new t AMD Ryzen 7 7840U testing with a PHX Ray_PEU (V1.04 BIOS) and GFX1103 512MB on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 7 7840U @ 3.30GHz (8 Cores / 16 Threads), Motherboard: PHX Ray_PEU (V1.04 BIOS), Chipset: AMD Device 14e8, Memory: 16GB, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: GFX1103 512MB (2700/800MHz), Audio: AMD Device 1640, Network: MEDIATEK Device 0616 OS: Ubuntu 22.04, Kernel: 6.4.0-060400-generic (x86_64), Desktop: KDE Plasma 5.24.7, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 22.2.5-0ubuntu0.1~22.04.3 (LLVM 15.0.7 DRM 3.52), Vulkan: 1.3.224, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3200x2000 b: Processor: AMD Ryzen 7 7840U @ 3.30GHz (8 Cores / 16 Threads), Motherboard: PHX Ray_PEU (V1.04 BIOS), Chipset: AMD Device 14e8, Memory: 16GB, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: GFX1103 512MB (2700/800MHz), Audio: AMD Device 1640, Network: MEDIATEK Device 0616 OS: Ubuntu 22.04, Kernel: 6.4.0-060400-generic (x86_64), Desktop: KDE Plasma 5.24.7, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 22.2.5-0ubuntu0.1~22.04.3 (LLVM 15.0.7 DRM 3.52), Vulkan: 1.3.224, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3200x2000 vkpeak 20230730 fp32-scalar GFLOPS > Higher Is Better a . 191.61 |=================================================================== b . 191.92 |=================================================================== vkpeak 20230730 fp32-vec4 GFLOPS > Higher Is Better a . 194.96 |=================================================================== b . 194.40 |=================================================================== vkpeak 20230730 fp16-scalar GFLOPS > Higher Is Better a . 44.53 |==================================================================== b . 44.61 |==================================================================== vkpeak 20230730 fp16-vec4 GFLOPS > Higher Is Better a . 114.59 |=================================================================== b . 114.66 |=================================================================== vkpeak 20230730 fp64-scalar GFLOPS > Higher Is Better a . 161.17 |=================================================================== b . 161.56 |=================================================================== vkpeak 20230730 fp64-vec4 GFLOPS > Higher Is Better a . 96.34 |==================================================================== b . 96.91 |==================================================================== vkpeak 20230730 int32-scalar GIOPS > Higher Is Better a . 269.09 |=================================================================== b . 269.36 |=================================================================== vkpeak 20230730 int32-vec4 GIOPS > Higher Is Better a . 241.85 |================================================================== b . 244.74 |=================================================================== vkpeak 20230730 int16-scalar GIOPS > Higher Is Better a . 267.34 |=================================================================== b . 267.27 |=================================================================== vkpeak 20230730 int16-vec4 GIOPS > Higher Is Better a . 708.28 |=================================================================== b . 709.85 |=================================================================== VkFFT 1.2.31 Test: FFT + iFFT R2C / C2R Benchmark Score > Higher Is Better a . 141 |====================================================================== b . 142 |====================================================================== VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in half precision Benchmark Score > Higher Is Better a . 259 |====================================================================== b . 259 |====================================================================== VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein in single precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in double precision Benchmark Score > Higher Is Better a . 218 |===================================================================== b . 220 |====================================================================== VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision Benchmark Score > Higher Is Better a . 280 |====================================================================== b . 280 |====================================================================== VkFFT 1.2.31 Test: FFT + iFFT C2C multidimensional in single precision Benchmark Score > Higher Is Better a . 166 |===================================================================== b . 168 |====================================================================== VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein benchmark in double precision Benchmark Score > Higher Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling Benchmark Score > Higher Is Better a . 303 |====================================================================== b . 303 |====================================================================== VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better Crypto++ 8.8 Test: Keyed Algorithms MiB/second > Higher Is Better a . 819.76 |=================================================================== b . 815.60 |=================================================================== Crypto++ 8.8 Test: Unkeyed Algorithms MiB/second > Higher Is Better a . 548.99 |=================================================================== b . 550.00 |=================================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast Frames Per Second > Higher Is Better a . 1.154 |==================================================================== b . 1.155 |==================================================================== VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster Frames Per Second > Higher Is Better a . 2.418 |=================================================================== b . 2.441 |==================================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast Frames Per Second > Higher Is Better a . 3.731 |==================================================================== b . 3.737 |==================================================================== VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster Frames Per Second > Higher Is Better a . 8.466 |==================================================================== b . 8.494 |==================================================================== Timed GCC Compilation 13.2 Time To Compile Seconds < Lower Is Better a . 2640.78 |================================================================== b . 2641.58 |================================================================== Apache CouchDB 3.3.2 Bulk Size: 100 - Inserts: 1000 - Rounds: 30 Seconds < Lower Is Better a . 81.50 |==================================================================== b . 81.18 |==================================================================== Apache CouchDB 3.3.2 Bulk Size: 100 - Inserts: 3000 - Rounds: 30 Seconds < Lower Is Better a . 267.24 |=================================================================== b . 