Go to file
Adam Nemet 6dafe97271 [X86] Adjust cost of FP_TO_UINT v8f32->v8i32
There is no direct AVX instruction to convert to unsigned.  I have some ideas
how we may be able to do this with three vector instructions but the current
backend just bails on this to get it scalarized.

See the comment why we need to adjust the cost returned by BasicTTI.

The test is a bit roundabout (and checks assembly rather than bit code) because
I'd like it to work even if at some point we could vectorize this conversion.

Fixes <rdar://problem/16371920>

llvm-svn: 205159
2014-03-30 18:07:13 +00:00
clang RTTI: refactor the uniqueness question into CGCXXABI. 2014-03-30 17:32:48 +00:00
clang-tools-extra clang-modernize: fix invalid assignment in findClangApplyReplacements() 2014-03-30 10:50:25 +00:00
compiler-rt [sanitizer] Fix Mac build. 2014-03-28 14:01:40 +00:00
debuginfo-tests relax testcase for LLDB output format compatibility. 2014-03-19 23:06:18 +00:00
libclc Introduce M_LOG2E_F and M_LOG2E 2014-03-28 21:19:03 +00:00
libcxx Use defined(__APPLE__) rather than __APPLE__ 2014-03-30 14:59:12 +00:00
libcxxabi Simplify. 2014-03-20 01:28:28 +00:00
lld Forgot to replace a %t1 in the previous commit. 2014-03-29 06:45:26 +00:00
lldb Include string.h for memset() prototype. Thanks Dmitri. 2014-03-29 19:29:04 +00:00
llvm [X86] Adjust cost of FP_TO_UINT v8f32->v8i32 2014-03-30 18:07:13 +00:00
openmp Revert commit (testing commit hook). 2014-03-04 18:06:04 +00:00
polly Updated test/create_ll.sh to work with old & new clang versions. 2014-03-25 15:50:44 +00:00