Hpt
Home
GitHub
crate.io
Benchmarks
Home
GitHub
crate.io
Benchmarks
  • Benchmarks

    • unary
    • binary
    • reduce
    • conv(f32)
    • conv(f16)
    • pooling
    • normalization
    • matmul
    • fft
    • nn

      • resnet(f32)
      • resnet(f16)
      • lstm
Conv2d f16 Performance (width = 256, height = 256, out channel = 128, kernel size = 3)
Conv2d f16 Performance (width = 256, height = 256, in channel = 128, kernel size = 3)
Conv2d f16 Performance (in channel = 128, out channel = 128, kernel size = 3)

Compilation config

[profile.release]
opt-level = 3
incremental = true
debug = true
lto = "fat"
codegen-units = 1

Running Threads

10

Device specification

CPU: 12th Gen Intel(R) Core(TM) i5-12600K 3.69 GHz

RAM: G.SKILL Trident Z Royal Series (Intel XMP) DDR4 64GB

System: Windows 11 Pro 23H2

最近更新:: 2025/4/19 02:39
Contributors: Jianqoq
Prev
conv(f32)
Next
pooling