opencl-set0-yoda-prehw Test after swapping in the new HW, after Manjaro installed, with rocm AMD version of opencl. 20230927-trial: Processor: Intel Core i7-7700 @ 4.20GHz (4 Cores / 8 Threads), Motherboard: ASUS PRIME H270M-PLUS (0809 BIOS), Chipset: Intel Xeon E3-1200 v6/7th + H270, Memory: 32GB, Disk: Samsung SSD 960 EVO 250GB + 1000GB Samsung SSD 970 EVO Plus 1TB + 3001GB Western Digital WD30EFRX-68E, Graphics: Sapphire AMD Radeon RX 6700 XT 12GB (2725/1000MHz), Audio: Realtek ALC887-VD, Monitor: PB248, Network: Intel I219-V + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-84-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 23.2.0-devel (LLVM 16.0.6 DRM 3.54), OpenCL: OpenCL 2.1 AMD-APP (3590.0), Vulkan: 1.3.252, Compiler: GCC 11.4.0 + LLVM 14.0.0, File-System: ext4 (ecryptfs), Screen Resolution: 1920x1200 20230928_preswitch: Processor: Intel Core i7-7700 @ 4.20GHz (4 Cores / 8 Threads), Motherboard: ASUS PRIME H270M-PLUS (0809 BIOS), Chipset: Intel Xeon E3-1200 v6/7th + H270, Memory: 32GB, Disk: Samsung SSD 960 EVO 250GB + 1000GB Samsung SSD 970 EVO Plus 1TB + 3001GB Western Digital WD30EFRX-68E, Graphics: Sapphire AMD Radeon RX 6700 XT 12GB (2725/1000MHz), Audio: Realtek ALC887-VD, Monitor: PB248, Network: Intel I219-V + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-84-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 23.2.0-devel (LLVM 16.0.6 DRM 3.54), OpenCL: OpenCL 2.1 AMD-APP (3590.0), Vulkan: 1.3.252, Compiler: GCC 11.4.0 + LLVM 14.0.0, File-System: ext4 (ecryptfs), Screen Resolution: 1920x1200 20231020_postswitchperf: Processor: AMD Ryzen 9 7950X3D 16-Core @ 4.20GHz (16 Cores / 32 Threads), Motherboard: ASUS TUF GAMING B650M-PLUS WIFI (0823 BIOS), Chipset: AMD Device 14d8, Memory: 62GB, Disk: 1000GB Samsung SSD 970 EVO Plus 1TB + Samsung SSD 970 EVO Plus 500GB + 3001GB Western Digital WD30EFRX-68E, Graphics: Sapphire AMD Radeon RX 6700 XT 12GB (2725/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: PB248, Network: Realtek RTL8125 2.5GbE + Realtek Device b852 OS: Ubuntu 22.04, Kernel: 5.15.0-86-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 23.2.0-devel (LLVM 16.0.6 DRM 3.54), OpenCL: OpenCL 2.1 AMD-APP (3590.0), Vulkan: 1.3.252, Compiler: GCC 11.4.0 + LLVM 14.0.0, File-System: ext4 (ecryptfs), Screen Resolution: 1920x1200 20231107_postswitch_mjrperf_opencl_cmnt: Processor: AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads), Motherboard: ASUS TUF GAMING B650M-PLUS WIFI (0823 BIOS), Chipset: AMD Device 14d8, Memory: 62GB, Disk: 1000GB Samsung SSD 970 EVO Plus 1TB + Samsung SSD 970 EVO Plus 500GB + 3001GB Western Digital WD30EFRX-68E + 4001GB Rugged USB-C + 3001GB Elements 25A2, Graphics: Sapphire AMD Radeon RX 6700 XT 12GB (2200/2400MHz), Audio: AMD Navi 21/23, Monitor: PB248, Network: Realtek RTL8125 2.5GbE + Realtek Device b852 OS: ManjaroLinux 23.1.0, Kernel: 6.5.9-1-MANJARO (x86_64), Desktop: KDE Plasma 5.27.9, Display Server: X Server 1.21.1.9, OpenGL: 4.6 Mesa 23.1.9-manjaro1.1 (LLVM 16.0.6 DRM 3.54), OpenCL: OpenCL 2.1 AMD-APP (3590.0), Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6, File-System: btrfs, Screen Resolution: 1920x1200 20231107_postswitch_mjrperf_opencl_rocm: Processor: AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads), Motherboard: ASUS TUF GAMING B650M-PLUS WIFI (0823 BIOS), Chipset: AMD Device 14d8, Memory: 62GB, Disk: 1000GB Samsung SSD 970 EVO Plus 1TB + Samsung SSD 970 EVO Plus 500GB + 3001GB Western Digital WD30EFRX-68E + 4001GB Rugged USB-C + 3001GB Elements 25A2, Graphics: Sapphire AMD Radeon RX 6700 XT 12GB (2200/2400MHz), Audio: AMD Navi 21/23, Monitor: PB248, Network: Realtek RTL8125 2.5GbE + Realtek Device b852 OS: ManjaroLinux 23.1.0, Kernel: 6.5.9-1-MANJARO (x86_64), Desktop: KDE Plasma 5.27.9, Display Server: X Server 1.21.1.9, OpenGL: 4.6 Mesa 23.1.9-manjaro1.1 (LLVM 16.0.6 DRM 3.54), OpenCL: OpenCL 2.1 AMD-APP.dbg (3570.0), Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6, File-System: btrfs, Screen Resolution: 1920x1200 SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad GB/s > Higher Is Better 20230927-trial .......................... 11.11 |============== 20230928_preswitch ...................... 