Acim-Maravic f3138524db [AMDGPU] Generic lowering for rint and nearbyint (#69596) ...

The are three different rounding intrinsics, that are brought down to
same instruction.

Co-authored-by: Acim Maravic <acim.maravic@amd.com>

2023-11-14 18:49:21 +01:00

..

add-sub.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

addrspacecast.ll

…

aggregates.ll

…

arith-fp.ll

…

arith-sminmax.ll

…

arith-ssat.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

arith-uminmax.ll

…

arith-usat.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

bit-ops.ll

…

cast.ll

[opt] Infer DataLayout from triple if not specified

2023-10-26 12:07:37 -07:00

control-flow.ll

…

div.ll

…

extractelement.ll

…

fabs.ll

…

fadd.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

fdiv.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

fma.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

fmul.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

fneg.ll

…

fptosi.ll

…

fptoui.ll

…

fround.ll

[AMDGPU] Generic lowering for rint and nearbyint (#69596)

2023-11-14 18:49:21 +01:00

fsub.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

fused_costs.ll

…

gep.ll

…

insertelement.ll

…

lit.local.cfg

…

load-to-trunc.ll

[opt] Infer DataLayout from triple if not specified

2023-10-26 12:07:37 -07:00

logicalop.ll

…

mul.ll

[AMDGPU] make v32i16/v32f16 legal (#70484)

2023-10-27 15:28:31 -07:00

reduce-and.ll

…

reduce-or.ll

…

rem.ll

…

shifts.ll

…

shufflevector.ll

…