github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-09 15:08:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

am: make mqd contig (#13786)

Browse Source
This commit is contained in:
nimlgen
2025-12-21 17:00:33 +03:00
committed by GitHub
parent 09e060eab5
commit e523971028
1 changed files with 4 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tinygrad/runtime/support/am/ip.py
View File

@@ -273,11 +273,10 @@ class AM_GFX(AM_IP):
def setup_ring(self, ring_addr:int, ring_size:int, rptr_addr:int, wptr_addr:int, eop_addr:int, eop_size:int, doorbell:int, pipe:int, queue:int,
aql:bool) -> int:
mqd = self.adev.mm.valloc(0x1000 * self.xccs, uncached=True, contiguous=True)
for xcc in range(self.xccs if aql else 1):
mqd = self.adev.mm.valloc(0x1000, uncached=True, contiguous=True)
struct_t = getattr(am, f"struct_v{self.adev.ip_ver[am.GC_HWIP][0]}{'_compute' if self.adev.ip_ver[am.GC_HWIP][0] >= 10 else ''}_mqd")
mqd_struct = struct_t(header=0xC0310800, cp_mqd_base_addr_lo=lo32(mqd.va_addr), cp_mqd_base_addr_hi=hi32(mqd.va_addr),
mqd_struct = struct_t(header=0xC0310800, cp_mqd_base_addr_lo=lo32(mqd.va_addr + 0x1000*xcc), cp_mqd_base_addr_hi=hi32(mqd.va_addr + 0x1000*xcc),
cp_hqd_persistent_state=self.adev.regCP_HQD_PERSISTENT_STATE.encode(preload_size=0x55, preload_req=1),
cp_hqd_pipe_priority=0x2, cp_hqd_queue_priority=0xf, cp_hqd_quantum=0x111,
cp_hqd_pq_base_lo=lo32(ring_addr>>8), cp_hqd_pq_base_hi=hi32(ring_addr>>8),
@@ -290,11 +289,11 @@ class AM_GFX(AM_IP):
cp_mqd_control=self.adev.regCP_MQD_CONTROL.encode(priv_state=1), cp_hqd_vmid=0, cp_hqd_aql_control=int(aql),
cp_hqd_eop_base_addr_lo=lo32(eop_addr>>8), cp_hqd_eop_base_addr_hi=hi32(eop_addr>>8),
cp_hqd_eop_control=self.adev.regCP_HQD_EOP_CONTROL.encode(eop_size=(eop_size//4).bit_length()-2),
**({'compute_tg_chunk_size':1, 'compute_current_logic_xcc_id':xcc} if aql and self.xccs > 1 else {}))
**({'compute_tg_chunk_size':1, 'compute_current_logic_xcc_id':xcc, 'cp_mqd_stride_size':0x1000} if aql and self.xccs > 1 else {}))
for se in range(8 if self.adev.ip_ver[am.GC_HWIP][0] >= 10 else 4): setattr(mqd_struct, f'compute_static_thread_mgmt_se{se}', 0xffffffff)
# Copy mqd into memory
self.adev.vram.view(mqd.paddrs[0][0], ctypes.sizeof(mqd_struct))[:] = memoryview(mqd_struct).cast('B')
self.adev.vram.view(mqd.paddrs[0][0] + 0x1000*xcc, ctypes.sizeof(mqd_struct))[:] = memoryview(mqd_struct).cast('B')
self.adev.gmc.flush_hdp()
self._grbm_select(me=1, pipe=pipe, queue=queue, inst=xcc)