Matt Arsenault a2a73d892a AMDGPU: Fix no return atomicrmw fadd v2f16 selection for gfx908 (#96948) ...

We previously would always expand this with a cmpxchg loop, while
it should be the same conditions as the f32 case (except for the
denormal concern).

2024-06-27 21:17:16 +02:00

..

expand-atomic-f32-agent.ll

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (#95592)

2024-06-23 10:10:41 +02:00

expand-atomic-f32-system.ll

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (#95592)

2024-06-23 10:10:41 +02:00

expand-atomic-f64-agent.ll

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (#95592)

2024-06-23 10:10:41 +02:00

expand-atomic-f64-system.ll

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (#95592)

2024-06-23 10:10:41 +02:00

expand-atomic-fp128.ll

AMDGPU: Add some tests for i128 and fp128 atomic expansion

2024-06-18 10:33:25 +02:00

expand-atomic-i8-system.ll

AtomicExpand: Emit or with constant on RHS

2024-04-23 15:00:31 +02:00

expand-atomic-i8.ll

AtomicExpand: Fix creating invalid ptrmask for fat pointers (#94955)

2024-06-12 10:45:42 +02:00

expand-atomic-i16-system.ll

AMDGPU: Do not bitcast atomicrmw in IR (#90045)

2024-05-07 18:26:32 +02:00

expand-atomic-i16.ll

AtomicExpand: Fix creating invalid ptrmask for fat pointers (#94955)

2024-06-12 10:45:42 +02:00

expand-atomic-i32-agent.ll

AMDGPU: Add more tests for atomicrmw handling

2024-05-03 11:50:59 +02:00

expand-atomic-i32-system.ll

AMDGPU: Update name for amdgpu.no.remote.memory metadata

2024-05-03 11:50:59 +02:00

expand-atomic-i64-agent.ll

AMDGPU: Add more tests for atomicrmw handling

2024-05-03 11:50:59 +02:00

expand-atomic-i64-system.ll

AMDGPU: Update name for amdgpu.no.remote.memory metadata

2024-05-03 11:50:59 +02:00

expand-atomic-i128.ll

AMDGPU: Add some tests for i128 and fp128 atomic expansion

2024-06-18 10:33:25 +02:00

expand-atomic-mmra.ll

[IR] Memory Model Relaxation Annotations (#78569)

2024-04-24 08:52:25 +02:00

expand-atomic-rmw-fadd-flat-specialization.ll

…

expand-atomic-rmw-fadd.ll

AMDGPU: Fix no return atomicrmw fadd v2f16 selection for gfx908 (#96948)

2024-06-27 21:17:16 +02:00

expand-atomic-rmw-fmax.ll

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (#95592)

2024-06-23 10:10:41 +02:00

expand-atomic-rmw-fmin.ll

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (#95592)

2024-06-23 10:10:41 +02:00

expand-atomic-rmw-fsub.ll

…

expand-atomic-rmw-nand.ll

…

expand-atomic-simplify-cfg-CAS-block.ll

…

expand-atomic-v2bf16-agent.ll

Reapply "AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (#95394)"

2024-06-17 16:34:35 +02:00

expand-atomic-v2bf16-system.ll

Reapply "AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (#95394)"

2024-06-17 16:34:35 +02:00

expand-atomic-v2f16-agent.ll

Reapply "AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (#95394)"

2024-06-17 16:34:35 +02:00

expand-atomic-v2f16-system.ll

Reapply "AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (#95394)"

2024-06-17 16:34:35 +02:00

expand-atomicrmw-fp-vector.ll

Reapply "AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (#95394)"

2024-06-17 16:34:35 +02:00

expand-atomicrmw-integer-ops-0-to-add-0.ll

AMDGPU: Add more tests for atomicrmw handling

2024-05-03 11:50:59 +02:00

lit.local.cfg

…

no-expand-atomic-load.ll

AMDGPU: Do not bitcast atomic load in IR (#90060)

2024-04-26 12:20:40 +02:00

no-expand-atomic-store.ll

AMDGPU: Don't bitcast float typed atomic store in IR (#90116)

2024-05-07 21:43:22 +02:00

unaligned-atomic.ll

…