llvm-project

History

AMDGPU: Add back half and bfloat support for global_load_tr16 pats (#99540 )

half and bfloat are common types for 16-bit elements. The support of
them was original there and dropped due to some reasons. This work adds
the support of the float types back.

2024-07-18 11:23:35 -07:00

deprecated

…

irreducible

[AMDGPU] Fix filecheck annotation typos

2024-05-29 15:01:48 +01:00

MIR

AMDGPU: Support local atomicrmw fmin/fmax for float/double (#95590 )

2024-06-18 18:34:34 +02:00

always_uniform.ll

…

atomics.ll

[Analysis] Convert tests to opaque pointers (NFC)

2024-02-05 12:04:39 +01:00

b42473-r1-crash.ll

…

control-flow-intrinsics.ll

…

hidden_diverge.ll

…

hidden_loopdiverge.ll

…

inline-asm.ll

…

interp_f16.ll

…

intrinsics.ll

AMDGPU: Add back half and bfloat support for global_load_tr16 pats (#99540 )

2024-07-18 11:23:35 -07:00

join-at-loop-exit.ll

…

kernel-args.ll

…

lit.local.cfg

…

llvm.amdgcn.buffer.atomic.ll

[RFC][AMDGPU] Remove old llvm.amdgcn.buffer.* and tbuffer intrinsics (#93801 )

2024-06-10 12:14:51 +01:00

llvm.amdgcn.image.atomic.ll

…

no-return-blocks.ll

…

phi-undef.ll

…

propagate-loop-live-out.ll

…

temporal_diverge.ll

…

trivial-join-at-loop-exit.ll

…

unreachable-loop-block.ll

…

workitem-intrinsics.ll

…