HWBench

AMD Versal AI Edge Series Gen 2 VEK385 vs Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)

FPGA / Versal coverage note: 1,243 rows come from the AMD Vitis AI 3.0/3.5 Model Zoo tables; 733 (59%) are image classification. Detection, segmentation and other workloads are thinner, and there is no LLM or speech data for these boards. All are vendor-published (grade D). FPGA / Versal overview.

AMD Versal AI Edge Series Gen 2 VEK385 is faster in all 2 like-for-like comparisons (largest gap: object detection, 15.53×).

AMD Versal AI Edge Series Gen 2 VEK385Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)
Best object detection93.50 FPS D
2026-09-24 (published)
66.21 FPS D
2026-09-11 (page last edited)
Powern/an/a
Perf / Wn/an/a
Price$15995 listn/a
Workloads with data2 of 75 of 7

Best published object detection result per platform (may be from different like-for-like groups — see data). n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

✓ Like-for-like: model-size class medium (YOLO-m), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
AMD Versal AI Edge Series Gen 2 VEK38593.50 FPS
throughput · b=1
yolov8m
VINT8 with BF16 tail (Quark) · Vitis AI 6.3 VART ml_vart --benchmark --runs 100 · medium (YOLO-m)
Dunknown power n/a
no power published
AMD Vitis AI 6.3 VEK385 YOLOv8m tutorial
2026-09-24 (published)
Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)6.02 FPS
inference_time · b=1
yolov5m.relu
INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · medium (YOLO-m)
Dunknown power n/a
no power published
Microchip VectorBlox SDK tutorial metrics
2026-09-11 (page last edited)

instance segmentation

Only Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)14.13 FPS
inference_time · b=1
yolov8n-seg
INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · nano (YOLO-n)
Dunknown power n/a
no power published
Microchip VectorBlox SDK tutorial metrics
2026-09-11 (page last edited)

AMD Versal AI Edge Series Gen 2 VEK385:

◌

No published instance segmentation results for AMD Versal AI Edge Series Gen 2 VEK385 or Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

Only Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) has published pose estimation results.

PlatformResultModel · precision · stackGradePowerSource
Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)64.49 FPS
inference_time · b=1
yolov8n_pose_50s_25p_512x288_split
INT8 (VNNX) · VectorBlox SDK (VNNX), unstructured compression · nano (YOLO-n)
Dunknown power n/a
no power published
Microchip VectorBlox SDK tutorial metrics
2026-09-11 (page last edited)

AMD Versal AI Edge Series Gen 2 VEK385:

◌

No published pose estimation results for AMD Versal AI Edge Series Gen 2 VEK385 or Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

✓ Like-for-like: model-size class mid-size CNN, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
AMD Versal AI Edge Series Gen 2 VEK385265 FPS
throughput · b=1
resnet50-v1-12 (ONNX)
INT8 (Quark) · Vitis AI 6.3 ONNX Runtime Vitis AI EP (evaluate.py, Python loop) · mid-size CNN
Dunknown power n/a
no power published
AMD Vitis AI 6.3 VEK385 ResNet50 Quark tutorial
2026-09-23 (page last edited)
Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)68.35 FPS
inference_time · b=1
resnet18_86s_07p
INT8 (VNNX) · VectorBlox SDK (VNNX), unstructured compression · mid-size CNN
Dunknown power n/a
no power published
Microchip VectorBlox SDK tutorial metrics
2026-09-11 (page last edited)

semantic segmentation

Only Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) has published semantic segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox)3.88 FPS
inference_time · b=1
deeplabv3
INT8 (VNNX) · VectorBlox SDK (VNNX), no compression · mid-size CNN
Dunknown power n/a
no power published
Microchip VectorBlox SDK tutorial metrics
2026-09-11 (page last edited)

AMD Versal AI Edge Series Gen 2 VEK385:

◌

No published semantic segmentation results for AMD Versal AI Edge Series Gen 2 VEK385 or Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

speech-to-text

◌

No published speech-to-text results for AMD Versal AI Edge Series Gen 2 VEK385 or Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

◌

No published LLM generation results for AMD Versal AI Edge Series Gen 2 VEK385 or Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.

Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.