[llvm] [AMDGPU][MC] Add dpp for V_PK_FMAC_F16 for GFX10 (PR #79598)

Georg Lehmann via llvm-commits llvm-commits at lists.llvm.org
Fri Jan 26 08:38:39 PST 2024

Previous message: [llvm] [AMDGPU][MC] Add dpp for V_PK_FMAC_F16 for GFX10 (PR #79598)
Next message: [llvm] [SLP] Initial vectorization of non-power-of-2 ops. (PR #77790)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

DadSchoorse wrote:

Another question is if `v_pk_fmac_f16_dpp16` supports abs/neg modifiers.

https://github.com/llvm/llvm-project/pull/79598

Previous message: [llvm] [AMDGPU][MC] Add dpp for V_PK_FMAC_F16 for GFX10 (PR #79598)
Next message: [llvm] [SLP] Initial vectorization of non-power-of-2 ops. (PR #77790)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list