maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/lld/test/COFF/msvclto-archive.ll

41 lines
1.4 KiB
LLVM
Raw Normal View History

[LLD] Mark a number of x86 only tests to require x86 Noticed while testing for an out of tree target. There are probably more tests that should be so marked. I'm not sure who owns these tests so I've added a few names I recognise from the recent history. With advice from probinson, ruiu, rafael and dramatically improved by davidb. Thank you all! Differential Revision: https://reviews.llvm.org/D34685 llvm-svn: 308335
2017-07-19 02:40:50 +08:00
; REQUIRES: x86
Do not pass archive files containing non-native object files. The MSVC linker doesn't like archive files containing non-native object files. When we are doing an LTO build, we may create archive files containing both LLVM bitcode files and native object files. For example, if a project contains assembly files and C++ files, we create native object files for the assembly files and LLVM bitcode files for the C++ files. With the /msvclto option, LLD passes archive files to the MSVC linker. Previously, we didn't pass archive files if they contain at least one bitcode files. That wasn't correct because the native object files that weren't passed to the MSVC linker may be needed to complete linking. In this patch, we create new temporary archive files to strip bitcode files. Differential Revision: https://reviews.llvm.org/D31053 llvm-svn: 297997
2017-03-17 05:19:36 +08:00
;; Make sure we re-create archive files to strip bitcode files.
Do not pass archive files containing bitcode files to the MSVC Linker. If /msvclto is specified, we compile bitcode files and pass it to the MSVC linker, stripping all bitcode files. We haven't stripped archive files, because I was thinking that the MSVC linker wouldn't touch files in archive files. When we pass an object file to link.exe, all symbols have been resolved already, so link.exe shoulnd't need any of the files in archives. It turns out that even though link.exe doesn't need to do that, it seems to try to read each file in all archives. And if there's a non- COFF file in an archive, it exists with an error message. So we need to remove archives from the command line too. llvm-svn: 297191
2017-03-08 03:45:53 +08:00
COFF: Do not create empty temporary archives for /msvclto. The MSVC linker doesn't support them. Differential Revision: https://reviews.llvm.org/D31067 llvm-svn: 298034
2017-03-17 10:04:22 +08:00
;; Do not create empty archives because the MSVC linker
;; doesn't support them.
Do not pass archive files containing bitcode files to the MSVC Linker. If /msvclto is specified, we compile bitcode files and pass it to the MSVC linker, stripping all bitcode files. We haven't stripped archive files, because I was thinking that the MSVC linker wouldn't touch files in archive files. When we pass an object file to link.exe, all symbols have been resolved already, so link.exe shoulnd't need any of the files in archives. It turns out that even though link.exe doesn't need to do that, it seems to try to read each file in all archives. And if there's a non- COFF file in an archive, it exists with an error message. So we need to remove archives from the command line too. llvm-svn: 297191
2017-03-08 03:45:53 +08:00
; RUN: llvm-as -o %t.obj %s
Do not pass archive files containing non-native object files. The MSVC linker doesn't like archive files containing non-native object files. When we are doing an LTO build, we may create archive files containing both LLVM bitcode files and native object files. For example, if a project contains assembly files and C++ files, we create native object files for the assembly files and LLVM bitcode files for the C++ files. With the /msvclto option, LLD passes archive files to the MSVC linker. Previously, we didn't pass archive files if they contain at least one bitcode files. That wasn't correct because the native object files that weren't passed to the MSVC linker may be needed to complete linking. In this patch, we create new temporary archive files to strip bitcode files. Differential Revision: https://reviews.llvm.org/D31053 llvm-svn: 297997
2017-03-17 05:19:36 +08:00
; RUN: rm -f %t-main1.a
Pass archive files to link.exe if they contain at least one native object file. Some archive files created during chromium build contains both BC and native files. If that's the case, we want to pass the archive file to link.exe. Otherwise, the MSVC linker would complain that there's an unresolved symbol in a given set of files. I cannot explain why link.exe doesn't complain about the presence of bitcode files in this case, but it seems link.exe doesn't touch BC. llvm-svn: 297229
