Benchmarks 2024 11 26 TVM LLVM O3 spike_rv32_min - tum-ei-eda/muriscv-nn GitHub Wiki
Setup
Simulator
- Spike (
riscv-isa-sim) (ISS, CPI=1)- Spike :
eb0a3e2b0a7c57522928be39de95cd9f8c6dc636 - Spike PK :
fix-gcc14-rvv
- Spike :
Toolchains
-
RISC-V GCC:
- Scalar:
riscv32-unknown-elf-gcc (g8b4bb54e6c4) 14.2.1 20241118 - Vector:
riscv32-unknown-elf-gcc (g8b4bb54e6c4) 14.2.1 20241118 - Packed: Self compiled using patches found in https://github.com/riscv-collab/riscv-gcc/pull/258 and https://github.com/riscvarchive/riscv-binutils-gdb/pull/257
- Scalar:
-
LLVM/Clang:
clang version 18.1.8 (https://github.com/llvm/llvm-project.git 3b5b5c1ec4a3095ab096dd780e84d7ab81f3d7ff)- Linker: lld (TODO)
Models
-
MLPerfTiny Benchmark
-
TODO: others!
Frameworks
-
MLonMCU :
develop -
TVM :
Nightly Pre-Build
Miscellaneous
- Used
-Osflag for compilation. - Benchmarks generated using MLonMCU deployment tool with minimal efforts.
- Memory metrics are reported in Bytes
Results (Framework: tvm, Backend: tvmaot, Toolchain: llvm, Flags: -O3, Target: spike_rv32_min )
Audio Wake Words (aww)
| Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
|---|---|---|---|---|---|---|---|---|---|
13501144.0 ( 1.1x ) |
172048 ( 1.354 ) |
59492 ( 3.098 ) |
0 | NCHW | TVM | Fallback | RV32IM | 0 | - |
21040927.0 ( 0.7x ) |
155300 ( 1.222 ) |
59492 ( 3.098 ) |
0 | NHWC | TVM | Fallback | RV32IM | 0 | - |
- ( ?x ) |
165676 ( 1.304 ) |
59492 ( 3.098 ) |
128 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
166636 ( 1.311 ) |
59492 ( 3.098 ) |
256 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
167524 ( 1.318 ) |
59492 ( 3.098 ) |
512 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
170204 ( 1.34 ) |
59492 ( 3.098 ) |
1024 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
170664 ( 1.343 ) |
59492 ( 3.098 ) |
2048 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
171256 ( 1.348 ) |
59492 ( 3.098 ) |
4096 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
178572 ( 1.405 ) |
59492 ( 3.098 ) |
128 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
178516 ( 1.405 ) |
59492 ( 3.098 ) |
256 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
174524 ( 1.374 ) |
59492 ( 3.098 ) |
512 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
159584 ( 1.256 ) |
59492 ( 3.098 ) |
1024 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
159756 ( 1.257 ) |
59492 ( 3.098 ) |
2048 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
159520 ( 1.255 ) |
59492 ( 3.098 ) |
4096 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
15180408.0 ( Base ) |
127060 ( Base ) |
19204 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV32IM | 0 | - |
14522433.0 ( 1.0x ) |
126696 ( 0.997 ) |
23668 ( 1.232 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM | 0 | - |
- ( ?x ) |
135104 ( 1.063 ) |
19244 ( 1.002 ) |
128 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135120 ( 1.063 ) |
19204 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135120 ( 1.063 ) |
19204 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135120 ( 1.063 ) |
19204 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135120 ( 1.063 ) |
19204 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135120 ( 1.063 ) |
19204 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
5104729.0 ( 3.0x ) |
129636 ( 1.02 ) |
23668 ( 1.232 ) |
128 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
3970756.0 ( 3.8x ) |
129608 ( 1.02 ) |
23668 ( 1.232 ) |
256 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
3412486.0 ( 4.4x ) |
129608 ( 1.02 ) |
23668 ( 1.232 ) |
512 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
3371502.0 ( 4.5x ) |
129608 ( 1.02 ) |
23668 ( 1.232 ) |
1024 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
3371923.0 ( 4.5x ) |
129608 ( 1.02 ) |
23668 ( 1.232 ) |
2048 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
3372248.0 ( 4.5x ) |
129608 ( 1.02 ) |
23668 ( 1.232 ) |
4096 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
135812 ( 1.069 ) |
23708 ( 1.235 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135704 ( 1.068 ) |
23668 ( 1.232 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135704 ( 1.068 ) |
23668 ( 1.232 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135704 ( 1.068 ) |
23668 ( 1.232 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135656 ( 1.068 ) |
23668 ( 1.232 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
135656 ( 1.068 ) |
23668 ( 1.232 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
Image Classification (resnet)
| Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
|---|---|---|---|---|---|---|---|---|---|
