nimlgen/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Activity

Add method to return field masks for AMDReg (#10511)

Browse Source
This commit is contained in:
Panagiotis Kourouklidis
2025-05-25 14:47:20 -07:00
committed by GitHub
parent 88c5864bf3
commit 4941486cb0
2 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tinygrad/runtime/ops_amd.py
+3 -3
View File
@@ -190,15 +190,15 @@ class AMDComputeQueue(HWQueue):
self.wreg(self.gc.regGRBM_GFX_INDEX, se_index=se, instance_broadcast_writes=1)
# Wait for FINISH_PENDING==0
self.pkt3(self.pm4.PACKET3_WAIT_REG_MEM, self.pm4.WAIT_REG_MEM_FUNCTION(WAIT_REG_MEM_FUNCTION_EQ),
self.gc.regSQ_THREAD_TRACE_STATUS.addr, 0, 0, self.gc.SQ_THREAD_TRACE_STATUS__FINISH_PENDING_MASK, 4)
self.gc.regSQ_THREAD_TRACE_STATUS.addr, 0, 0, self.gc.regSQ_THREAD_TRACE_STATUS.field_mask('finish_pending'), 4)
# Wait for FINISH_DONE!=0
self.pkt3(self.pm4.PACKET3_WAIT_REG_MEM, self.pm4.WAIT_REG_MEM_FUNCTION(WAIT_REG_MEM_FUNCTION_NEQ),
self.gc.regSQ_THREAD_TRACE_STATUS.addr, 0, 0, self.gc.SQ_THREAD_TRACE_STATUS__FINISH_DONE_MASK, 4)
self.gc.regSQ_THREAD_TRACE_STATUS.addr, 0, 0, self.gc.regSQ_THREAD_TRACE_STATUS.field_mask('finish_done'), 4)
# Disable SQTT
self.sqtt_config(tracing=False)
# Wait for BUSY==0
self.pkt3(self.pm4.PACKET3_WAIT_REG_MEM, self.pm4.WAIT_REG_MEM_FUNCTION(WAIT_REG_MEM_FUNCTION_EQ),
self.gc.regSQ_THREAD_TRACE_STATUS.addr, 0, 0, self.gc.SQ_THREAD_TRACE_STATUS__BUSY_MASK, 4)
self.gc.regSQ_THREAD_TRACE_STATUS.addr, 0, 0, self.gc.regSQ_THREAD_TRACE_STATUS.field_mask('busy'), 4)
# Copy WPTR to memory (src_sel = perf, dst_sel = tc_l2, wr_confirm = True)
self.pkt3(self.pm4.PACKET3_COPY_DATA, 1 << 20 | 2 << 8 | 4, self.gc.regSQ_THREAD_TRACE_WPTR.addr, 0, *data64_le(wptrs.va_addr+(se*4)))
# Restore global broadcasting
tinygrad/runtime/support/amd.py
+4
View File
@@ -11,6 +11,10 @@ class AMDReg:
def encode(self, **kwargs) -> int: return functools.reduce(int.__or__, (value << self.fields[name][0] for name,value in kwargs.items()), 0)
def decode(self, val: int) -> dict: return {name:getbits(val, start, end) for name,(start,end) in self.fields.items()}
def field_mask(self, field_name) -> int:
start, end = self.fields[field_name]
num_bits = end - start + 1
return ((1 << num_bits) - 1) << start
@property
def addr(self): return self.bases[self.segment] + self.offset