github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-04-29 03:00:14 -04:00
Code Issues Packages Projects Releases Wiki Activity

usb: faster custom (#15678)

Browse Source 
* usb: _f0_out_buf for e4 cmd as well

* custom speed

* fast
This commit is contained in:
nimlgen
2026-04-10 23:00:31 +03:00
committed by GitHub
parent 58646f9569
commit aa012d6f08
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tinygrad/runtime/ops_amd.py
View File

@@ -925,7 +925,8 @@ class USBIface(PCIIface):
return HCQBuffer(vaddr, size, meta=PCIAllocationMeta(region, has_cpu_mapping=False), view=self.pci_dev.dma_view(ctrl_addr, size), owner=self.dev)
def alloc(self, size:int, host=False, uncached=False, cpu_access=False, contiguous=False, force_devmem=False, **kwargs) -> HCQBuffer:
if (host or (uncached and cpu_access)) and self.sys_next_off + size < self.sys_buf.size:
# custom usb allocates uncached and cpu_access in vram. vram writes are faster than sram writes
if (host or (not self.pci_dev.usb.usb.is_custom and uncached and cpu_access)) and self.sys_next_off + size < self.sys_buf.size:
self.sys_next_off += size
return self.sys_buf.offset(self.sys_next_off - size, size)

3
tinygrad/runtime/support/usb.py
View File

@@ -175,8 +175,7 @@ class CustomASM24Controller:
self._pci_cacheable: list[tuple[int, int]] = []
self._pci_cache: dict[int, int|None] = {}
# Pre-allocate buffers for _f0_out (12 bytes) and _f0_in (8 bytes)
self._f0_out_buf, self._f0_out_mv = alloc_cbuffer(12)
self._f0_out_buf, self._f0_out_mv = alloc_cbuffer(0x1000) # for f0 and e4, allocate big enough for e4
self._f0_in_buf, _ = alloc_cbuffer(8)
# Verify custom firmware is running and PCIe link is up (LTSSM=0x78).