functional.fold — fwd (cpu, torch.complex64, inner, default)
← Back to compiled benchmarks
Result
| Field |
Value |
| Operator |
functional.fold |
| Category |
functional |
| Method |
fwd |
| Device |
cpu |
| Dtype |
torch.complex64 |
| Compile level |
inner |
| Compile config |
default |
| Status |
ok |
| Class |
works |
| Graph breaks |
0 |
| Recompiles |
— |
| Eager time |
21.39 us |
| Compiled time |
16.58 us |
| Speedup |
1.29x |
| Max abs diff |
0.0 |
| Max rel diff |
0.0 |
| Degraded |
False |
Tensors
| Tensor |
Shape |
Dtype |
Device |
Numel |
Bytes |
View |
Contiguous |
Stride |
| input |
[2, 2, 2, 4, 4] |
torch.complex64 |
cpu |
128 |
1.00 KB |
False |
True |
[64, 32, 16, 4, 1] |
| output |
[2, 8, 8] |
torch.complex64 |
cpu |
128 |
1.00 KB |
True |
True |
[64, 8, 1] |
Notes
—