Skip to content

Stack — adj (cuda, torch.float32, wrapper, default)

← Back to compiled benchmarks

Result

Field Value
Operator Stack
Category linop
Method adj
Device cuda
Dtype torch.float32
Compile level wrapper
Compile config default
Status ok
Class works_with_breaks
Graph breaks 1
Recompiles —
Eager time 799.12 us
Compiled time 838.73 us
Speedup 0.95x
Max abs diff 0.0
Max rel diff 0.0
Degraded False

Tensors

Tensor Shape Dtype Device Numel Bytes View Contiguous Stride
input [3, 2] torch.float32 cuda:0 6 24.00 B False True [2, 1]
output [4] torch.float32 cuda:0 4 16.00 B False True [1]

Graph-break locations

  • /home/mark/.local/share/opencode/worktree/d3d230/compiled-benchmarks/src/torchlinops/linops/namedlinop.py:151 in forward: Unsupported method call
  • /home/mark/.local/share/opencode/worktree/d3d230/compiled-benchmarks/src/torchlinops/linops/stack.py:213 in _fn: Unsupported method call

Notes

—