61065388.0 ( 0.9x ) |
277900 ( 1.607 ) |
108404 ( 1.953 ) |
0 | NCHW | TVM | Fallback | RV32IM | 0 | - |
66654801.0 ( 0.8x ) |
267868 ( 1.549 ) |
108404 ( 1.953 ) |
0 | NHWC | TVM | Fallback | RV32IM | 0 | - |
- ( ?x ) |
351848 ( 2.035 ) |
108404 ( 1.953 ) |
128 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
349064 ( 2.019 ) |
108404 ( 1.953 ) |
256 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
349152 ( 2.019 ) |
108404 ( 1.953 ) |
512 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
348192 ( 2.014 ) |
108404 ( 1.953 ) |
1024 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347856 ( 2.012 ) |
108404 ( 1.953 ) |
2048 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
348108 ( 2.013 ) |
108404 ( 1.953 ) |
4096 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
54562451.0 ( 1.0x ) |
272028 ( 1.573 ) |
108404 ( 1.953 ) |
128 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
51420843.0 ( 1.1x ) |
271988 ( 1.573 ) |
108404 ( 1.953 ) |
256 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
268424 ( 1.552 ) |
108404 ( 1.953 ) |
512 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
266308 ( 1.54 ) |
108404 ( 1.953 ) |
1024 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
266052 ( 1.539 ) |
108404 ( 1.953 ) |
2048 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
265656 ( 1.536 ) |
108404 ( 1.953 ) |
4096 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
56117151.0 ( Base ) |
172900 ( Base ) |
55508 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV32IM | 0 | - |
72319168.0 ( 0.8x ) |
172316 ( 0.997 ) |
55508 ( 1.0 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM | 0 | - |
- ( ?x ) |
182636 ( 1.056 ) |
55540 ( 1.001 ) |
128 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
182780 ( 1.057 ) |
55508 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
182780 ( 1.057 ) |
55508 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
182780 ( 1.057 ) |
55508 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
182780 ( 1.057 ) |
55508 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
182780 ( 1.057 ) |
55508 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
15166972.0 ( 3.7x ) |
175976 ( 1.018 ) |
55508 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
9584333.0 ( 5.9x ) |
176124 ( 1.019 ) |
55508 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
7038743.0 ( 8.0x ) |
176124 ( 1.019 ) |
55508 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
5796679.0 ( 9.7x ) |
176124 ( 1.019 ) |
55508 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
4868892.0 ( 11.5x ) |
176124 ( 1.019 ) |
55508 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
4620135.0 ( 12.1x ) |
176124 ( 1.019 ) |
55508 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
181604 ( 1.05 ) |
55540 ( 1.001 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
181748 ( 1.051 ) |
55508 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
181748 ( 1.051 ) |
55508 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
181748 ( 1.051 ) |
55508 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
181748 ( 1.051 ) |
55508 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
181748 ( 1.051 ) |
55508 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
Anomaly Detection (toycar)
| Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
|---|---|---|---|---|---|---|---|---|---|
1646617.0 ( 1.0x ) |
621844 ( 1.799 ) |
5540 ( 1.169 ) |
0 | NCHW | TVM | Fallback | RV32IM | 0 | - |
1646617.0 ( 1.0x ) |
621844 ( 1.799 ) |
5540 ( 1.169 ) |
0 | NHWC | TVM | Fallback | RV32IM | 0 | - |
840888.0 ( 2.0x ) |
623712 ( 1.804 ) |
5540 ( 1.169 ) |
128 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
781448.0 ( 2.2x ) |
623468 ( 1.804 ) |
5540 ( 1.169 ) |
256 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
622784 ( 1.802 ) |
5540 ( 1.169 ) |
512 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
622500 ( 1.801 ) |
5540 ( 1.169 ) |
1024 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
632204 ( 1.829 ) |
5540 ( 1.169 ) |
2048 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
623196 ( 1.803 ) |
5540 ( 1.169 ) |
4096 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
840888.0 ( 2.0x ) |
623712 ( 1.804 ) |
5540 ( 1.169 ) |
128 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
781448.0 ( 2.2x ) |
623468 ( 1.804 ) |
5540 ( 1.169 ) |
256 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
622784 ( 1.802 ) |
5540 ( 1.169 ) |
512 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
622500 ( 1.801 ) |
5540 ( 1.169 ) |
1024 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
