new sun AMD EPYC 9655P 96-Core testing with a Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) and ASPEED on Ubuntu 24.10 via the Phoronix Test Suite. a: Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-linux-pm-next-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768 b: Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-linux-pm-next-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768 c: Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 24.10, Kernel: 6.12.0-rc7-linux-pm-next-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768 Renaissance 0.16 Test: In-Memory Database Shootout ms < Lower Is Better a . 10422.6 |================================================================== b . 9314.3 |=========================================================== c . 10030.8 |================================================================ Renaissance 0.16 Test: Apache Spark Bayes ms < Lower Is Better a . 299.2 |============================================================= b . 310.6 |================================================================ c . 332.0 |==================================================================== 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 . 147.28 |=================================================================== b . 141.73 |================================================================ c . 136.97 |============================================================== Renaissance 0.16 Test: Savina Reactors.IO ms < Lower Is Better a . 9997.9 |============================================================== b . 10225.3 |=============================================================== c . 10675.6 |================================================================== 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 . 141.60 |=================================================================== b . 141.33 |=================================================================== c . 133.76 |=============================================================== 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 . 94.55 |==================================================================== b . 92.09 |================================================================== c . 89.99 |================================================================= Renaissance 0.16 Test: Random Forest ms < Lower Is Better a . 672.1 |================================================================= b . 705.0 |==================================================================== c . 687.2 |================================================================== 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 . 286.32 |================================================================= b . 297.04 |=================================================================== c . 290.80 |================================================================== 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 . 92.46 |================================================================== b . 95.50 |==================================================================== c . 94.04 |=================================================================== 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 . 202.95 |================================================================= b . 204.44 |================================================================= c . 209.51 |=================================================================== Renaissance 0.16 Test: Akka Unbalanced Cobwebbed Tree ms < Lower Is Better a . 17556.2 |================================================================== b . 17357.9 |================================================================= c . 17006.5 |================================================================ Renaissance 0.16 Test: Finagle HTTP Requests ms < Lower Is Better a . 2859.7 |================================================================= b . 2947.6 |=================================================================== c . 2933.9 |=================================================================== 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 . 72.00 |================================================================== b . 74.08 |==================================================================== c . 73.87 |==================================================================== 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 . 74.34 |==================================================================== b . 72.56 |================================================================== c . 73.99 |==================================================================== Renaissance 0.16 Test: Genetic Algorithm Using Jenetics + Futures ms < Lower Is Better a . 1417.2 |=================================================================== b . 1403.0 |================================================================== c . 1391.1 |================================================================== 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 . 97.62 |=================================================================== b . 98.93 |==================================================================== c . 97.18 |=================================================================== Renaissance 0.16 Test: Gaussian Mixture Model ms < Lower Is Better a . 5479.3 |=================================================================== b . 5433.1 |================================================================== c . 5503.2 |=================================================================== 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 . 47.72 |=================================================================== b . 47.84 |==================================================================== c . 48.16 |==================================================================== Renaissance 0.16 Test: Apache Spark PageRank ms < Lower Is Better a . 2299.3 |=================================================================== b . 2315.4 |=================================================================== c . 2294.9 |================================================================== Blender 4.3 Blend File: Junkshop - Compute: CPU-Only Seconds < Lower Is Better a . 17.50 |==================================================================== b . 17.36 |=================================================================== c . 17.36 |=================================================================== Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better a . 19.08 |==================================================================== b . 19.14 |==================================================================== c . 19.00 |==================================================================== Primesieve 12.6 Length: 1e12 Seconds < Lower Is Better a . 1.912 |==================================================================== b . 1.924 |==================================================================== c . 1.910 |==================================================================== Blender 4.3 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better a . 13.67 |==================================================================== b . 13.59 |==================================================================== c . 13.68 |==================================================================== 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 . 45.91 |==================================================================== b . 46.07 |==================================================================== c . 45.79 |==================================================================== Blender 4.3 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better a . 35.91 |==================================================================== b . 35.80 |==================================================================== c . 35.73 |==================================================================== Renaissance 0.16 Test: ALS Movie Lens ms < Lower Is Better a . 21012.4 |================================================================== b . 20956.9 |================================================================== c . 21047.6 |================================================================== Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better a . 42.22 |==================================================================== b . 42.12 |==================================================================== c . 42.24 |==================================================================== Blender 4.3 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better a . 125.69 |=================================================================== b . 125.86 |=================================================================== c . 125.72 |=================================================================== Primesieve 12.6 Length: 1e13 Seconds < Lower Is Better a . 23.71 |==================================================================== b . 23.70 |==================================================================== c . 23.69 |==================================================================== 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 . 151.71 |================================================================== b . 149.06 |================================================================= c . 154.18 |=================================================================== Renaissance 0.16 Test: Apache Spark ALS ms < Lower Is Better Renaissance 0.16 Test: Scala Dotty ms < Lower Is Better a . 723.7 |==================================================================== b . 694.0 |================================================================= c . 642.6 |============================================================