2017-03-08 05:26:10 +08:00
; RUN: llvm-ar cru %t-main1.a %t.obj
Do not pass archive files containing bitcode files to the MSVC Linker. If /msvclto is specified, we compile bitcode files and pass it to the MSVC linker, stripping all bitcode files. We haven't stripped archive files, because I was thinking that the MSVC linker wouldn't touch files in archive files. When we pass an object file to link.exe, all symbols have been resolved already, so link.exe shoulnd't need any of the files in archives. It turns out that even though link.exe doesn't need to do that, it seems to try to read each file in all archives. And if there's a non- COFF file in an archive, it exists with an error message. So we need to remove archives from the command line too. llvm-svn: 297191
2017-03-08 03:45:53 +08:00
; RUN: mkdir -p %t.dir
; RUN: llvm-mc -triple=x86_64-pc-windows-msvc -filetype=obj -o %t.dir/bitcode.obj %p/Inputs/msvclto.s
Pass archive files to link.exe if they contain at least one native object file. Some archive files created during chromium build contains both BC and native files. If that's the case, we want to pass the archive file to link.exe. Otherwise, the MSVC linker would complain that there's an unresolved symbol in a given set of files. I cannot explain why link.exe doesn't complain about the presence of bitcode files in this case, but it seems link.exe doesn't touch BC. llvm-svn: 297229
2017-03-08 05:26:10 +08:00
; RUN: lld-link %t-main1.a %t.dir/bitcode.obj /msvclto /out:%t.exe /opt:lldlto=1 /opt:icf \
Use ErrorOS for log messages as well as error log are also diagnostics so it seems like they should to the same place as errors and debug messages. Without this change when I enable --verbose those messages go to stdout, but when I enable "-mllvm -debug" those messages go to stderr (because dbgs() goes to stderr by default). So I end up having to do this a lot: lld <args> > output_message 2>&1 Differential Revision: https://reviews.llvm.org/D41033 llvm-svn: 320427
2017-12-12 05:57:31 +08:00
; RUN: /entry:main /verbose 2> %t.log || true
Pass archive files to link.exe if they contain at least one native object file. Some archive files created during chromium build contains both BC and native files. If that's the case, we want to pass the archive file to link.exe. Otherwise, the MSVC linker would complain that there's an unresolved symbol in a given set of files. I cannot explain why link.exe doesn't complain about the presence of bitcode files in this case, but it seems link.exe doesn't touch BC. llvm-svn: 297229
2017-03-08 05:26:10 +08:00
; RUN: FileCheck -check-prefix=BC %s < %t.log
COFF: Do not create empty temporary archives for /msvclto. The MSVC linker doesn't support them. Differential Revision: https://reviews.llvm.org/D31067 llvm-svn: 298034
2017-03-17 10:04:22 +08:00
; BC-NOT: Creating a temporary archive for
Do not pass archive files containing bitcode files to the MSVC Linker. If /msvclto is specified, we compile bitcode files and pass it to the MSVC linker, stripping all bitcode files. We haven't stripped archive files, because I was thinking that the MSVC linker wouldn't touch files in archive files. When we pass an object file to link.exe, all symbols have been resolved already, so link.exe shoulnd't need any of the files in archives. It turns out that even though link.exe doesn't need to do that, it seems to try to read each file in all archives. And if there's a non- COFF file in an archive, it exists with an error message. So we need to remove archives from the command line too. llvm-svn: 297191
2017-03-08 03:45:53 +08:00
Do not pass archive files containing non-native object files. The MSVC linker doesn't like archive files containing non-native object files. When we are doing an LTO build, we may create archive files containing both LLVM bitcode files and native object files. For example, if a project contains assembly files and C++ files, we create native object files for the assembly files and LLVM bitcode files for the C++ files. With the /msvclto option, LLD passes archive files to the MSVC linker. Previously, we didn't pass archive files if they contain at least one bitcode files. That wasn't correct because the native object files that weren't passed to the MSVC linker may be needed to complete linking. In this patch, we create new temporary archive files to strip bitcode files. Differential Revision: https://reviews.llvm.org/D31053 llvm-svn: 297997
2017-03-17 05:19:36 +08:00
; RUN: rm -f %t-main2.a
; RUN: llvm-ar cru %t-main2.a %t.dir/bitcode.obj
; RUN: lld-link %t.obj %t-main2.a /msvclto /out:%t.exe /opt:lldlto=1 /opt:icf \