266.89 |=================================================================== Apache CouchDB 3.3.2 Bulk Size: 300 - Inserts: 1000 - Rounds: 30 Seconds < Lower Is Better a . 134.34 |================================================================== b . 136.36 |=================================================================== Apache CouchDB 3.3.2 Bulk Size: 300 - Inserts: 3000 - Rounds: 30 Seconds < Lower Is Better a . 444.12 |=================================================================== b . 445.48 |=================================================================== Apache CouchDB 3.3.2 Bulk Size: 500 - Inserts: 1000 - Rounds: 30 Seconds < Lower Is Better a . 238.90 |=================================================================== Apache CouchDB 3.3.2 Bulk Size: 500 - Inserts: 3000 - Rounds: 30 Seconds < Lower Is Better a . 942.50 |=================================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 200 point/sec > Higher Is Better a . 764198.22 |================================================================ b . 754295.46 |=============================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 200 Average Latency > Higher Is Better a . 12.25 |=================================================================== b . 12.37 |==================================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500 point/sec > Higher Is Better a . 1434283.46 |============================================================= b . 1469303.82 |=============================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500 Average Latency > Higher Is Better a . 20.89 |==================================================================== b . 20.15 |================================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200 point/sec > Higher Is Better a . 1148481.56 |=============================================================== b . 1151261.34 |=============================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200 Average Latency > Higher Is Better a . 10.47 |==================================================================== b . 10.47 |==================================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500 point/sec > Higher Is Better a . 1904407.96 |=============================================================== b . 1902392.91 |=============================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500 Average Latency > Higher Is Better a . 19.26 |==================================================================== b . 19.29 |==================================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 200 point/sec > Higher Is Better a . 31156415.06 |============================================================== b . 30973284.30 |============================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 200 Average Latency > Higher Is Better a . 48.74 |=================================================================== b . 49.27 |==================================================================== Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 500 point/sec > Higher Is Better a . 37173315.01 |============================================================== b . 36760107.65 |============================================================= Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 100 - Sensor Count: 500 Average Latency > Higher Is Better a . 118.12 |=================================================================== b . 118.58 |=================================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200 point/sec > Higher Is Better a . 34027351.93 |============================================================ b . 35441446.08 |============================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200 Average Latency > Higher Is Better a . 50.63 |==================================================================== b . 48.20 |================================================================= Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500 point/sec > Higher Is Better a . 30434143.68 |============================================================= b . 30869603.97 |============================================================== Apache IoTDB 1.1.2 Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500 Average Latency > Higher Is Better a . 154.17 |=================================================================== b . 151.94 |================================================================== Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 1379888.16 |========================================================== b . 1491166.66 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3840222.05 |=============================================================== b . 3831976.08 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3688737.76 |=============================================================== b . 3697778.34 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3586089.56 |============================================================== b . 3624676.16 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 1637117.07 |=============================================================== b . 1502494.92 |========================================================== Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 3869729.38 |============================================================== b . 3922671.60 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 3697587.29 |=============================================================== b . 3708754.43 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 3591856.98 |=============================================================== b . 3600224.35 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 1499036.96 |============================================================= b . 1538274.60 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 3937888.94 |============================================================== b . 3970717.74 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 3755227.91 |============================================================== b . 3789965.37 |=============================================================== Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:100 Ops/sec > Higher Is Better a . 3676368.91 |=============================================================== b . 3645464.56 |============================================================== YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 1 - Num Threads Read: 1 Write Ops/sec > Higher Is Better a . 4847.12 |==================================================== b . 6161.63 |================================================================== YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 1 - Num Threads Read: 16 Write Ops/sec > Higher Is Better a . 5085.19 |======================================================== b . 6018.89 |================================================================== YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 1 - Num Threads Read: 32 Write Ops/sec > Higher Is Better a . 5128.71 |================================================================== b . 4674.10 |============================================================ YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 16 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 5042.93 |=================================================== b . 