RADEON HD5970とP6T7 WS Super computer
で、CPU->GPUは4Gb/secだがGPU->CPUは800MB/secが限界。
GPU->CPUが遅すぎる。一体何故だろう?
$./PCIeSpeedTest
Devices found: 2
===> Testing device 0 <===
Device type: Unknown
Max resource 2D width/height: 16384/16384
Total GPU memory size: 2048 MB
Total CPU cached space size: 508 MB
Total CPU uncached space size: 1788 MB
GPU engine clock: 0 MHz
GPU memory clock: 0 MHz
Number of timing loops: 100
[ 16 bytes] CPU->GPU= 320.000 KB/sec, GPU->CPU= 200.000 KB/sec
[ 32 bytes] CPU->GPU= 1.067 MB/sec, GPU->CPU= 800.000 KB/sec
[ 64 bytes] CPU->GPU= 1.600 MB/sec, GPU->CPU= 2.133 MB/sec
[ 128 bytes] CPU->GPU= 1.600 MB/sec, GPU->CPU= 3.200 MB/sec
[ 256 bytes] CPU->GPU= 6.400 MB/sec, GPU->CPU= 8.533 MB/sec
[ 512 bytes] CPU->GPU= 12.800 MB/sec, GPU->CPU= 17.067 MB/sec
[ 1024 bytes] CPU->GPU= 34.133 MB/sec, GPU->CPU= 25.600 MB/sec
[ 2048 bytes] CPU->GPU= 51.200 MB/sec, GPU->CPU= 68.267 MB/sec
[ 4096 bytes] CPU->GPU= 102.400 MB/sec, GPU->CPU= 136.533 MB/sec
[ 8192 bytes] CPU->GPU= 273.067 MB/sec, GPU->CPU= 204.800 MB/sec
[ 16384 bytes] CPU->GPU= 546.133 MB/sec, GPU->CPU= 409.600 MB/sec
[ 32768 bytes] CPU->GPU= 1.092 GB/sec, GPU->CPU= 819.200 MB/sec
[ 65536 bytes] CPU->GPU= 2.185 GB/sec, GPU->CPU= 819.200 MB/sec
[ 131072 bytes] CPU->GPU= 2.621 GB/sec, GPU->CPU= 569.878 MB/sec
[ 262144 bytes] CPU->GPU= 3.277 GB/sec, GPU->CPU= 514.008 MB/sec
[ 524288 bytes] CPU->GPU= 4.033 GB/sec, GPU->CPU= 529.584 MB/sec
[ 1048576 bytes] CPU->GPU= 4.033 GB/sec, GPU->CPU= 551.882 MB/sec
[ 2097152 bytes] CPU->GPU= 4.194 GB/sec, GPU->CPU= 509.017 MB/sec
[ 4194304 bytes] CPU->GPU= 4.194 GB/sec, GPU->CPU= 502.914 MB/sec
[ 8388608 bytes] CPU->GPU= 4.173 GB/sec, GPU->CPU= 485.733 MB/sec
[ 16777216 bytes] CPU->GPU= 4.215 GB/sec, GPU->CPU= 460.407 MB/sec
[ 33554432 bytes] CPU->GPU= 4.092 GB/sec, GPU->CPU= 447.512 MB/sec
[ 67108864 bytes] CPU->GPU= 4.048 GB/sec, GPU->CPU= 442.029 MB/sec
[ 134217728 bytes] CPU->GPU= 4.086 GB/sec, GPU->CPU= 446.114 MB/sec
[ 268435456 bytes] CPU->GPU= 4.071 GB/sec, GPU->CPU= 463.467 MB/sec
[ 536870912 bytes] CPU->GPU= 4.214 GB/sec, GPU->CPU= 486.063 MB/sec
で、CPU->GPUは4Gb/secだがGPU->CPUは800MB/secが限界。
GPU->CPUが遅すぎる。一体何故だろう?
$./PCIeSpeedTest
Devices found: 2
===> Testing device 0 <===
Device type: Unknown
Max resource 2D width/height: 16384/16384
Total GPU memory size: 2048 MB
Total CPU cached space size: 508 MB
Total CPU uncached space size: 1788 MB
GPU engine clock: 0 MHz
GPU memory clock: 0 MHz
Number of timing loops: 100
[ 16 bytes] CPU->GPU= 320.000 KB/sec, GPU->CPU= 200.000 KB/sec
[ 32 bytes] CPU->GPU= 1.067 MB/sec, GPU->CPU= 800.000 KB/sec
[ 64 bytes] CPU->GPU= 1.600 MB/sec, GPU->CPU= 2.133 MB/sec
[ 128 bytes] CPU->GPU= 1.600 MB/sec, GPU->CPU= 3.200 MB/sec
[ 256 bytes] CPU->GPU= 6.400 MB/sec, GPU->CPU= 8.533 MB/sec
[ 512 bytes] CPU->GPU= 12.800 MB/sec, GPU->CPU= 17.067 MB/sec
[ 1024 bytes] CPU->GPU= 34.133 MB/sec, GPU->CPU= 25.600 MB/sec
[ 2048 bytes] CPU->GPU= 51.200 MB/sec, GPU->CPU= 68.267 MB/sec
[ 4096 bytes] CPU->GPU= 102.400 MB/sec, GPU->CPU= 136.533 MB/sec
[ 8192 bytes] CPU->GPU= 273.067 MB/sec, GPU->CPU= 204.800 MB/sec
[ 16384 bytes] CPU->GPU= 546.133 MB/sec, GPU->CPU= 409.600 MB/sec
[ 32768 bytes] CPU->GPU= 1.092 GB/sec, GPU->CPU= 819.200 MB/sec
[ 65536 bytes] CPU->GPU= 2.185 GB/sec, GPU->CPU= 819.200 MB/sec
[ 131072 bytes] CPU->GPU= 2.621 GB/sec, GPU->CPU= 569.878 MB/sec
[ 262144 bytes] CPU->GPU= 3.277 GB/sec, GPU->CPU= 514.008 MB/sec
[ 524288 bytes] CPU->GPU= 4.033 GB/sec, GPU->CPU= 529.584 MB/sec
[ 1048576 bytes] CPU->GPU= 4.033 GB/sec, GPU->CPU= 551.882 MB/sec
[ 2097152 bytes] CPU->GPU= 4.194 GB/sec, GPU->CPU= 509.017 MB/sec
[ 4194304 bytes] CPU->GPU= 4.194 GB/sec, GPU->CPU= 502.914 MB/sec
[ 8388608 bytes] CPU->GPU= 4.173 GB/sec, GPU->CPU= 485.733 MB/sec
[ 16777216 bytes] CPU->GPU= 4.215 GB/sec, GPU->CPU= 460.407 MB/sec
[ 33554432 bytes] CPU->GPU= 4.092 GB/sec, GPU->CPU= 447.512 MB/sec
[ 67108864 bytes] CPU->GPU= 4.048 GB/sec, GPU->CPU= 442.029 MB/sec
[ 134217728 bytes] CPU->GPU= 4.086 GB/sec, GPU->CPU= 446.114 MB/sec
[ 268435456 bytes] CPU->GPU= 4.071 GB/sec, GPU->CPU= 463.467 MB/sec
[ 536870912 bytes] CPU->GPU= 4.214 GB/sec, GPU->CPU= 486.063 MB/sec