Benchmarks 2024 11 26 TVM GCC Os spike_rv64 - 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:
Models
-
MLPerfTiny Benchmark
-
TODO: others!
Frameworks
-
MLonMCU :
develop
-
TVM :
Nightly Pre-Build
Miscellaneous
- Used
-Os
flag for compilation. - Benchmarks generated using MLonMCU deployment tool with minimal efforts.
- Memory metrics are reported in Bytes
Results (Framework: tvm, Backend: tvmaot, Toolchain: gcc, Flags: -Os, Target: spike_rv64 )
aww
)
Audio Wake Words (Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
---|---|---|---|---|---|---|---|---|---|
27930318.0 ( 0.6x ) |
104128 ( 1.261 ) |
61328 ( 2.909 ) |
0 | NCHW | TVM | Fallback | RV64GC | 0 | - |
31271085.0 ( 0.6x ) |
98432 ( 1.192 ) |
61328 ( 2.909 ) |
0 | NHWC | TVM | Fallback | RV64GC | 0 | - |
28646211.0 ( 0.6x ) |
103296 ( 1.251 ) |
61328 ( 2.909 ) |
128 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
28590725.0 ( 0.6x ) |
103198 ( 1.25 ) |
61328 ( 2.909 ) |
256 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
28705182.0 ( 0.6x ) |
103066 ( 1.249 ) |
61328 ( 2.909 ) |
512 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
27946305.0 ( 0.6x ) |
102768 ( 1.245 ) |
61328 ( 2.909 ) |
1024 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
27886711.0 ( 0.6x ) |
102834 ( 1.246 ) |
61328 ( 2.909 ) |
2048 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
27886711.0 ( 0.6x ) |
102834 ( 1.246 ) |
61328 ( 2.909 ) |
4096 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
31270221.0 ( 0.6x ) |
98414 ( 1.192 ) |
61328 ( 2.909 ) |
128 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
31270221.0 ( 0.6x ) |
98414 ( 1.192 ) |
61328 ( 2.909 ) |
256 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
31270221.0 ( 0.6x ) |
98414 ( 1.192 ) |
61328 ( 2.909 ) |
512 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
31270221.0 ( 0.6x ) |
98414 ( 1.192 ) |
61328 ( 2.909 ) |
1024 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
31270221.0 ( 0.6x ) |
98414 ( 1.192 ) |
61328 ( 2.909 ) |
2048 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
31270221.0 ( 0.6x ) |
98414 ( 1.192 ) |
61328 ( 2.909 ) |
4096 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
17462814.0 ( Base ) |
82548 ( Base ) |
21080 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV64GC | 0 | - |
17774988.0 ( 1.0x ) |
82194 ( 0.996 ) |
25544 ( 1.212 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV64GC | 0 | - |
17467940.0 ( 1.0x ) |
83016 ( 1.006 ) |
21080 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
17467903.0 ( 1.0x ) |
82998 ( 1.005 ) |
21080 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
17467903.0 ( 1.0x ) |
82998 ( 1.005 ) |
21080 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
17467903.0 ( 1.0x ) |
82998 ( 1.005 ) |
21080 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
17467903.0 ( 1.0x ) |
82998 ( 1.005 ) |
21080 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
17467903.0 ( 1.0x ) |
82998 ( 1.005 ) |
21080 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
8570247.0 ( 2.0x ) |
85584 ( 1.037 ) |
25544 ( 1.212 ) |
128 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
6549137.0 ( 2.7x ) |
85584 ( 1.037 ) |
25544 ( 1.212 ) |
256 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
5543363.0 ( 3.2x ) |
85584 ( 1.037 ) |
25544 ( 1.212 ) |
512 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
5502772.0 ( 3.2x ) |
85584 ( 1.037 ) |
25544 ( 1.212 ) |
1024 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
5502772.0 ( 3.2x ) |
85584 ( 1.037 ) |
25544 ( 1.212 ) |
2048 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
5504637.0 ( 3.2x ) |
85584 ( 1.037 ) |
25544 ( 1.212 ) |
4096 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
17774987.0 ( 1.0x ) |
82662 ( 1.001 ) |
25544 ( 1.212 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
17774950.0 ( 1.0x ) |
82644 ( 1.001 ) |
25544 ( 1.212 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
17774950.0 ( 1.0x ) |
82644 ( 1.001 ) |
25544 ( 1.212 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
17774950.0 ( 1.0x ) |
82644 ( 1.001 ) |
25544 ( 1.212 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
17774950.0 ( 1.0x ) |
82644 ( 1.001 ) |
25544 ( 1.212 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
17774950.0 ( 1.0x ) |
82644 ( 1.001 ) |
25544 ( 1.212 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
resnet
)
Image Classification (Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
---|---|---|---|---|---|---|---|---|---|
131024136.0 ( 0.6x ) |
213690 ( 1.631 ) |
110240 ( 1.921 ) |
0 | NCHW | TVM | Fallback | RV64GC | 0 | - |
128091259.0 ( 0.7x ) |
204424 ( 1.56 ) |
110240 ( 1.921 ) |
0 | NHWC | TVM | Fallback | RV64GC | 0 | - |
125043451.0 ( 0.7x ) |
212206 ( 1.62 ) |
110240 ( 1.921 ) |
128 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
129285584.0 ( 0.6x ) |
212026 ( 1.618 ) |
110240 ( 1.921 ) |
