sunny Testss for a future article. Intel Core Ultra 7 256V testing with a ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS) and ASUS Intel LNL 7GB on Ubuntu 24.10 via the Phoronix Test Suite. a: Processor: Intel Core Ultra 7 256V @ 4.70GHz (8 Cores), Motherboard: ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS), Chipset: Intel Device a87f, Memory: 8 x 2GB LPDDR5-8533MT/s Samsung, Disk: 1024GB Western Digital WD PC SN560 SDDPNQE-1T00-1102, Graphics: ASUS Intel LNL 7GB, Audio: Intel Lunar Lake-M HD Audio, Network: Intel Device a840 OS: Ubuntu 24.10, Kernel: 6.12.0-rc3-phx-aipt (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.3~git2410200600.4bc2d2~oibaf~o (git-4bc2d22 2024-10-20 oracular-oibaf-pp, OpenCL: OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 b: Processor: Intel Core Ultra 7 256V @ 4.70GHz (8 Cores), Motherboard: ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS), Chipset: Intel Device a87f, Memory: 8 x 2GB LPDDR5-8533MT/s Samsung, Disk: 1024GB Western Digital WD PC SN560 SDDPNQE-1T00-1102, Graphics: ASUS Intel LNL 7GB, Audio: Intel Lunar Lake-M HD Audio, Network: Intel Device a840 OS: Ubuntu 24.10, Kernel: 6.12.0-rc3-phx-aipt (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.3~git2410200600.4bc2d2~oibaf~o (git-4bc2d22 2024-10-20 oracular-oibaf-pp, OpenCL: OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 Blender 4.3 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 2528.85 |================================================================== b . 2538.07 |================================================================== Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 836.92 |=================================================================== b . 841.40 |=================================================================== Blender 4.3 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 640.15 |=================================================================== b . 632.33 |================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 23.32 |================================================================== b . 23.86 |==================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 23.46 |================================================================== b . 24.01 |==================================================================== Primesieve 12.6 Length: 1e13 Seconds < Lower Is Better a . 375.35 |=================================================================== b . 375.68 |=================================================================== Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 340.45 |=================================================================== b . 339.50 |=================================================================== Blender 4.3 Blend File: Junkshop - Compute: CPU-Only Seconds < Lower Is Better a . 325.79 |================================================================= b . 334.36 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 22.02 |=========================================================== b . 25.22 |==================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 25.33 |==================================================================== b . 25.19 |==================================================================== Blender 4.3 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 222.76 |=================================================================== b . 221.76 |=================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 Tokens Per Second > Higher Is Better a . 66.40 |==================================================================== b . 65.53 |=================================================================== vkpeak 20240505 int16-vec4 GIOPS > Higher Is Better a . 3616.14 |================================================================== b . 3625.91 |================================================================== vkpeak 20240505 int16-scalar GIOPS > Higher Is Better a . 3189.67 |================================================================== b . 3190.35 |================================================================== vkpeak 20240505 int32-vec4 GIOPS > Higher Is Better a . 848.97 |=================================================================== b . 849.17 |=================================================================== vkpeak 20240505 int32-scalar GIOPS > Higher Is Better a . 826.97 |=================================================================== b . 827.21 |=================================================================== vkpeak 20240505 fp64-vec4 GFLOPS > Higher Is Better a . 213.37 |=================================================================== b . 213.43 |=================================================================== vkpeak 20240505 fp64-scalar GFLOPS > Higher Is Better a . 218.71 |=================================================================== b . 218.75 |=================================================================== vkpeak 20240505 fp16-vec4 GFLOPS > Higher Is Better a . 6532.13 |================================================================== b . 6532.63 |================================================================== vkpeak 20240505 fp16-scalar GFLOPS > Higher Is Better a . 6201.56 |================================================================== b . 6202.63 |================================================================== vkpeak 20240505 fp32-vec4 GFLOPS > Higher Is Better a . 2928.03 |================================================================== b . 2928.51 |================================================================== vkpeak 20240505 fp32-scalar GFLOPS > Higher Is Better a . 1989.85 |================================================================== b . 1990.33 |================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 25.04 |================================================================== b . 25.84 |==================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 25.77 |==================================================================== b . 25.70 |==================================================================== Renaissance 0.16 Test: ALS Movie Lens ms < Lower Is Better a . 11841.5 |================================================================= b . 11978.1 |================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 Tokens Per Second > Higher Is Better a . 74.15 |=================================================================== b . 74.85 |==================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 8.18 |=============================================================== b . 8.99 |===================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 8.69 |===================================================================== b . 8.66 |===================================================================== Renaissance 0.16 Test: Akka Unbalanced Cobwebbed Tree ms < Lower Is Better a . 4680.4 |============================================================== b . 5048.7 |=================================================================== Renaissance 0.16 Test: Apache Spark PageRank ms < Lower Is Better a . 2499.1 |================================================================== b . 2555.2 |=================================================================== Renaissance 0.16 Test: Savina Reactors.IO ms < Lower Is Better a . 5040.0 |=================================================================== b . 4962.2 |================================================================== Renaissance 0.16 Test: In-Memory Database Shootout ms < Lower Is Better a . 3666.0 |============================================================== b . 3960.0 |=================================================================== Renaissance 0.16 Test: Gaussian Mixture Model ms < Lower Is Better a . 3998.5 |=================================================================== b . 3964.1 |================================================================== OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 2484.80 |================================================================== b . 2479.73 |================================================================== OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 1.61 |===================================================================== b . 1.60 |===================================================================== Renaissance 0.16 Test: Apache Spark Bayes ms < Lower Is Better a . 576.1 |==================================================================== b . 548.5 |================================================================= Renaissance 0.16 Test: Random Forest ms < Lower Is Better a . 530.0 |================================================================== b . 549.0 |==================================================================== Renaissance 0.16 Test: Finagle HTTP Requests ms < Lower Is Better a . 