llvm-project/llvm/test/Analysis/CostModel/AMDGPU
Alexey Bataev 60470ac7ff [Cost]Add tests for boolean and/or reductions, NFC.
Tests with the default costs for boolean and/or reductions.

Differential Revision: https://reviews.llvm.org/D97793
2021-03-03 12:34:30 -08:00
..
add-sub.ll
addrspacecast.ll
bit-ops.ll
br.ll
extractelement.ll
fabs.ll
fadd.ll [AMDGPU] gfx90a support 2021-02-17 16:01:32 -08:00
fdiv.ll [AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions. 2020-10-24 19:53:08 +03:00
fma.ll [AMDGPU] gfx90a support 2021-02-17 16:01:32 -08:00
fmul.ll [AMDGPU] gfx90a support 2021-02-17 16:01:32 -08:00
fneg.ll
fsub.ll [AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions. 2020-10-24 19:53:08 +03:00
fused_costs.ll [AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions. 2020-10-24 19:53:08 +03:00
insertelement.ll
lit.local.cfg
logicalop.ll [TTI] Consider select form of and/or i1 as having arithmetic cost 2021-03-02 02:18:19 +09:00
mul.ll [AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions. 2020-10-24 19:53:08 +03:00
reduce-and.ll [Cost]Add tests for boolean and/or reductions, NFC. 2021-03-03 12:34:30 -08:00
reduce-or.ll [Cost]Add tests for boolean and/or reductions, NFC. 2021-03-03 12:34:30 -08:00
shifts.ll [AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions. 2020-10-24 19:53:08 +03:00
shufflevector.ll