Commit Graph

7 Commits

Author SHA1 Message Date
David Green a24b02193a [DSE] Remove stores in the same loop iteration
DSE will currently only remove stores in the same block unless they can
be guaranteed to be loop invariant. This expands that to any stores that
are in the same Loop, at the same loop level. This should still account
for where AA/MSSA will not handle aliasing between loops, but allow the
dead stores to be removed where they overlap in the same loop iteration.
It requires adding loop info to DSE, but that looks fairly harmless.

The test case this helps is from code like this, which can come up in
certain matrix operations:
  for(i=..)
    dst[i] = 0;
    for(j=..)
      dst[i] += src[i*n+j];

After LICM, this becomes:
for(i=..)
  dst[i] = 0;
  sum = 0;
  for(j=..)
    sum += src[i*n+j];
  dst[i] = sum;

The first store is dead, and with this patch is now removed.

Differntial Revision: https://reviews.llvm.org/D100464
2021-06-20 17:03:30 +01:00
David Green 562593ff82 [DSE] Extra multiblock loop tests, NFC.
Some of these can be DSE'd, some of which cannot. Useful in D100464.
2021-06-13 22:30:42 +01:00
David Green 0178ae734c [DSE] Add another multiblock loop DSE test. NFC
As reported in D100464, the stores in these loops should not be removed.
2021-06-08 21:54:59 +01:00
David Green 297088d1ad Revert "[DSE] Remove stores in the same loop iteration"
Apparently non-dead stores are being removed, as noted in D100464.

This reverts commit 222aeb4d51.
2021-06-08 21:23:08 +01:00
David Green 222aeb4d51 [DSE] Remove stores in the same loop iteration
DSE will currently only remove stores in the same block unless they can
be guaranteed to be loop invariant. This expands that to any stores that
are in the same Loop, at the same loop level. This should still account
for where AA/MSSA will not handle aliasing between loops, but allow the
dead stores to be removed where they overlap in the same loop iteration.
It requires adding loop info to DSE, but that looks fairly harmless.

The test case this helps is from code like this, which can come up in
certain matrix operations:
  for(i=..)
    dst[i] = 0;
    for(j=..)
      dst[i] += src[i*n+j];

After LICM, this becomes:
for(i=..)
  dst[i] = 0;
  sum = 0;
  for(j=..)
    sum += src[i*n+j];
  dst[i] = sum;

The first store is dead, and with this patch is now removed.

Differntial Revision: https://reviews.llvm.org/D100464
2021-05-31 10:22:37 +01:00
David Green f7cb654763 [DSE] Move isOverwrite into DSEState. NFC
This moves the isOverwrite function into the DSEState so that it can
share the analyses and members from the state.

A few extra loop tests were also added to test stores in and around
multi block loops for D100464.
2021-05-14 09:16:51 +01:00
Nikita Popov 176bbcae11 [DSE] Remove MemDep-based implementation
The MemorySSA-based implementation has been enabled without issue
for a while now, so keeping the old implementation around doesn't
seem useful anymore. This drops the MemDep-based implementation.

Differential Revision: https://reviews.llvm.org/D97877
2021-03-07 18:17:31 +01:00