10.92 |============== 20231020_postswitchperf ................. 13.51 |================= 20231107_postswitch_mjrperf_opencl_rocm . 23.18 |============================== cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better 20230927-trial .......................... 281.3 |============================== 20230928_preswitch ...................... 281.2 |============================== 20231020_postswitchperf ................. 281.5 |============================== 20231107_postswitch_mjrperf_opencl_cmnt . 281.8 |============================== 20231107_postswitch_mjrperf_opencl_rocm . 281.3 |============================== FluidX3D 2.3 Test: FP32-FP16S MLUPs/s > Higher Is Better 20230927-trial .......................... 2689 |============================== 20230928_preswitch ...................... 2716 |============================== 20231020_postswitchperf ................. 2620 |============================= 20231107_postswitch_mjrperf_opencl_cmnt . 2778 |=============================== 20231107_postswitch_mjrperf_opencl_rocm . 2704 |============================== clpeak 1.1.2 OpenCL Test: Double-Precision Compute GFLOPS > Higher Is Better 20230927-trial .......................... 808.92 |============================= 20230928_preswitch ...................... 808.68 |============================= 20231020_postswitchperf ................. 788.75 |============================ 20231107_postswitch_mjrperf_opencl_cmnt . 801.19 |============================= 20231107_postswitch_mjrperf_opencl_rocm . 795.31 |============================= Parboil 2.5 Test: OpenMP Stencil Seconds < Lower Is Better 20230927-trial .......................... 23.165349 |========================== 20230928_preswitch ...................... 22.160171 |========================= 20231020_postswitchperf ................. 4.738262 |===== Rodinia 3.1 Test: OpenCL Myocyte Seconds < Lower Is Better 20230927-trial .......................... 12.063 |======= 20230928_preswitch ...................... 8.657 |===== 20231020_postswitchperf ................. 47.627 |========================== 20231107_postswitch_mjrperf_opencl_cmnt . 22.363 |============ 20231107_postswitch_mjrperf_opencl_rocm . 52.376 |============================= ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY GB/s > Higher Is Better 20230927-trial .......................... 413 |============================== 20230928_preswitch ...................... 429 |=============================== 20231020_postswitchperf ................. 422 |=============================== 20231107_postswitch_mjrperf_opencl_cmnt . 423 |=============================== 20231107_postswitch_mjrperf_opencl_rocm . 442 |================================ ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY GB/s > Higher Is Better 20230927-trial .......................... 620 |================================ 20230928_preswitch ...................... 598 |=============================== 20231020_postswitchperf ................. 590 |============================== 20231107_postswitch_mjrperf_opencl_cmnt . 575 |============================= 20231107_postswitch_mjrperf_opencl_rocm . 626 |================================ ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT GB/s > Higher Is Better 20230927-trial .......................... 322 |============================ 20230928_preswitch ...................... 305 |========================== 20231020_postswitchperf ................. 335 |============================= 20231107_postswitch_mjrperf_opencl_cmnt . 369 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 361 |=============================== ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY GB/s > Higher Is Better 20230927-trial .......................... 201 |======================== 20230928_preswitch ...................... 194 |======================= 20231020_postswitchperf ................. 270 |================================ 20231107_postswitch_mjrperf_opencl_cmnt . 268 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 270 |================================ ViennaCL 1.7.1 Test: OpenCL BLAS - dDOT GB/s > Higher Is Better 20230927-trial .......................... 