6576.40 |================================================================== YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 32 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 6087.76 |================================================================== b . 4312.29 |=============================================== YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 16 - Num Threads Read: 16 Write Ops/sec > Higher Is Better a . 51050.66 |================================================================= b . 48138.55 |============================================================= YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 16 - Num Threads Read: 32 Write Ops/sec > Higher Is Better a . 32899.69 |============================================= b . 47496.53 |================================================================= YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 32 - Num Threads Read: 16 Write Ops/sec > Higher Is Better a . 42448.33 |================================================================= b . 25837.10 |======================================== YugabyteDB 2.19 Workload: CassandraKeyValue - Num Threads Write: 32 - Num Threads Read: 32 Write Ops/sec > Higher Is Better a . 58589.84 |================================================================= b . 53696.74 |============================================================ YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 1 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 4966.57 |================================================================== b . 4678.43 |============================================================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 1 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 6052.40 |================================================================= b . 6184.37 |================================================================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 1 - Num Threads Read: 16 Write Ops/sec > Higher Is Better a . 26474.34 |============================================================ b . 28523.23 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 1 - Num Threads Read: 32 Write Ops/sec > Higher Is Better a . 38593.13 |================================================================ b . 39107.77 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 16 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 5369.55 |============================================================ b . 5918.62 |================================================================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 32 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 4117.93 |============================================================= b . 4467.15 |================================================================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 1 - Num Threads Read: 16 Write Ops/sec > Higher Is Better a . 48848.26 |================================================================= b . 42497.31 |========================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 1 - Num Threads Read: 32 Write Ops/sec > Higher Is Better a . 38485.27 |=============================================================== b . 39864.58 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 16 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 5195.87 |================================================================== b . 4712.61 |============================================================ YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 32 - Num Threads Read: 1 Read Ops/sec > Higher Is Better a . 4562.18 |====================================================== b . 5622.46 |================================================================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 16 - Num Threads Read: 16 Read Ops/sec > Higher Is Better a . 50925.69 |================================================================= b . 50394.90 |================================================================ YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 16 - Num Threads Read: 32 Read Ops/sec > Higher Is Better a . 32758.11 |============================================= b . 47245.32 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 16 - Num Threads Read: 32 Write Ops/sec > Higher Is Better a . 7436.82 |================================================================== b . 2367.74 |===================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 32 - Num Threads Read: 16 Read Ops/sec > Higher Is Better a . 52428.30 |=================================================== b . 66912.26 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 32 - Num Threads Read: 32 Read Ops/sec > Higher Is Better a . 42619.03 |======================================== b . 68865.02 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 16 - Num Threads Read: 16 Read Ops/sec > Higher Is Better a . 27192.29 |======================= b . 76398.39 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 16 - Num Threads Read: 32 Read Ops/sec > Higher Is Better a . 34204.91 |================================================================ b . 34813.01 |================================================================= YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 32 - Num Threads Read: 16 Read Ops/sec > Higher Is Better a . 42063.16 |================================================================= b . 19662.00 |============================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 25 - Num Threads Write: 32 - Num Threads Read: 32 Read Ops/sec > Higher Is Better a . 24786.46 |==================================================== b . 30787.11 |================================================================= Redis 7.0.12 + memtier_benchmark 2.0 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3170726.69 |=============================================================== b . 2973746.29 |=========================================================== Redis 7.0.12 + memtier_benchmark 2.0 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 3069952.67 |=============================================================== b . 2849758.37 |========================================================== Redis 7.0.12 + memtier_benchmark 2.0 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 3050497.79 |=============================================================== b . 3054116.42 |=============================================================== Redis 7.0.12 + memtier_benchmark 2.0 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5 Ops/sec > Higher Is Better a . 2779173.08 |============================================================= b . 2884149.30 |=============================================================== Redis 7.0.12 + memtier_benchmark 2.0 Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 2880502.94 |=============================================================== b . 2895297.95 |=============================================================== Redis 7.0.12 + memtier_benchmark 2.0 Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10 Ops/sec > Higher Is Better a . 