pts-clpeak
AMD Ryzen 5 5600X 6-Core testing with a MSI B550M PRO-VDH WIFI (MS-7C95) v1.0 (2.G0 BIOS) and MSI AMD Radeon RX 6500 XT 15GB on Arch rolling via the Phoronix Test Suite.


RX6500XT + Tesla T4: 

	Processor: AMD Ryzen 5 5600X 6-Core @ 3.70GHz (6 Cores / 12 Threads), Motherboard: MSI B550M PRO-VDH WIFI (MS-7C95) v1.0 (2.G0 BIOS), Chipset: AMD Starship/Matisse, Memory: 48GB, Disk: 2048GB Lexar SSD NM620 2TB + 256GB HFM256GDHTNG-8510B + 500GB Seagate ST3500418AS + 4001GB TOSHIBA DT02ABA4 + 1000GB Seagate ST1000VX000-1ES1 + 2 x 0GB Storage Device, Graphics: MSI AMD Radeon RX 6500 XT 15GB, Audio: AMD Navi 21/23, Monitor: ASUS VA27EHE, Network: Realtek RTL8111/8168/8411

	OS: Arch rolling, Kernel: 6.6.1-zen1-1-zen (x86_64), Desktop: KDE Plasma 5.27.9, Display Server: X Server 1.21.1.9, Display Driver: NVIDIA, OpenGL: 4.6 Mesa 23.2.1-arch1.2 (LLVM 16.0.6 DRM 3.54), OpenCL: OpenCL 2.1 AMD-APP.dbg (3570.0) + OpenCL 3.0 CUDA 12.3.99, Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6 + CUDA 12.3, File-System: xfs, Screen Resolution: 1920x1080


clpeak 1.1.2
OpenCL Test: Transfer Bandwidth enqueueWriteBuffer
GBPS > Higher Is Better
RX6500XT + Tesla T4 . 21.05 |==================================================


clpeak 1.1.2
OpenCL Test: Transfer Bandwidth enqueueReadBuffer
GBPS > Higher Is Better
RX6500XT + Tesla T4 . 4.27 |===================================================


clpeak 1.1.2
OpenCL Test: Single-Precision Compute
GFLOPS > Higher Is Better
RX6500XT + Tesla T4 . 5498.84 |================================================


clpeak 1.1.2
OpenCL Test: Double-Precision Compute
GFLOPS > Higher Is Better
RX6500XT + Tesla T4 . 337.60 |=================================================


clpeak 1.1.2
OpenCL Test: Global Memory Bandwidth
GBPS > Higher Is Better
RX6500XT + Tesla T4 . 126.53 |=================================================


clpeak 1.1.2
OpenCL Test: Integer 24-bit Compute
GIOPS > Higher Is Better
RX6500XT + Tesla T4 . 5407.95 |================================================


clpeak 1.1.2
OpenCL Test: Integer Compute
GIOPS > Higher Is Better
RX6500XT + Tesla T4 . 1112.44 |================================================


clpeak 1.1.2
OpenCL Test: Kernel Latency
us < Lower Is Better
RX6500XT + Tesla T4 . 9.75 |===================================================