187 |================== 20230928_preswitch ...................... 210 |===================== 20231020_postswitchperf ................. 326 |================================ 20231107_postswitch_mjrperf_opencl_cmnt . 316 |=============================== 20231107_postswitch_mjrperf_opencl_rocm . 324 |================================ ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N GB/s > Higher Is Better 20230927-trial .......................... 75.8 |====================== 20230928_preswitch ...................... 76.1 |====================== 20231020_postswitchperf ................. 102.0 |============================== 20231107_postswitch_mjrperf_opencl_cmnt . 102.0 |============================== 20231107_postswitch_mjrperf_opencl_rocm . 102.0 |============================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T GB/s > Higher Is Better 20230927-trial .......................... 173 |=================== 20230928_preswitch ...................... 199 |====================== 20231020_postswitchperf ................. 290 |================================ 20231107_postswitch_mjrperf_opencl_cmnt . 281 |=============================== 20231107_postswitch_mjrperf_opencl_rocm . 286 |================================ ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN GFLOPs/s > Higher Is Better 20230927-trial .......................... 705 |================================ 20230928_preswitch ...................... 712 |================================ 20231020_postswitchperf ................. 700 |=============================== 20231107_postswitch_mjrperf_opencl_cmnt . 705 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 702 |================================ ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT GFLOPs/s > Higher Is Better 20230927-trial .......................... 732 |================================ 20230928_preswitch ...................... 733 |================================ 20231020_postswitchperf ................. 722 |=============================== 20231107_postswitch_mjrperf_opencl_cmnt . 736 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 724 |=============================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN GFLOPs/s > Higher Is Better 20230927-trial .......................... 710 |================================ 20230928_preswitch ...................... 708 |================================ 20231020_postswitchperf ................. 701 |================================ 20231107_postswitch_mjrperf_opencl_cmnt . 703 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 696 |=============================== ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT GFLOPs/s > Higher Is Better 20230927-trial .......................... 729 |================================ 20230928_preswitch ...................... 730 |================================ 20231020_postswitchperf ................. 716 |=============================== 20231107_postswitch_mjrperf_opencl_cmnt . 731 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 719 |=============================== ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY GB/s > Higher Is Better 20230927-trial .......................... 221 |======================= 20230928_preswitch ...................... 223 |======================== 20231020_postswitchperf ................. 302 |================================ 20231107_postswitch_mjrperf_opencl_cmnt . 298 |================================ 20231107_postswitch_mjrperf_opencl_rocm . 301 |================================ Darktable 4.4.2 Test: Masskrug - Acceleration: OpenCL Seconds < Lower Is Better 20230927-trial .......................... 5.216 |============================= 20230928_preswitch ...................... 5.330 |============================== 20231020_postswitchperf ................. 1.382 |======== 20231107_postswitch_mjrperf_opencl_cmnt . 1.363 |======== Darktable 4.4.2 Test: Masskrug - Acceleration: CPU-only Seconds < Lower Is Better 20230927-trial .......................... 7.894 |============================== 20230928_preswitch ...................... 