Skip to content

SumReduce — fwd (cpu, torch.float32, wrapper, default)

← Back to compiled benchmarks

Result

Field Value
Operator SumReduce
Category linop
Method fwd
Device cpu
Dtype torch.float32
Compile level wrapper
Compile config default
Status ok
Class works
Graph breaks 0
Recompiles —
Eager time 11.72 us
Compiled time 9.77 us
Speedup 1.20x
Max abs diff 0.0
Max rel diff 0.0
Degraded False

Tensors

Tensor Shape Dtype Device Numel Bytes View Contiguous Stride
input [5, 2, 3] torch.float32 cpu 30 120.00 B False True [6, 3, 1]
output [5, 2] torch.float32 cpu 10 40.00 B False True [2, 1]

Notes

—