Skip to content

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

← Back to compiled benchmarks

Result

Field Value
Operator Stack
Category linop
Method adj
Device cpu
Dtype torch.float32
Compile level wrapper
Compile config default
Status ok
Class compiles_slower
Graph breaks 0
Recompiles —
Eager time 425.23 us
Compiled time 499.47 us
Speedup 0.85x
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 cpu 6 24.00 B False True [2, 1]
output [4] torch.float32 cpu 4 16.00 B False True [1]

Graph-break locations

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

Notes

—