Use ErrorOS for log messages as well as error log are also diagnostics so it seems like they should to the same place as errors and debug messages. Without this change when I enable --verbose those messages go to stdout, but when I enable "-mllvm -debug" those messages go to stderr (because dbgs() goes to stderr by default). So I end up having to do this a lot: lld <args> > output_message 2>&1 Differential Revision: https://reviews.llvm.org/D41033 llvm-svn: 320427
2017-12-12 05:57:31 +08:00
; RUN: /entry:main /verbose 2> %t.log || true
Pass archive files to link.exe if they contain at least one native object file. Some archive files created during chromium build contains both BC and native files. If that's the case, we want to pass the archive file to link.exe. Otherwise, the MSVC linker would complain that there's an unresolved symbol in a given set of files. I cannot explain why link.exe doesn't complain about the presence of bitcode files in this case, but it seems link.exe doesn't touch BC. llvm-svn: 297229
2017-03-08 05:26:10 +08:00
; RUN: FileCheck -check-prefix=OBJ %s < %t.log
Do not pass archive files containing non-native object files. The MSVC linker doesn't like archive files containing non-native object files. When we are doing an LTO build, we may create archive files containing both LLVM bitcode files and native object files. For example, if a project contains assembly files and C++ files, we create native object files for the assembly files and LLVM bitcode files for the C++ files. With the /msvclto option, LLD passes archive files to the MSVC linker. Previously, we didn't pass archive files if they contain at least one bitcode files. That wasn't correct because the native object files that weren't passed to the MSVC linker may be needed to complete linking. In this patch, we create new temporary archive files to strip bitcode files. Differential Revision: https://reviews.llvm.org/D31053 llvm-svn: 297997
2017-03-17 05:19:36 +08:00
; OBJ-NOT: Creating a temporary archive
;; Make sure that we always rebuild thin archives because
;; the MSVC linker doesn't support thin archives.
; RUN: rm -f %t-main3.a
; RUN: llvm-ar cruT %t-main3.a %t.dir/bitcode.obj
; RUN: lld-link %t.obj %t-main3.a /msvclto /out:%t.exe /opt:lldlto=1 /opt:icf \
Use ErrorOS for log messages as well as error log are also diagnostics so it seems like they should to the same place as errors and debug messages. Without this change when I enable --verbose those messages go to stdout, but when I enable "-mllvm -debug" those messages go to stderr (because dbgs() goes to stderr by default). So I end up having to do this a lot: lld <args> > output_message 2>&1 Differential Revision: https://reviews.llvm.org/D41033 llvm-svn: 320427
2017-12-12 05:57:31 +08:00
; RUN: /entry:main /verbose 2> %t.log || true
Do not pass archive files containing non-native object files. The MSVC linker doesn't like archive files containing non-native object files. When we are doing an LTO build, we may create archive files containing both LLVM bitcode files and native object files. For example, if a project contains assembly files and C++ files, we create native object files for the assembly files and LLVM bitcode files for the C++ files. With the /msvclto option, LLD passes archive files to the MSVC linker. Previously, we didn't pass archive files if they contain at least one bitcode files. That wasn't correct because the native object files that weren't passed to the MSVC linker may be needed to complete linking. In this patch, we create new temporary archive files to strip bitcode files. Differential Revision: https://reviews.llvm.org/D31053 llvm-svn: 297997
2017-03-17 05:19:36 +08:00
; RUN: FileCheck -check-prefix=THIN %s < %t.log
; THIN: Creating a temporary archive
Do not pass archive files containing bitcode files to the MSVC Linker. If /msvclto is specified, we compile bitcode files and pass it to the MSVC linker, stripping all bitcode files. We haven't stripped archive files, because I was thinking that the MSVC linker wouldn't touch files in archive files. When we pass an object file to link.exe, all symbols have been resolved already, so link.exe shoulnd't need any of the files in archives. It turns out that even though link.exe doesn't need to do that, it seems to try to read each file in all archives. And if there's a non- COFF file in an archive, it exists with an error message. So we need to remove archives from the command line too. llvm-svn: 297191
2017-03-08 03:45:53 +08:00
target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-windows-msvc"
declare void @foo()
define i32 @main() {
call void @foo()
ret i32 0
}