Skip to content

Concat — fwd (cuda, torch.float32, wrapper, default)

← Back to compiled benchmarks

Result

Field Value
Operator Concat
Category linop
Method fwd
Device cuda
Dtype torch.float32
Compile level wrapper
Compile config default
Status ok
Class works_with_breaks
Graph breaks 1
Recompiles —
Eager time 715.86 us
Compiled time 763.79 us
Speedup 0.94x
Max abs diff 0.0
Max rel diff 0.0
Degraded False

Tensors

Tensor Shape Dtype Device Numel Bytes View Contiguous Stride
input [1, 8] torch.float32 cuda:0 8 32.00 B False True [8, 1]
output [1, 3] torch.float32 cuda:0 3 12.00 B False True [3, 1]

Graph-break locations

  • /home/mark/.local/share/opencode/worktree/d3d230/compiled-benchmarks/src/torchlinops/linops/namedlinop.py:151 in forward: Data-dependent branching
  • /home/mark/.local/share/opencode/worktree/d3d230/compiled-benchmarks/src/torchlinops/linops/concat.py:173 in _fn: generic_jump TensorVariable()

Notes

—