2847988.80 |============================================================= b . 2918894.71 |=============================================================== NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better a . 27.50 |==================================================================== b . 27.43 |==================================================================== NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 8.32 |===================================================================== b . 8.32 |===================================================================== NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 8.03 |===================================================================== b . 8.03 |===================================================================== NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better a . 5.82 |===================================================================== b . 5.70 |==================================================================== NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better a . 8.05 |===================================================================== b . 8.01 |===================================================================== NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better a . 11.35 |==================================================================== b . 11.31 |==================================================================== NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better a . 1.78 |===================================================================== b . 1.78 |===================================================================== NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better a . 21.15 |==================================================================== b . 21.12 |==================================================================== NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better a . 75.37 |==================================================================== b . 75.36 |==================================================================== NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better a . 15.28 |==================================================================== b . 15.29 |==================================================================== NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better a . 11.63 |==================================================================== b . 11.68 |==================================================================== NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better a . 38.24 |=================================================================== b . 38.98 |==================================================================== NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better a . 37.21 |=================================================================== b . 37.55 |==================================================================== NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better a . 16.14 |==================================================================== b . 16.09 |==================================================================== NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better a . 17.66 |==================================================================== b . 17.66 |==================================================================== NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better a . 290.59 |=================================================================== b . 290.71 |=================================================================== NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better a . 4.19 |================================================================ b . 4.51 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better a . 27.61 |==================================================================== b . 27.52 |==================================================================== NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 8.36 |===================================================================== b . 8.34 |===================================================================== NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 8.03 |===================================================================== b . 8.04 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better a . 5.86 |===================================================================== b . 5.83 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better a . 8.02 |===================================================================== b . 8.04 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better a . 11.37 |==================================================================== b . 11.36 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better a . 1.79 |===================================================================== b . 1.79 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better a . 21.15 |==================================================================== b . 21.18 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better a . 75.36 |==================================================================== b . 75.37 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better a . 15.31 |==================================================================== b . 15.30 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better a . 11.69 |==================================================================== b . 11.70 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better a . 38.23 |==================================================================== b . 38.26 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better a . 37.46 |==================================================================== b . 37.23 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better a . 16.06 |==================================================================== b . 16.09 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better a . 17.71 |==================================================================== b . 17.71 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better a . 291.38 |=================================================================== b . 289.97 |=================================================================== NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better a . 4.38 |===================================================================== b . 4.37 |===================================================================== Apache Cassandra 4.1.3 Test: Writes Op/s > Higher Is Better a . 44343 |==================================================================== b . 44610 |==================================================================== BRL-CAD 7.36 VGR Performance Metric VGR Performance Metric > Higher Is Better a . 41630 |==================================================================== b . 41495 |==================================================================== YugabyteDB 2.19 Workload: CassandraBatchKeyValue, Batch 10 - Num Threads Write: 32 - Num Threads Read: 32 Write Ops/sec > Higher Is Better b . 76379.98 |=================================================================