8.008 |============================== 20231020_postswitchperf ................. 1.833 |======= 20231107_postswitch_mjrperf_opencl_cmnt . 1.811 |======= 20231107_postswitch_mjrperf_opencl_rocm . 1.874 |======= Xsbench OpenCL 2017-07-06 Lookups/s > Higher Is Better JuliaGPU 1.2pts1 OpenCL Device: CPU Samples/sec > Higher Is Better JuliaGPU 1.2pts1 OpenCL Device: GPU Samples/sec > Higher Is Better 20230927-trial .......................... 137240757.5 |====== 20230928_preswitch ...................... 142637305.6 |====== 20231020_postswitchperf ................. 428957016.6 |================== 20231107_postswitch_mjrperf_opencl_cmnt . 574416637.8 |======================== 20231107_postswitch_mjrperf_opencl_rocm . 570297541.0 |======================== JuliaGPU 1.2pts1 OpenCL Device: CPU+GPU Samples/sec > Higher Is Better 20230927-trial .......................... 135315754.4 |====== 20230928_preswitch ...................... 139394174.9 |====== 20231020_postswitchperf ................. 411077431.4 |================= 20231107_postswitch_mjrperf_opencl_cmnt . 573384003.0 |======================== 20231107_postswitch_mjrperf_opencl_rocm . 568108729.7 |======================== MandelbulbGPU 1.0pts1 OpenCL Device: CPU+GPU Samples/sec > Higher Is Better 20230927-trial .......................... 79519746.9 |====== 20230928_preswitch ...................... 79087731.3 |====== 20231020_postswitchperf ................. 222793824.3 |================ 20231107_postswitch_mjrperf_opencl_cmnt . 328322358.4 |======================== 20231107_postswitch_mjrperf_opencl_rocm . 329089248.8 |======================== MandelGPU 1.3pts1 OpenCL Device: CPU+GPU Samples/sec > Higher Is Better 20230927-trial .......................... 266133232.1 |=================== 20230928_preswitch ...................... 268569163.2 |==================== 20231020_postswitchperf ................. 330203056.3 |======================== 20231107_postswitch_mjrperf_opencl_cmnt . 316262936.2 |======================= 20231107_postswitch_mjrperf_opencl_rocm . 315714433.5 |======================= SmallPT GPU 1.6pts1 OpenCL Device: CPU - Scene: Caustic3 Samples/sec > Higher Is Better SmallPT GPU 1.6pts1 OpenCL Device: GPU - Scene: Caustic3 Samples/sec > Higher Is Better 20230927-trial .......................... 1695834535 |========================= 20230928_preswitch ...................... 1695878016 |========================= 20231020_postswitchperf ................. 1697804201 |========================= 20231107_postswitch_mjrperf_opencl_cmnt . 1699389555 |========================= 20231107_postswitch_mjrperf_opencl_rocm . 1699398930 |========================= LuxMark 3.1 OpenCL Device: CPU - Scene: Microphone Score > Higher Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Microphone Score > Higher Is Better 20230927-trial .......................... 30063 |========================= 20230928_preswitch ...................... 29797 |========================= 20231020_postswitchperf ................. 35982 |============================== 20231107_postswitch_mjrperf_opencl_cmnt . 35717 |============================== 20231107_postswitch_mjrperf_opencl_rocm . 35105 |============================= LuxMark 3.1 OpenCL Device: CPU+GPU - Scene: Microphone Score > Higher Is Better 20230927-trial .......................... 29792 |========================= 20230928_preswitch ...................... 30132 |========================== 20231020_postswitchperf ................. 35363 |============================== 20231107_postswitch_mjrperf_opencl_cmnt . 35355 |============================== 20231107_postswitch_mjrperf_opencl_rocm . 34810 |============================== LuxMark 3.1 OpenCL Device: Hybrid GPU - Scene: Microphone Score > Higher Is Better Lulesh OpenCL 2017-07-06 z/s > Higher Is Better 20230927-trial .......................... 2953.38 |========================= 20230928_preswitch ...................... 2913.89 |======================== 20231020_postswitchperf ................. 3122.51 |========================== 20231107_postswitch_mjrperf_opencl_cmnt . 3350.39 |============================ 20231107_postswitch_mjrperf_opencl_rocm . 3332.66 |============================