geohot/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Actions Activity

usb amd: yield between signal polls (#17712)

Browse Source 
* AMD_USB_POLL_US

* com

* its micro
This commit is contained in:
YassineYousfi
2026-08-25 14:11:53 -07:00
committed by GitHub
parent 7fef98c86e
commit 2824504f90
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tinygrad/runtime/ops_amd.py
+4 -2
View File
@@ -25,6 +25,7 @@ SQTT = ContextVar("SQTT", abs(VIZ.value)>=2)
SQTT_ITRACE_SE_MASK, SQTT_LIMIT_SE, SQTT_SIMD_SEL, SQTT_TOKEN_EXCLUDE = \
ContextVar("SQTT_ITRACE_SE_MASK", 0b11), ContextVar("SQTT_LIMIT_SE", 0), ContextVar("SQTT_SIMD_SEL", 0), ContextVar("SQTT_TOKEN_EXCLUDE", 0)
PMC = ContextVar("PMC", abs(VIZ.value)>=2)
AMD_USB_POLL_US = getenv("AMD_USB_POLL_US", 500) # microseconds to sleep between USB signal polls. 0 disables
EVENT_INDEX_PARTIAL_FLUSH = 4 # based on a comment in nvd.h
WAIT_REG_MEM_FUNCTION_EQ = 3 # ==
WAIT_REG_MEM_FUNCTION_NEQ = 4 # !=
@@ -45,8 +46,9 @@ class AMDSignal(HCQSignal):
def __init__(self, *args, **kwargs): super().__init__(*args, **{**kwargs, 'timestamp_divider': 100})
def _sleep(self, time_spent_since_last_sleep_ms:int):
# Reasonable to sleep for long workloads (which take more than 200ms) and only timeline signals.
if time_spent_since_last_sleep_ms > 200 and self.owner is not None: self.owner.iface.sleep(200)
# USB signals live in VRAM across the link, so yield between polls. Native AMD only blocks after 200 ms.
if self.owner is not None and self.owner.is_usb() and AMD_USB_POLL_US: time.sleep(AMD_USB_POLL_US / 1e6)
elif time_spent_since_last_sleep_ms > 200 and self.owner is not None: self.owner.iface.sleep(200)
class AMDComputeQueue(HWQueue):
def __init__(self, dev:AMDDevice):