diff options
| author | Chandler Carruth <chandlerc@gmail.com> | 2018-07-16 04:17:51 +0000 |
|---|---|---|
| committer | Chandler Carruth <chandlerc@gmail.com> | 2018-07-16 04:17:51 +0000 |
| commit | cdf0addc65e72e8bdcc23b1e26af5ff3f7ccd8c6 (patch) | |
| tree | 9a2dd81514d2c300f79b034feb2170f2d1ffb1e5 /llvm/lib/Analysis/Delinearization.cpp | |
| parent | ccc84224644e267fce8b70e32833b887f4e12a61 (diff) | |
| download | bcm5719-llvm-cdf0addc65e72e8bdcc23b1e26af5ff3f7ccd8c6.tar.gz bcm5719-llvm-cdf0addc65e72e8bdcc23b1e26af5ff3f7ccd8c6.zip | |
[x86/SLH] Teach speculative load hardening to correctly harden the
indices used by AVX2 and AVX-512 gather instructions.
The index vector is hardened by broadcasting the predicate state
into a vector register and then or-ing. We don't even have to worry
about EFLAGS here.
I've added a test for all of the gather intrinsics to make sure that we
don't miss one. A particularly interesting creation is the gather
prefetch, which needs to be marked as potentially "loading" to get the
correct behavior. It's a memory access in many ways, and is actually
relevant for SLH. Based on discussion with Craig in review, I've moved
it to be `mayLoad` and `mayStore` rather than generic side effects. This
matches how we model other prefetch instructions.
Many thanks to Craig for the review here.
Differential Revision: https://reviews.llvm.org/D49336
llvm-svn: 337144
Diffstat (limited to 'llvm/lib/Analysis/Delinearization.cpp')
0 files changed, 0 insertions, 0 deletions
