Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
CNN Inference Acceleration on VGG 16-layer (inference)
Loading...
72.5
Conv Latency (ms)
Ma et al.
65.42
113.21
161
208.79
Feb 3, 2026
Conv Latency (ms)
LUT Utilization (%)
FF Utilization (%)
BRAM Utilization (%)
DSP Utilization (%)
Power Consumption (W)
Updated 4d ago
Evaluation Results
Method
Method
Links
Conv Latency (ms)
LUT Utilization (%)
FF Utilization (%)
BRAM Utilization (%)
DSP Utilization (%)
Power Consumption (W)
Ma et al.
FPGA=STRATIX V, FREQ (...
2026.02
72.5
-
-
-
256,100
-
HLS parameterizable convolution FPGA accelerator template
FPGA=XCZU3EG, FREQ (MH...
2026.02
126.52
4,843,469
4,492,632
19,590
26,674
4.26
Angel-Eye
FPGA=XC7Z045, FREQ (MH...
2026.02
163.42
18,261,684
12,765,329
48,689
78,087
9.63
fpgaConvNet
FPGA=XC7Z045, FREQ (MH...
2026.02
249.5
218,600,100
-
545,100
900,100
-
Feedback
Search any
task
Search any
task