256 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
130400577.0 ( 0.6x ) |
211908 ( 1.617 ) |
110240 ( 1.921 ) |
512 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
130735242.0 ( 0.6x ) |
211944 ( 1.618 ) |
110240 ( 1.921 ) |
1024 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
131022299.0 ( 0.6x ) |
211874 ( 1.617 ) |
110240 ( 1.921 ) |
2048 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
131022299.0 ( 0.6x ) |
211874 ( 1.617 ) |
110240 ( 1.921 ) |
4096 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
128086125.0 ( 0.7x ) |
204398 ( 1.56 ) |
110240 ( 1.921 ) |
128 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
128086125.0 ( 0.7x ) |
204398 ( 1.56 ) |
110240 ( 1.921 ) |
256 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
128086125.0 ( 0.7x ) |
204396 ( 1.56 ) |
110240 ( 1.921 ) |
512 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
128086125.0 ( 0.7x ) |
204396 ( 1.56 ) |
110240 ( 1.921 ) |
1024 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
128086125.0 ( 0.7x ) |
204396 ( 1.56 ) |
110240 ( 1.921 ) |
2048 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
128086125.0 ( 0.7x ) |
204396 ( 1.56 ) |
110240 ( 1.921 ) |
4096 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
83904733.0 ( Base ) |
131026 ( Base ) |
57384 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV64GC | 0 | - |
78073797.0 ( 1.1x ) |
130716 ( 0.998 ) |
57384 ( 1.0 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV64GC | 0 | - |
83904728.0 ( 1.0x ) |
132006 ( 1.007 ) |
57384 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
83904693.0 ( 1.0x ) |
131946 ( 1.007 ) |
57384 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
83904693.0 ( 1.0x ) |
131946 ( 1.007 ) |
57384 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
83904693.0 ( 1.0x ) |
131946 ( 1.007 ) |
57384 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
83904693.0 ( 1.0x ) |
131946 ( 1.007 ) |
57384 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
83904693.0 ( 1.0x ) |
131946 ( 1.007 ) |
57384 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
28307373.0 ( 3.0x ) |
134696 ( 1.028 ) |
57384 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
17527089.0 ( 4.8x ) |
134696 ( 1.028 ) |
57384 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
12612083.0 ( 6.7x ) |
134696 ( 1.028 ) |
57384 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
10215980.0 ( 8.2x ) |
134696 ( 1.028 ) |
57384 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
8423076.0 ( 10.0x ) |
134696 ( 1.028 ) |
57384 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
7944233.0 ( 10.6x ) |
134696 ( 1.028 ) |
57384 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
78068663.0 ( 1.1x ) |
131696 ( 1.005 ) |
57384 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
78068628.0 ( 1.1x ) |
131636 ( 1.005 ) |
57384 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
78068628.0 ( 1.1x ) |
131636 ( 1.005 ) |
57384 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
78068628.0 ( 1.1x ) |
131636 ( 1.005 ) |
57384 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
78068628.0 ( 1.1x ) |
131636 ( 1.005 ) |
57384 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
78068628.0 ( 1.1x ) |
131636 ( 1.005 ) |
57384 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
toycar
)
Anomaly Detection (Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
---|---|---|---|---|---|---|---|---|---|
3131668.0 ( 0.6x ) |
576732 ( 1.851 ) |
7416 ( 1.121 ) |
0 | NCHW | TVM | Fallback | RV64GC | 0 | - |
3131668.0 ( 0.6x ) |
576732 ( 1.851 ) |
7416 ( 1.121 ) |
0 | NHWC | TVM | Fallback | RV64GC | 0 | - |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
128 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
256 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
512 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
1024 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
2048 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
4096 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
128 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
256 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
512 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
1024 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
2048 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
3131668.0 ( 0.6x ) |
576736 ( 1.851 ) |
7416 ( 1.121 ) |
4096 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
1986374.0 ( Base ) |
311530 ( Base ) |
6616 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV64GC | 0 | - |
1986374.0 ( 1.0x ) |
311530 ( 1.0 ) |
6616 ( 1.0 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV64GC | 0 | - |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
1986401.0 ( 1.0x ) |
312130 ( 1.002 ) |
6616 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
1986401.0 ( 1.0x ) |
312130 ( 1.002 ) |
6616 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
