mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-16 11:05:54 +00:00
813456527e
The costs are overfitted so that I can still use the legalization factor. For example the following kernel has about half the throughput vectorized than unvectorized when compiled with SSE2. Before this patch we would vectorize it. unsigned short A[1024]; double B[1024]; void f() { int i; for (i = 0; i < 1024; ++i) { B[i] = (double) A[i]; } } radar://13599001 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179033 91177308-0d34-0410-b5e6-96231b3b80d8 |
||
---|---|---|
.. | ||
arith.ll | ||
cast.ll | ||
cmp.ll | ||
gep.ll | ||
i32.ll | ||
insert-extract-at-zero.ll | ||
intrinsic-cost.ll | ||
lit.local.cfg | ||
load_store.ll | ||
loop_v2.ll | ||
sitofp.ll | ||
testshiftashr.ll | ||
testshiftlshr.ll | ||
testshiftshl.ll | ||
tiny.ll | ||
uitofp.ll | ||
vectorized-loop.ll |