[PATCH] D70874: [X86] Add initialization of MXCSR in llvm-exegesis
Craig Topper via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Sat Nov 30 22:14:57 PST 2019
craig.topper added a comment.
I'm not sure I understand why this needs to be initialized. Why don't we need to do it for FPCW?
================
Comment at: llvm/tools/llvm-exegesis/lib/X86/Target.cpp:506
+ add(allocateStackSpace(4));
+ add(fillStackSpace(X86::MOV32mi, 0, 0x1f8)); // Mask all FP exceptions
+ add(MCInstBuilder(HasAVX ? X86::VLDMXCSR : X86::LDMXCSR)
----------------
Isn't the default value of MXCSR 0x1f80 not 0x1f8?
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D70874/new/
https://reviews.llvm.org/D70874
More information about the llvm-commits
mailing list