896500.0 ( 2.2x ) |
313410 ( 1.006 ) |
6616 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
662172.0 ( 3.0x ) |
313410 ( 1.006 ) |
6616 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
545008.0 ( 3.6x ) |
313410 ( 1.006 ) |
6616 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
486966.0 ( 4.1x ) |
313410 ( 1.006 ) |
6616 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
481546.0 ( 4.1x ) |
313410 ( 1.006 ) |
6616 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
477836.0 ( 4.2x ) |
313410 ( 1.006 ) |
6616 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
1986401.0 ( 1.0x ) |
312130 ( 1.002 ) |
6616 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
1986403.0 ( 1.0x ) |
312136 ( 1.002 ) |
6616 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
vww
)
Visual Wake Words (Cycles (Speedup) | Total ROM (rel.) | Total RAM (rel.) | VLEN | Layout | Kernels | Mode | Arch | Unroll | Auto-Vectorization |
---|---|---|---|---|---|---|---|---|---|
81850639.0 ( 0.6x ) |
536608 ( 1.702 ) |
182840 ( 2.089 ) |
0 | NCHW | TVM | Fallback | RV64GC | 0 | - |
89234826.0 ( 0.6x ) |
516864 ( 1.64 ) |
182840 ( 2.089 ) |
0 | NHWC | TVM | Fallback | RV64GC | 0 | - |
83586596.0 ( 0.6x ) |
533272 ( 1.692 ) |
182840 ( 2.089 ) |
128 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
83526869.0 ( 0.6x ) |
532518 ( 1.69 ) |
182840 ( 2.089 ) |
256 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
84025692.0 ( 0.6x ) |
532498 ( 1.689 ) |
182840 ( 2.089 ) |
512 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
81853649.0 ( 0.6x ) |
531858 ( 1.687 ) |
182840 ( 2.089 ) |
1024 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
81776425.0 ( 0.6x ) |
531966 ( 1.688 ) |
182840 ( 2.089 ) |
2048 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
81776425.0 ( 0.6x ) |
531966 ( 1.688 ) |
182840 ( 2.089 ) |
4096 | NCHW | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
89217602.0 ( 0.6x ) |
516758 ( 1.64 ) |
182840 ( 2.089 ) |
128 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
89217602.0 ( 0.6x ) |
516758 ( 1.64 ) |
182840 ( 2.089 ) |
256 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
89217602.0 ( 0.6x ) |
516758 ( 1.64 ) |
182840 ( 2.089 ) |
512 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
89217602.0 ( 0.6x ) |
516758 ( 1.64 ) |
182840 ( 2.089 ) |
1024 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
89217602.0 ( 0.6x ) |
516758 ( 1.64 ) |
182840 ( 2.089 ) |
2048 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
89217602.0 ( 0.6x ) |
516758 ( 1.64 ) |
182840 ( 2.089 ) |
4096 | NHWC | TVM | Fallback | RV64GCV | 0 | Loop+SLP |
51370243.0 ( Base ) |
315192 ( Base ) |
87520 ( Base ) |
0 | NHWC | muRISCV-NN | Scalar | RV64GC | 0 | - |
53077205.0 ( 1.0x ) |
315100 ( 1.0 ) |
87520 ( 1.0 ) |
0 | NHWC | muRISCV-NN | Vector (Portable) | RV64GC | 0 | - |
51380480.0 ( 1.0x ) |
316932 ( 1.006 ) |
87520 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
51370107.0 ( 1.0x ) |
316652 ( 1.005 ) |
87520 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
51370107.0 ( 1.0x ) |
316652 ( 1.005 ) |
87520 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
51370107.0 ( 1.0x ) |
316652 ( 1.005 ) |
87520 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
51370107.0 ( 1.0x ) |
316652 ( 1.005 ) |
87520 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
51370107.0 ( 1.0x ) |
316652 ( 1.005 ) |
87520 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Scalar | RV64GCV | 0 | Loop+SLP |
22994010.0 ( 2.2x ) |
318490 ( 1.01 ) |
87520 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
17041350.0 ( 3.0x ) |
318490 ( 1.01 ) |
87520 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
14757444.0 ( 3.5x ) |
318490 ( 1.01 ) |
87520 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
13852870.0 ( 3.7x ) |
318490 ( 1.01 ) |
87520 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
13775790.0 ( 3.7x ) |
318490 ( 1.01 ) |
87520 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
13777655.0 ( 3.7x ) |
318490 ( 1.01 ) |
87520 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector | RV64GCV | 0 | - |
53087442.0 ( 1.0x ) |
316882 ( 1.005 ) |
87520 ( 1.0 ) |
128 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
53077069.0 ( 1.0x ) |
316592 ( 1.004 ) |
87520 ( 1.0 ) |
256 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
53077069.0 ( 1.0x ) |
316592 ( 1.004 ) |
87520 ( 1.0 ) |
512 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
53077069.0 ( 1.0x ) |
316592 ( 1.004 ) |
87520 ( 1.0 ) |
1024 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
53077069.0 ( 1.0x ) |
316592 ( 1.004 ) |
87520 ( 1.0 ) |
2048 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
53077069.0 ( 1.0x ) |
316592 ( 1.004 ) |
87520 ( 1.0 ) |
4096 | NHWC | muRISCV-NN | Vector (Portable) | RV64GCV | 0 | Loop+SLP |
Original data
Click here to download the raw files for this benchmark.