632204 ( 1.829 ) |
5540 ( 1.169 ) |
2048 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
623196 ( 1.803 ) |
5540 ( 1.169 ) |
4096 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
1717519.0 ( Base ) |
345656 ( Base ) |
4740 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV32IM | 0 | - |
1717519.0 ( 1.0x ) |
345656 ( 1.0 ) |
4740 ( 1.0 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM | 0 | - |
- ( ?x ) |
347096 ( 1.004 ) |
4740 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
620814.0 ( 2.8x ) |
347420 ( 1.005 ) |
4740 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
504124.0 ( 3.4x ) |
347384 ( 1.005 ) |
4740 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
445789.0 ( 3.9x ) |
347384 ( 1.005 ) |
4740 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
416941.0 ( 4.1x ) |
347384 ( 1.005 ) |
4740 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
413310.0 ( 4.2x ) |
347384 ( 1.005 ) |
4740 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
411455.0 ( 4.2x ) |
347384 ( 1.005 ) |
4740 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
347096 ( 1.004 ) |
4740 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
347008 ( 1.004 ) |
4740 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
Visual Wake Words (vww)
| Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
|---|---|---|---|---|---|---|---|---|---|
42157983.0 ( 1.1x ) |
665152 ( 1.837 ) |
181000 ( 2.113 ) |
0 | NCHW | TVM | Fallback | RV32IM | 0 | - |
55748115.0 ( 0.8x ) |
630596 ( 1.742 ) |
181000 ( 2.113 ) |
0 | NHWC | TVM | Fallback | RV32IM | 0 | - |
- ( ?x ) |
816876 ( 2.256 ) |
181000 ( 2.113 ) |
128 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
817704 ( 2.259 ) |
181000 ( 2.113 ) |
256 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
823108 ( 2.274 ) |
181000 ( 2.113 ) |
512 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
821988 ( 2.271 ) |
181000 ( 2.113 ) |
1024 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
821372 ( 2.269 ) |
181000 ( 2.113 ) |
2048 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
819564 ( 2.264 ) |
181000 ( 2.113 ) |
4096 | NCHW | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
707260 ( 1.954 ) |
181000 ( 2.113 ) |
128 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
707456 ( 1.954 ) |
181000 ( 2.113 ) |
256 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
701356 ( 1.937 ) |
181000 ( 2.113 ) |
512 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
679876 ( 1.878 ) |
181000 ( 2.113 ) |
1024 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
662276 ( 1.829 ) |
181000 ( 2.113 ) |
2048 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
656416 ( 1.813 ) |
181000 ( 2.113 ) |
4096 | NHWC | TVM | Fallback | RV32IM_ZVE64X | 0 | Loop+SLP |
45237678.0 ( Base ) |
362020 ( Base ) |
85640 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV32IM | 0 | - |
44813418.0 ( 1.0x ) |
361852 ( 1.0 ) |
85640 ( 1.0 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM | 0 | - |
- ( ?x ) |
370380 ( 1.023 ) |
85784 ( 1.002 ) |
128 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
370488 ( 1.023 ) |
85640 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
370488 ( 1.023 ) |
85640 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
370488 ( 1.023 ) |
85640 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
370488 ( 1.023 ) |
85640 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
370488 ( 1.023 ) |
85640 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
365224 ( 1.009 ) |
85640 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
365352 ( 1.009 ) |
85640 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
365352 ( 1.009 ) |
85640 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
365352 ( 1.009 ) |
85640 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
365348 ( 1.009 ) |
85640 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
365352 ( 1.009 ) |
85640 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector | RV32IM_ZVE64X | 0 | - |
- ( ?x ) |
371284 ( 1.026 ) |
85784 ( 1.002 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
371264 ( 1.026 ) |
85640 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
371268 ( 1.026 ) |
85640 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
371268 ( 1.026 ) |
85640 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
371216 ( 1.025 ) |
85640 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
- ( ?x ) |
371220 ( 1.025 ) |
85640 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV32IM_ZVE64X | 0 | Loop+SLP |
Original data
Click here to download the raw files for this benchmark.