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

improve DEBUG=2 string with TB/s and TFLOPS [pr] (#11875)

Browse Source
This commit is contained in:
George Hotz
2025-08-27 11:42:41 -07:00
committed by GitHub
parent e9789d8a70
commit e4afdf9ea1
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tinygrad/engine/realize.py
+8 -3
View File
@@ -160,10 +160,15 @@ class ExecItem:
if DEBUG >= 2:
lds_est = sym_infer(self.prg.estimates.lds, var_vals)
mem_est = min(mem_est, lds_est) # there can't be more memory accessed than loads/stores. remove this when symbolic is fixed
header_color = 'magenta' if jit else ('green' if self.prg.first_run else None)
ptm = colored(time_to_str(et, w=9), "yellow" if et > 0.01 else None) if et is not None else ""
print(f"{colored(f'*** {self.prg.device[:7]:7s} {GlobalCounters.kernel_count:4d}', 'magenta' if jit else ('green' if self.prg.first_run else None))} {self.prg.display_name+' '*(44-ansilen(self.prg.display_name))} arg {len(bufs):2d} mem {GlobalCounters.mem_used/1e9:5.2f} GB " + # noqa: E501
(str() if et is None else f"tm {ptm}/{GlobalCounters.time_sum_s*1e3:9.2f}ms ({op_est/((et or 1e-20)*1e9):9.2f} GFLOPS {mem_est/((et or 1e-20)*1e9):6.1f}|{lds_est/((et or 1e-20)*1e9):<7.1f} GB/s)" + # noqa: E501
f" {[repr(m) if TRACEMETA >= 2 else str(m) for m in self.metadata] if self.metadata else ''}"))
flops, membw, ldsbw = op_est/(et or 1e-20), mem_est/(et or 1e-20), lds_est/(et or 1e-20)
flops_str = f"{flops*1e-9:9.2f} GFLOPS" if flops < 1e14 else colored(f"{flops*1e-12:9.2f} TFLOPS", 'green')
mem_str = f"{membw*1e-9:6.1f}|{ldsbw*1e-9:<7.1f} GB/s" if membw < 1e13 else colored(f"{membw*1e-12:6.1f}|{ldsbw*1e-12:<7.1f} TB/s", 'green')
print(f"{colored(f'*** {self.prg.device[:7]:7s} {GlobalCounters.kernel_count:4d}', header_color)}"+
f" {self.prg.display_name+' '*(44-ansilen(self.prg.display_name))} arg {len(bufs):2d} mem {GlobalCounters.mem_used/1e9:5.2f} GB"+
("" if et is None else f" tm {ptm}/{GlobalCounters.time_sum_s*1e3:9.2f}ms ({flops_str} {mem_str})")+
f" {[repr(m) if TRACEMETA >= 2 else str(m) for m in self.metadata] if self.metadata else ''}")
self.prg.first_run = False
return et