1603.6 |================================================================== b . 1620.8 |=================================================================== Renaissance 0.16 Test: Genetic Algorithm Using Jenetics + Futures ms < Lower Is Better a . 1345.6 |=================================================================== b . 1344.7 |=================================================================== OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 653.94 |=================================================================== b . 656.46 |=================================================================== OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 6.10 |===================================================================== b . 6.06 |===================================================================== Renaissance 0.16 Test: Scala Dotty ms < Lower Is Better a . 504.9 |================================================================ b . 535.0 |==================================================================== OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 227.74 |=================================================================== b . 227.50 |=================================================================== OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 17.53 |==================================================================== b . 17.56 |==================================================================== OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 229.63 |=================================================================== b . 229.90 |=================================================================== OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 17.39 |==================================================================== b . 17.37 |==================================================================== OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 186.74 |=================================================================== b . 187.74 |=================================================================== OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 21.38 |==================================================================== b . 21.25 |==================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better a . 65.18 |=================================================================== b . 65.73 |==================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better a . 91.93 |==================================================================== b . 91.16 |=================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better a . 5.82 |===================================================================== b . 4.02 |================================================ OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better a . 1026.90 |================================================================== b . 988.82 |================================================================ OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU ms < Lower Is Better a . 16.22 |==================================================================== b . 16.30 |==================================================================== OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU FPS > Higher Is Better a . 245.22 |=================================================================== b . 244.20 |=================================================================== OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU ms < Lower Is Better a . 20.99 |==================================================================== b . 21.04 |==================================================================== OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU FPS > Higher Is Better a . 284.72 |=================================================================== b . 283.97 |=================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better a . 31.30 |==================================================================== b . 31.43 |==================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better a . 127.48 |=================================================================== b . 126.97 |=================================================================== OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 18.14 |================================================================== b . 18.73 |==================================================================== OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 219.73 |=================================================================== b . 212.79 |================================================================= OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better a . 64.03 |================================================================= b . 66.75 |==================================================================== OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better a . 62.38 |==================================================================== b . 59.84 |================================================================= OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better a . 76.47 |==================================================================== b . 76.88 |==================================================================== OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better a . 78.37 |==================================================================== b . 77.92 |==================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 33.06 |==================================================================== b . 32.23 |================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 120.7 |================================================================== b . 123.8 |==================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 12.58 |==================================================================== b . 12.62 |==================================================================== OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 316.02 |=================================================================== b . 315.00 |=================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 38.57 |==================================================================== b . 38.78 |==================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 155.06 |=================================================================== b . 154.23 |=================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 0.51 |==================================================================== b . 0.52 |===================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 11199.94 |================================================================= b . 11036.01 |================================================================ OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 10.42 |==================================================================== b . 10.45 |==================================================================== OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 571.40 |=================================================================== b . 570.08 |=================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better a . 9.53 |===================================================================== b . 9.55 |===================================================================== OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better a . 416.85 |=================================================================== b . 416.05 |=================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 1.43 |===================================================================== b . 1.43 |===================================================================== OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 4019.35 |================================================================== b . 4033.01 |================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 Tokens Per Second > Higher Is Better a . 82.40 |================================================================== b . 84.56 |==================================================================== Primesieve 12.6 Length: 1e12 Seconds < Lower Is Better a . 24.63 |==================================================================== b . 24.60 |==================================================================== Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 Tokens Per Second > Higher Is Better a . 36.91 |================================================================= b . 38.36 |==================================================================== Renaissance 0.16 Test: Apache Spark ALS ms < Lower Is Better