IP PortfolioCompute acceleratorsgpu
of_acc_gpu_memsys
GPU memory subsystem
Maturity plannedTargets FPGA + ASICDifficulty Very hardPriority 2
Sliced GPU L2 cache with atomics, GPU MMU with multi-level TLBs and replayable page faults, and compression metadata handling.
Planned. This block is specified in the catalog with its interfaces and targets. No implementation exists yet; the skeleton command below generates a lint-clean shell with its ports and registers.
Interfaces
| Port | Direction | Kind | Width | Notes |
|---|---|---|---|---|
| ctrl | in/out | AXI4-Lite control bus | 32 | Control and status registers, including ID, VERSION and STATUS |
| irq | out | interrupt | 1 | Interrupt request |
Standards
No external standard applies.
More in gpu
| ID | Block | Maturity |
|---|---|---|
| of_acc_gpu_simt_core | SIMT shader core | planned |
| of_acc_gpu_tensor_core | GPU tensor core | planned |
| of_acc_gpu_cmd_proc | GPU command processor | planned |
| of_acc_gpu_geometry | Geometry front end | planned |
| of_acc_gpu_rasterizer | Rasteriser | planned |
| of_acc_gpu_texture | Texture unit | planned |
| of_acc_gpu_rop | Render output unit | planned |
| of_acc_gpu_tbdr | Tile-based rendering binner | planned |
| of_acc_gpu_compute | Compute-only GPU cluster | planned |
| of_acc_gpu_raytrace | Ray tracing BVH unit | planned |