Lines Matching defs:GFX9

326      **GCN GFX9 (Vega)** [AMD-GCN-GFX900-GFX904-VEGA]_ [AMD-GCN-GFX906-VEGA7NM]_ [AMD-GCN-GFX908-CDNA1]_ [AMD-GCN-GFX90A-CDNA2]_ [AMD-GCN-GFX940-GFX942-CDNA3]_
897   GFX9-GFX11 the aperture base addresses are directly available as inline
967   GFX9-GFX11.
3531   For GFX9-GFX11 this is 4.
3534   For GFX9-GFX11 this is 1.
4217                                                                   GFX6-GFX9. A register
4225                                                                   Scratch (GFX7-GFX9)
4227                                                                   GFX8-GFX9). It does
4238                                                                   GFX6-GFX9. A register
4700                                                        associated dispatch AQL packet. It is only required for pre-GFX9
4828 supported except by flat and scratch instructions in GFX9-GFX11.
4847 GFX9-GFX11 the aperture base addresses are directly available as inline constant
4962      383:352 4 bytes COMPUTE_PGM_RSRC3               GFX6-GFX9
5033      458     1 bit   ENABLE_WAVEFRONT_SIZE32         GFX6-GFX9
5047      470:464 7 bits  KERNARG_PRELOAD_SPEC_LENGTH     GFX6-GFX9
5055      479:471 9 bits  KERNARG_PRELOAD_SPEC_OFFSET     GFX6-GFX9
5080                                                      GFX6-GFX9
5122                                                      GFX9
5239      21      1 bit   ENABLE_DX10_CLAMP               GFX9-GFX11
5268      23      1 bit   ENABLE_IEEE_MODE                GFX9-GFX11
5305                                                      GFX9-GFX12
5322      29      1 bit    WGP_MODE                       GFX6-GFX9
5334      30      1 bit    MEM_ORDERED                    GFX6-GFX9
5357      31      1 bit    FWD_PROGRESS                   GFX6-GFX9
5789                                                   may be needed for GFX9-GFX11 which
5895 instructions (GFX9-GFX11).
5972 GFX9-GFX11
6193 (GFX6-GFX8), or ``scratch_load/store`` (GFX9-GFX11). Since only a single thread
6292 Memory Model GFX6-GFX9
6295 For GFX6-GFX9:
6317   that for GFX7-GFX9 ``flat_load/store/atomic`` instructions can report out of
6379 The code sequences used to implement the memory model for GFX6-GFX9 are defined
6382   .. table:: AMDHSA Memory Model Code Sequences GFX6-GFX9
6387                   Ordering     Sync Scope     Address    GFX6-GFX9
16499      Usage               Code Sequence   GFX6-GFX8 Inputs GFX9-GFX11 Inputs Description
17537     GCN 5         :doc:`GFX9<AMDGPU/AMDGPUAsmGFX9>`             :doc:`gfx900<AMDGPU/AMDGPUAsmGFX900>`
17549     CDNA 1        :doc:`GFX9<AMDGPU/AMDGPUAsmGFX9>`             :doc:`gfx908<AMDGPU/AMDGPUAsmGFX908>`
17551     CDNA 2        :doc:`GFX9<AMDGPU/AMDGPUAsmGFX9>`             :doc:`gfx90a<AMDGPU/AMDGPUAsmGFX90a>`
17553     CDNA 3        :doc:`GFX9<AMDGPU/AMDGPUAsmGFX9>`             :doc:`gfx940<AMDGPU/AMDGPUAsmGFX940>`
17817 example, when assembling for a "GFX9" target this will be set to the integer
17988 example, when assembling for a "GFX9" target this will be set to the integer
18187      ``.amdhsa_fp16_overflow``                                0                   GFX9-GFX12   Controls FP16_OVFL in