Ice Lake shows a significant single-thread uplift over Whiskey Lake, which translates into big leads in the multi-threaded portion of the benchmark as well. The 15W Core i7-1065G7 offered much better single-thread performance than
Ryzen as well, but couldn't catch the 3700U in the MT test. The 25W Core i7-1065G7 configuration, however, led the pack by a wide margin.
POV-Ray, or the Persistence of Vision Ray-Tracer, is an open source tool for creating realistically lit images. We tested with POV-Ray's standard 'one-CPU' and 'all-CPU' benchmarking tools on all of our test machines and recorded the scores reported for each. Results are measured in pixels-per-second throughput; higher scores equate to better performance.
The POV-Ray benchmark tells a similar story to Cinebench. Once again, we see Ice Lake dominating the single-threaded test and the 25W Core i7-1065G7 configuration leading the pack.
 |
| Blender |
| 3D Rendering Benchmark |
|
Blender is a free and open source 3D creation suite that can handle everything from modeling, rigging, animation, simulation, rendering, compositing and motion tracking, even video editing and game creation. It has a built-in benchmarking tool that will track the time it takes to complete rendering a particular model. We used a
CPU-focused BMW model for these tests here...
The Blender benchmark places a heavy, sustained workload on the CPU, which clearly exposes the performance benefits of the Core i7-1065G7's 25W TDP configuration. When running flat out, the 25W Core i7-1065G7 outpaces the Ryzen 7 3700U by nearly a minute. The more power constrained 15W Core i7-1065G7 setup, however, trails the Ryzen CPU by a few minutes. It was able to outrun the 8th Generation
Whiskey Lake-based Core i7-8565U though.
|
| AIXPRT |
| AI Inferencing Performance |
|
AIXPRT is an Artificial Intelligence benchmark that supports Intel OpenVINO, TensorFlow, and TensorFlow with NVIDIA TensorRT toolkits to run image-classification and object-detection workloads with the ResNet-50 and SSD-MobileNet v1 networks. AIXPRT reports FP32, FP16, and INT8 levels of precision, but we are showing only the FP32 and Int8 throughput and latency summaries below. Although these numbers are somewhat nebulous on their own, performance levels should be indicative of AI performance as more desktop applications adopt and use the technology.
AIXPRT is able to leverage the Intel DL Boost AI acceleration instructions available in Ice Lake, and as such, both Core i7-1065G7 configurations absolutely crush the
Ryzen 7 3700U and 8th Gen Core i7. Throughput and latency are increased across the board, sometimes to the tune of 2x - 3x over Whiskey Lake.
