6 Commits

Author SHA1 Message Date
Ulrich Weigand
0a0cac6dbd
[SystemZ] Simplify f128 atomic load/store (#90977)
Change definition of expandBitCastI128ToF128 and expandBitCastF128ToI128
to allow for simplified use in atomic load/store.

Update logic to split 128-bit loads and stores in DAGCombine to also
handle the f128 case where appropriate. This fixes the regressions
introduced by recent atomic load/store patches.
2024-05-06 12:17:19 +02:00
Matt Arsenault
38f9c013a0
SystemZ: Stop casting fp typed atomic loads in the IR (#90768)
shouldCastAtomicLoadInIR is a hack that should be removed. Simple
bitcasting of operations should be in the domain of ordinary type
legalization and does not need to be done in the IR.

This introduces a code quality regression due to the hack currently used
to avoid using 128-bit values in the case where the floating point value
is ultimately used as an integer. This would be avoidable if there were
always a legal 128-bit type (like v2i64). This is a pretty niche
situation so I assume it's not important.

I implemented about 85% of the work necessary to make v2i64 legal, but
it was taking too long and I lack the necessary familiarity with systemz
to complete it. I've pushed it here for someone to pick up:
https://github.com/arsenm/llvm-project/pull/new/systemz-legal-v2i64

Depends #90861
2024-05-02 21:31:29 +02:00
Matt Arsenault
3a1e55904b
SystemZ: Add some tests for fp128 atomics with soft-float (#90826) 2024-05-02 15:22:34 +02:00
Matt Arsenault
738c135ee0
SystemZ: Add more tests for fp128 atomics (#90269)
These did not have proper floating point uses so weren't representative
samples. The bitcast inserted by lowering could be absorbed by the
load/store on the source/use.
2024-04-27 20:26:09 +02:00
Jonas Paulsson
74a09bd1ec
[SystemZ] Test improvements for atomic load/store instructions (NFC). (#75630)
Improve tests for atomic loads and stores, mainly by testing 128-bit atomic load and store instructions both with and w/out natural alignment.
2023-12-21 20:48:00 +01:00
Ilya Leoshkevich
03934e70ef
[SystemZ] Enable AtomicExpand pass (#70398)
The upcoming OpenMP support for SystemZ requires handling of IR insns
like `atomicrmw fadd`. Normally atomic float operations are expanded by
Clang and such insns do not occur, but OpenMP generates them directly.
Other architectures handle this using the AtomicExpand pass, which
SystemZ did not need so far. Enable it.

Currently AtomicExpand treats atomic load and stores of floats
pessimistically: it casts them to integers, which SystemZ does not need,
since the floating point load and store instructions are already atomic.
However, the way Clang currently expands them is pessimistic as well, so
this change does not make things worse. Optimizing operations on atomic
floats can be a separate change in the future.

This change does not create any differences the Linux kernel build.
2023-10-31 09:51:06 +01:00