diff options
| author | Craig Topper <craig.topper@sifive.com> | 2021-03-09 08:38:45 -0800 |
|---|---|---|
| committer | Craig Topper <craig.topper@sifive.com> | 2021-03-09 08:50:02 -0800 |
| commit | 478317fbb79034694df934900665f363dd6c9a70 (patch) | |
| tree | 7b6ba7c9da2f0c9026cc091c6b116593e44691d1 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | df69c69427dea7f5b3b3a4d4564bc77b0926ec88 (diff) | |
| download | llvm-478317fbb79034694df934900665f363dd6c9a70.zip llvm-478317fbb79034694df934900665f363dd6c9a70.tar.gz llvm-478317fbb79034694df934900665f363dd6c9a70.tar.bz2 | |
[RISCV] Make the hasStdExtM() check in RISCVInstrInfo::getVLENFactoredAmount emit a diagnostic rather than an assert.
As far as I know we're not enforcing the StdExtM must be enabled
to use the V extension. If we use an assert here and hit this
code in a release build we'll silently emit an invalid instruction.
By using a diagnostic we report the error to the user in release
builds. I think there may still be a later fatal error from
the code emitter though.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97970
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions