search for: lcal

Hi all, I would like to propose an improvement of the “almost dead” block elimination in Transforms/Local.cpp so that it will preserve the canonical loop form for loops with a volatile iteration variable. *** Problem statement Nested loops in LCALS Subset B (https://codesign.llnl.gov/LCALS.php) are not vectorized with LLVM -O3 because the LLVM loop vectorizer fails the test whether the loop latch and exiting block of a loop is the same. The loops are vectorizable, and get vectorized with LLVM -O2 and also with other commercial compilers (icc...

...> > I would like to propose an improvement of the “almost dead” block > > elimination in Transforms/Local.cpp so that it will preserve the > > canonical loop form for loops with a volatile iteration variable. > > > *** Problem statement > > > Nested loops in LCALS Subset B ( > > https://codesign.llnl.gov/LCALS.php > > ) are not vectorized with LLVM -O3 because the LLVM loop vectorizer > > fails the test whether the loop latch and exiting block of a loop > > is > > the same. The loops are vectorizable, and get vectorized with LL...

...so that it will preserve > > > > the > > > > canonical loop form for loops with a volatile iteration > > > > variable. > > > > > > > > > > *** Problem statement > > > > > > > > > > Nested loops in LCALS Subset B ( > > > > https://codesign.llnl.gov/LCALS.php > > > > ) are not vectorized with LLVM -O3 because the LLVM loop > > > > vectorizer > > > > fails the test whether the loop latch and exiting block of a > > > > loop > > > &g...

...> > > > > > variable. > > > > > > > > > > > > > > > > > > > > > *** Problem statement > > > > > > > > > > > > > > > > > > > > > Nested loops in LCALS Subset B ( > > > > > > https://codesign.llnl.gov/LCALS.php > > > > > > ) are not vectorized with LLVM -O3 because the LLVM loop > > > > > > vectorizer > > > > > > fails the test whether the loop latch and exiting block of >...

...es, just for >> TSVC. Ideally, I'd like aligned and unaligned variants of each of >> these. I've not done that because I thought that 72 executables >> would be a bit much, but that's 544 executables if I generate one >> per kernel variant. >> >> The LCALS benchmark, which I'd really like to add sometime soon, has >> another ~100 kernels, which is ~200 to do both float and double >> (which we should do). >> >> What do you think is reasonable here? >> > > Also, we might want to consider updating some of thes...

...; TSVC. Ideally, I'd like aligned and unaligned variants of each of >>> these. I've not done that because I thought that 72 executables >>> would be a bit much, but that's 544 executables if I generate one >>> per kernel variant. >>> >>> The LCALS benchmark, which I'd really like to add sometime soon, has >>> another ~100 kernels, which is ~200 to do both float and double >>> (which we should do). >>> >>> What do you think is reasonable here? >>> >> >> Also, we might want to co...

...39;d like aligned and unaligned variants of each of >>>> these. I've not done that because I thought that 72 executables >>>> would be a bit much, but that's 544 executables if I generate one >>>> per kernel variant. >>>> >>>> The LCALS benchmark, which I'd really like to add sometime soon, has >>>> another ~100 kernels, which is ~200 to do both float and double >>>> (which we should do). >>>> >>>> What do you think is reasonable here? >>>> >>> >>&g...

...sung at us.ibm.com > wrote: > > Hi all, I would like to propose an improvement of the “almost dead” > block elimination in Transforms/Local.cpp so that it will preserve > the canonical loop form for loops with a volatile iteration > variable. *** Problem statement Nested loops in LCALS Subset B ( > https://codesign.llnl.gov/LCALS.php ) are not vectorized with LLVM > -O3 because the LLVM loop vectorizer fails the test whether the loop > latch and exiting block of a loop is the same. The loops are > vectorizable, and get vectorized with LLVM -O2 I would be interested &...