-NEXT: [[TMP9:%.*]] = load i64*, i64** [[TMP8]], align 8
; ALL-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP9]], i64 [[TMP5]]
; ALL-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP10]], i64 8), "nonnull"(i64* [[TMP9]]), "align"(i64* [[TMP9]], i64 8) ]
; ALL-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; ALL-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; ALL-NEXT: [[TMP11:%.*]] = bitcast %struct.A* [[TMP0]] to i32**
; ALL-NEXT: [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
; ALL-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; ALL-NEXT: ret i32 [[TMP13]]
;
; WITH-AC-LABEL: define {{[^@]+}}@test7
; WITH-AC-SAME: (%struct.A* nonnull [[TMP0:%.*]], i32 [[TMP1:%.*]])
; WITH-AC-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; WITH-AC-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_A:%.*]], %struct.A* [[TMP0]], i64 0, i32 3
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.A* [[TMP0]], i64 280), "align"(%struct.A* [[TMP0]], i64 16) ]
; WITH-AC-NEXT: [[TMP5:%.*]] = load i64, i64* [[TMP4]], align 8
; WITH-AC-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 2, i64 [[TMP3]], i64 [[TMP5]], i32 0
; WITH-AC-NEXT: [[TMP7:%.*]] = load i64, i64* [[TMP6]], align 32
; WITH-AC-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 1
; WITH-AC-NEXT: [[TMP9:%.*]] = load i64*, i64** [[TMP8]], align 8
; WITH-AC-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP9]], i64 [[TMP5]]
; WITH-AC-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP10]], i64 8), "nonnull"(i64* [[TMP9]]), "align"(i64* [[TMP9]], i64 8) ]
; WITH-AC-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; WITH-AC-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; WITH-AC-NEXT: [[TMP11:%.*]] = bitcast %struct.A* [[TMP0]] to i32**
; WITH-AC-NEXT: [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
; WITH-AC-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; WITH-AC-NEXT: ret i32 [[TMP13]]
;
; CROSS-BLOCK-LABEL: define {{[^@]+}}@test7
; CROSS-BLOCK-SAME: (%struct.A* nonnull [[TMP0:%.*]], i32 [[TMP1:%.*]])
; CROSS-BLOCK-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; CROSS-BLOCK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_A:%.*]], %struct.A* [[TMP0]], i64 0, i32 3
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(%struct.A* [[TMP0]], i64 280), "align"(%struct.A* [[TMP0]], i64 16) ]
; CROSS-BLOCK-NEXT: [[TMP5:%.*]] = load i64, i64* [[TMP4]], align 8
; CROSS-BLOCK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 2, i64 [[TMP3]], i64 [[TMP5]], i32 0
; CROSS-BLOCK-NEXT: [[TMP7:%.*]] = load i64, i64* [[TMP6]], align 32
; CROSS-BLOCK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 1
; CROSS-BLOCK-NEXT: [[TMP9:%.*]] = load i64*, i64** [[TMP8]], align 8
; CROSS-BLOCK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP9]], i64 [[TMP5]]
; CROSS-BLOCK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP10]], i64 8), "nonnull"(i64* [[TMP9]]), "align"(i64* [[TMP9]], i64 8) ]
; CROSS-BLOCK-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; CROSS-BLOCK-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; CROSS-BLOCK-NEXT: [[TMP11:%.*]] = bitcast %struct.A* [[TMP0]] to i32**
; CROSS-BLOCK-NEXT: [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
; CROSS-BLOCK-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CROSS-BLOCK-NEXT: ret i32 [[TMP13]]
;
; FULL-SIMPLIFY-LABEL: define {{[^@]+}}@test7
; FULL-SIMPLIFY-SAME: (%struct.A* nonnull align 16 dereferenceable(280) [[TMP0:%.*]], i32 [[TMP1:%.*]])
; FULL-SIMPLIFY-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; FULL-SIMPLIFY-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_A:%.*]], %struct.A* [[TMP0]], i64 0, i32 3
; FULL-SIMPLIFY-NEXT: [[TMP5:%.*]] = load i64, i64* [[TMP4]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 2, i64 [[TMP3]], i64 [[TMP5]], i32 0
; FULL-SIMPLIFY-NEXT: [[TMP7:%.*]] = load i64, i64* [[TMP6]], align 32
; FULL-SIMPLIFY-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_A]], %struct.A* [[TMP0]], i64 0, i32 1
; FULL-SIMPLIFY-NEXT: [[TMP9:%.*]] = load i64*, i64** [[TMP8]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, i64* [[TMP9]], i64 [[TMP5]]
; FULL-SIMPLIFY-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(i64* [[TMP10]], i64 8), "nonnull"(i64* [[TMP9]]), "align"(i64* [[TMP9]], i64 8) ]
; FULL-SIMPLIFY-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; FULL-SIMPLIFY-NEXT: store i64 [[TMP7]], i64* [[TMP10]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP11:%.*]] = bitcast %struct.A* [[TMP0]] to i32**
; FULL-SIMPLIFY-NEXT: [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
; FULL-SIMPLIFY-NEXT: [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; FULL-SIMPLIFY-NEXT: ret i32 [[TMP13]]
;
%3 = sext i32 %1 to i64
%4 = getelementptr inbounds %struct.A, %struct.A* %0, i64 0, i32 3
%5 = load i64, i64* %4, align 8
%6 = getelementptr inbounds %struct.A, %struct.A* %0, i64 0, i32 2, i64 %3, i64 %5, i32 0
%7 = load i64, i64* %6, align 32
%8 = getelementptr inbounds %struct.A, %struct.A* %0, i64 0, i32 1
%9 = load i64*, i64** %8, align 8
%10 = getelementptr inbounds i64, i64* %9, i64 %5
store i64 %7, i64* %10, align 8
store i64 %7, i64* %10, align 8
%11 = bitcast %struct.A* %0 to i32**
%12 = load i32*, i32** %11, align 8
%13 = load i32, i32* %12, align 4
ret i32 %13
}