9c7833faf9
* Vegetarian Filet o Fish model * fix.. atc.. * test cluster_speed_limit * fix.. cluster_speed_limit.. 2 * fix.. clusterspeedlimit3 * cruise speed to roadlimit speed * fix.. * fix.. eng * deltaUp/Down for lanechange * fix.. atc desire... * fix.. * ff * ff * fix.. * fix.. eng * fix engsound * Update desire_helper.py * fix.. connect... * fix curve_min speed * Revert "fix curve_min speed" This reverts commit fcc9c2eb14eb3504abef3e420db93e8882e56f37. * Reapply "fix curve_min speed" This reverts commit 2d2bba476c58a7b4e13bac3c3ad0e4694c95515d. * fix.. auto speed up.. roadlimit * fix.. atc auto lanechange... * Update desire_helper.py * Update cruise.py * debug atc... * fix.. waze alert offset.. * fix.. * test atc.. * fix.. * fix.. atc * atc test.. * fix.. atc * fix.. atc2 * fix.. atc3 * KerryGold Model. latsmooth_sec = 0.0 * lat smooth seconds 0.13 * fix comment * fix.. auto cruise, and speed unit * change lanemode switching. * erase mazda lkas button.
71 lines
2.4 KiB
Python
71 lines
2.4 KiB
Python
import gc
|
|
from tinygrad import Tensor, UOp, Device
|
|
from tinygrad.shape.shapetracker import views_to_indexed_uops
|
|
from tinygrad.engine.realize import method_cache, get_program
|
|
|
|
def uops_allocated(): return sum([isinstance(x, UOp) for x in gc.get_objects()])
|
|
def print_uops():
|
|
for x in gc.get_objects():
|
|
if isinstance(x, UOp): print(x)
|
|
|
|
def start(): pass
|
|
def single_tensor(): Tensor([2])
|
|
def two_plus_two(): Tensor([2])+Tensor([2])
|
|
def two_plus_two_schedule(): (Tensor([2])+Tensor([2])).schedule()
|
|
def two_plus_two_kernel():
|
|
si = (Tensor([2])+Tensor([2])).schedule()[-1]
|
|
get_program(Device.default.renderer, si.ast)
|
|
def two_plus_two_linearize():
|
|
si = (Tensor([2])+Tensor([2])).schedule()[-1]
|
|
get_program(Device.default.renderer, si.ast)
|
|
def two_plus_two_realize(): (Tensor([2])+Tensor([2])).realize()
|
|
def two_plus_two_item(): (Tensor([2])+Tensor([2])).item()
|
|
def gradient_test():
|
|
x = Tensor.eye(3, requires_grad=True)
|
|
y = Tensor([[2.0,0,-2.0]], requires_grad=True)
|
|
z = y.matmul(x).sum()
|
|
z.backward()
|
|
def realized_eye():
|
|
Tensor.eye(3, requires_grad=True).realize()
|
|
def realized_list():
|
|
Tensor([[2.0,0,-2.0]], requires_grad=True).realize()
|
|
def kernel_matmul():
|
|
x = Tensor.eye(3, requires_grad=True)
|
|
y = Tensor([[2.0,0,-2.0]], requires_grad=True)
|
|
z = y.matmul(x)
|
|
si = z.schedule()[-1]
|
|
get_program(Device.default.renderer, si.ast)
|
|
def realized_matmul():
|
|
x = Tensor.eye(3, requires_grad=True)
|
|
y = Tensor([[2.0,0,-2.0]], requires_grad=True)
|
|
z = y.matmul(x)
|
|
Tensor.realize(z)
|
|
def realized_gradient():
|
|
x = Tensor.eye(3, requires_grad=True)
|
|
y = Tensor([[2.0,0,-2.0]], requires_grad=True)
|
|
z = y.matmul(x).sum()
|
|
z.backward()
|
|
Tensor.realize(x, y, z, x.grad, y.grad)
|
|
tests = [start, single_tensor, two_plus_two, two_plus_two_schedule, two_plus_two_kernel,
|
|
two_plus_two_linearize, two_plus_two_realize, two_plus_two_item, gradient_test,
|
|
realized_eye, realized_list, kernel_matmul, realized_matmul, realized_gradient]
|
|
|
|
if __name__ == "__main__":
|
|
gc.disable()
|
|
start_uops = uops_allocated()
|
|
# there's a few consts created as default values
|
|
print_uops()
|
|
for t in tests:
|
|
t()
|
|
|
|
# these caches will keep uops alive
|
|
method_cache.clear()
|
|
views_to_indexed_uops.cache_clear()
|
|
|
|
new_uops = uops_allocated()
|
|
gc.collect()
|
|
new_uops_gc = uops_allocated()
|
|
print(f"{t.__name__:30s}: {new_uops:3d} -> {new_uops_gc:3d}")
|
|
assert new_uops == start_uops
|
|
#print_uops()
|