maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGen/arm-mfpu-none.c

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

10 lines
252 B
C
Raw Normal View History

[ARM] Fix recent breakage of -mfpu=none. The recent change D60691 introduced a bug in clang when handling option combinations such as `-mcpu=cortex-m4 -mfpu=none`. Those options together should select Cortex-M4 but disable all use of hardware FP, but in fact, now hardware FP instructions can still be generated in that mode. The reason is because the handling of FPUVersion::NONE disables all the same feature names it used to, of which the base one is `vfp2`. But now there are further features below that, like `vfp2d16fp` and (following D60694) `fpregs`, which also need to be turned off to disable hardware FP completely. Added a tiny test which double-checks that compiling a simple FP function doesn't access the FP registers. Reviewers: SjoerdMeijer, dmgreen Reviewed By: dmgreen Subscribers: lebedev.ri, javed.absar, kristof.beyls, hiraditya, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D62729 llvm-svn: 362380
2019-06-03 19:02:53 +08:00
// REQUIRES: arm-registered-target
// RUN: %clang -target arm-none-eabi -mcpu=cortex-m4 -mfpu=none -S -o - %s | FileCheck %s
// CHECK-LABEL: compute
// CHECK-NOT: {{s[0-9]}}
[clang] Prevent false positives in arm-mfpu-none codegen test. A user pointed out to me in private email that this test will fail if it sees the letter 's' followed by a digit in any part of clang's assembly output after the function label. That includes the .ident at the end, which can include a full pathname or hostname or both from the system clang was built on. So if that path or hostname includes any text like 's5' then it will cause the test to fail. Fixed by adding a check for `.fnend`, to limit the scope of the `CHECK-NOT` to only the actual generated code for the test function. (Committed without prior review on the basis that it's a simple and obvious pure test-suite fix and also in a test I contributed myself.) llvm-svn: 373744
2019-10-04 21:01:41 +08:00
// CHECK: .fnend
[ARM] Fix recent breakage of -mfpu=none. The recent change D60691 introduced a bug in clang when handling option combinations such as `-mcpu=cortex-m4 -mfpu=none`. Those options together should select Cortex-M4 but disable all use of hardware FP, but in fact, now hardware FP instructions can still be generated in that mode. The reason is because the handling of FPUVersion::NONE disables all the same feature names it used to, of which the base one is `vfp2`. But now there are further features below that, like `vfp2d16fp` and (following D60694) `fpregs`, which also need to be turned off to disable hardware FP completely. Added a tiny test which double-checks that compiling a simple FP function doesn't access the FP registers. Reviewers: SjoerdMeijer, dmgreen Reviewed By: dmgreen Subscribers: lebedev.ri, javed.absar, kristof.beyls, hiraditya, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D62729 llvm-svn: 362380
2019-06-03 19:02:53 +08:00
float compute(float a, float b) {
return (a+b) * (a-b);
}