CLPEAK SYS vs PTS

\

HTML result view exported from: https://openbenchmarking.org/result/2304011-EIRI-CLPEAKS97&sro&grr.

CLPEAK SYS vs PTSProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionRTX 2070 Max QUHD 630 + RTX 2070 Max-QIntel Core i7-9750H @ 4.50GHz (6 Cores / 12 Threads)Dell 0F7T8V (1.14.0 BIOS)Intel Cannon Lake PCH32GB2000GB Samsung SSD 970 EVO Plus 2TB + 1000GB CT1000MX500SSD1Intel UHD 630 CFL GT2 8GB (300/405MHz)Realtek ALC3204Realtek Device 2502 + Intel-AC 9260EndeavourOS rolling6.2.8-arch1-1 (x86_64)KDE Plasma 5.27.3X Server 1.21.1.8NVIDIA 530.41.034.6 Mesa 23.0.1OpenCL 3.0 CUDA 12.1.98 + OpenCL 3.0GCC 12.2.1 20230201 + Clang 15.0.7 + LLVM 15.0.7 + CUDA 12.1ext41920x1080Intel UHD 630 CFL GT2 8GB (885/6000MHz)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu Processor Details- Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xf0Graphics Details- BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.06.2d.00.bbOpenCL Details- GPU Compute Cores: 2304Security Details- RTX 2070 Max Q: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of IBRS IBPB: conditional STIBP: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Mitigation of Microcode + tsx_async_abort: Not affected - UHD 630 + RTX 2070 Max-Q: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + mmio_stale_data: Vulnerable + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled PBRSB-eIBRS: Not affected + srbds: Vulnerable + tsx_async_abort: Not affected Environment Details- UHD 630 + RTX 2070 Max-Q: NVM_CD_FLAGS=

CLPEAK SYS vs PTSclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueWriteBufferclpeak: Transfer Bandwidth enqueueReadBufferclpeak: Double-Precision Doubleclpeak: Integer Compute INTclpeak: Single-Precision Floatclpeak: Double-Precision Computeclpeak: Kernel Latencyclpeak: Integer 24-bit Computeclpeak: Integer Computeclpeak: Single-Precision Computeclpeak: Global Memory Bandwidthclpeak: Kernel LatencyRTX 2070 Max QUHD 630 + RTX 2070 Max-Q32.076.256.40107.60142.90428.65266.3132.454493.224524.595763.73325.675.9631.616.266.42107.00141.94425.86266.2428.434535.824622.515737.72325.665.95OpenBenchmarking.org

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthRTX 2070 Max QUHD 630 + RTX 2070 Max-Q714212835SE +/- 0.12, N = 3SE +/- 0.10, N = 332.0731.61

clpeak

OpenCL Test: Transfer Bandwidth enqueueWriteBuffer

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueWriteBufferRTX 2070 Max QUHD 630 + RTX 2070 Max-Q246810SE +/- 0.00, N = 3SE +/- 0.00, N = 36.256.261. (CXX) g++ options: -O3

clpeak

OpenCL Test: Transfer Bandwidth enqueueReadBuffer

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueReadBufferRTX 2070 Max QUHD 630 + RTX 2070 Max-Q246810SE +/- 0.01, N = 3SE +/- 0.00, N = 36.406.421. (CXX) g++ options: -O3

clpeak

OpenCL Test: Double-Precision Double

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleRTX 2070 Max QUHD 630 + RTX 2070 Max-Q20406080100SE +/- 0.05, N = 3SE +/- 0.03, N = 3107.60107.00

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2070 Max QUHD 630 + RTX 2070 Max-Q306090120150SE +/- 0.07, N = 3SE +/- 0.05, N = 3142.90141.94

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatRTX 2070 Max QUHD 630 + RTX 2070 Max-Q90180270360450SE +/- 0.10, N = 3SE +/- 0.26, N = 3428.65425.86

clpeak

OpenCL Test: Double-Precision Compute

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision ComputeRTX 2070 Max QUHD 630 + RTX 2070 Max-Q60120180240300SE +/- 1.07, N = 3SE +/- 0.80, N = 3266.31266.241. (CXX) g++ options: -O3

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyRTX 2070 Max QUHD 630 + RTX 2070 Max-Q816243240SE +/- 0.73, N = 15SE +/- 0.34, N = 332.4528.43

clpeak

OpenCL Test: Integer 24-bit Compute

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeRTX 2070 Max QUHD 630 + RTX 2070 Max-Q10002000300040005000SE +/- 88.24, N = 15SE +/- 99.88, N = 154493.224535.821. (CXX) g++ options: -O3

clpeak

OpenCL Test: Integer Compute

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRTX 2070 Max QUHD 630 + RTX 2070 Max-Q10002000300040005000SE +/- 83.18, N = 15SE +/- 93.07, N = 154524.594622.511. (CXX) g++ options: -O3

clpeak

OpenCL Test: Single-Precision Compute

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRTX 2070 Max QUHD 630 + RTX 2070 Max-Q12002400360048006000SE +/- 75.35, N = 3SE +/- 64.58, N = 155763.735737.721. (CXX) g++ options: -O3

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthRTX 2070 Max QUHD 630 + RTX 2070 Max-Q70140210280350SE +/- 0.03, N = 3SE +/- 0.02, N = 3325.67325.661. (CXX) g++ options: -O3

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, Fewer Is Betterclpeak 1.1.2OpenCL Test: Kernel LatencyRTX 2070 Max QUHD 630 + RTX 2070 Max-Q1.3412.6824.0235.3646.705SE +/- 0.01, N = 3SE +/- 0.01, N = 35.965.951. (CXX) g++ options: -O3

Phoronix Test Suite v10.8.5