Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

remove had_counter from rand #593

Closed
wants to merge 1 commit into from
Closed

remove had_counter from rand #593

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 5 additions & 8 deletions tinygrad/tensor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -492,6 +492,10 @@ def rand(*shape, device:Optional[str]=None, dtype:Optional[DTypeLike]=None, cont
if device is not None and not isinstance(device, str): raise ValueError(f"rand only supports single device, got {device=}")
_device = device = Device.canonicalize(device)

# if shape has 0, return zero tensor
if (numel := prod(shape)) == 0: return Tensor.zeros(shape, device=_device, dtype=dtype, **kwargs)
num = ceildiv(numel * dtype.itemsize, 4)

# when using MOCKGPU and NV generate rand on CLANG
if getenv("MOCKGPU") and device.startswith("NV"): device = "CLANG"

Expand All @@ -501,15 +505,8 @@ def rand(*shape, device:Optional[str]=None, dtype:Optional[DTypeLike]=None, cont
[int.from_bytes(hashlib.sha256(len(Tensor._device_seeds).to_bytes(4, "big")).digest(), "big"), Tensor._seed],
device=device, dtype=dtypes.uint32, requires_grad=False)
Tensor._device_rng_counters[device] = Tensor([0], device=device, dtype=dtypes.uint32, requires_grad=False)
had_counter = False
else: had_counter = True

# if shape has 0, return zero tensor
if (numel := prod(shape)) == 0: return Tensor.zeros(shape, device=_device, dtype=dtype, **kwargs)
num = ceildiv(numel * dtype.itemsize, 4)

# increment rng counter for devices
if had_counter: Tensor._device_rng_counters[device].assign(Tensor._device_rng_counters[device] + num).contiguous()
else: Tensor._device_rng_counters[device].assign(Tensor._device_rng_counters[device] + num).contiguous()

# threefry random bits
counts0 = (Tensor.arange(ceildiv(num, 2), device=device, dtype=dtypes.uint32, requires_grad=False)+Tensor._device_rng_counters[device])
Expand Down
Loading