wu-arch/kernels
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Created performance results from 2021/03/07

Browse Source
This commit is contained in:
Liam Paul Cooper
2021-03-30 16:44:57 -04:00
parent c89f735185
commit aa3c2bfeaa
55 changed files with 228394 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
evaluation/perf_2021_03_07/2c/afu_default.fit.summary Normal file
View File

@@ -0,0 +1,17 @@
Fitter Status : Successful - Sat Mar 6 01:44:47 2021
Quartus Prime Version : 19.2.0 Build 57 06/24/2019 Patches 0.01rc SJ Pro Edition
Revision Name : afu_default
Top-level Entity Name : dcp_top
Family : Arria 10
Device : 10AX115N2F40E2LG
Timing Models : Final
Logic utilization (in ALMs) : 74,001 / 427,200 ( 17 % )
Total registers : 109164
Total pins : 310 / 826 ( 38 % )
Total virtual pins : 0
Total block memory bits : 2,967,352 / 55,562,240 ( 5 % )
Total RAM Blocks : 451 / 2,713 ( 17 % )
Total DSP Blocks : 56 / 1,518 ( 4 % )
Total HSSI RX channels : 12 / 48 ( 25 % )
Total HSSI TX channels : 12 / 48 ( 25 % )
Total PLLs : 25 / 112 ( 22 % )

6945
evaluation/perf_2021_03_07/2c/afu_default.sta.summary Normal file
View File

File diff suppressed because it is too large Load Diff

4
evaluation/perf_2021_03_07/2c/afu_default.syn.summary Normal file
View File

@@ -0,0 +1,4 @@
Synthesis Status : Successful - Sat Mar 6 01:12:13 2021
Revision Name : afu_default
Top-level Entity Name : dcp_top
Family : Arria 10

34115
evaluation/perf_2021_03_07/2c/build.log Normal file
View File

File diff suppressed because it is too large Load Diff

29
evaluation/perf_2021_03_07/2c/guassian.result Normal file
View File

@@ -0,0 +1,29 @@
CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=2 -DNUM_WARPS=4 -DNUM_THREADS=4 -DL2_ENABLE=0 -DL3_ENABLE=0 -DPERF_ENABLE
make: Entering directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
rm -rf libvortex.so *.o .depend
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
make: Entering directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/guassian'
LD_LIBRARY_PATH=/opt/pocl/runtime/lib:/nethome/lcooper43/vortex-dev-old/driver/opae:/opt/opae/1.1.2/lib:/opt/inteldevstack/a10_gx_pac_ias_1_2_1_pv/opencl/opencl_bsp/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/host/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/linux64/lib: ./guassian
enter demo main
[VXDRV] DEVCAPS: version=0, num_cores=2, num_warps=4, num_threads=4
OK
The result of matrix m is:
0.00 0.00 0.00 0.00
0.50 0.00 0.00 0.00
0.67 0.26 0.00 0.00
-0.00 0.15 -0.28 0.00
The result of matrix a is:
-0.60 -0.50 0.70 0.30
0.00 -0.65 -0.05 0.55
0.00 0.00 -0.75 -1.14
0.00 0.00 0.00 0.50
The result of array b is:
-0.85 -0.25 0.87 -0.25
The final solution is:
0.70 0.00 -0.40 -0.50
Passed!
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/guassian'

19
evaluation/perf_2021_03_07/2c/nearn.result Normal file
View File

@@ -0,0 +1,19 @@
CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=2 -DNUM_WARPS=4 -DNUM_THREADS=4 -DL2_ENABLE=0 -DL3_ENABLE=0 -DPERF_ENABLE
make: Entering directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
rm -rf libvortex.so *.o .depend
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
make: Entering directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/nearn'
LD_LIBRARY_PATH=/opt/pocl/runtime/lib:/nethome/lcooper43/vortex-dev-old/driver/opae:/opt/opae/1.1.2/lib:/opt/inteldevstack/a10_gx_pac_ias_1_2_1_pv/opencl/opencl_bsp/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/host/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/linux64/lib: ./nearn
loading db: cane4_0.db
loading db: cane4_1.db
loading db: cane4_2.db
Number of records: 1500
Finding the 5 closest neighbors.
[VXDRV] DEVCAPS: version=0, num_cores=2, num_warps=4, num_threads=4
1974 12 22 18 24 JOYCE 30.6 89.9 80 593 --> Distance=0.608276
1965 5 13 0 17 TONY 27.8 89.0 122 260 --> Distance=2.416610
1991 3 18 12 19 DEBBY 28.5 87.8 107 850 --> Distance=2.662703
1957 4 17 6 12 ALBERTO 32.5 87.8 54 510 --> Distance=3.330163
1964 8 5 6 9 FLORENCE 31.5 86.3 18 242 --> Distance=3.992490
Passed!
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/nearn'

19
evaluation/perf_2021_03_07/2c/saxpy.result Normal file
View File

@@ -0,0 +1,19 @@
CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=2 -DNUM_WARPS=4 -DNUM_THREADS=4 -DL2_ENABLE=0 -DL3_ENABLE=0 -DPERF_ENABLE
make: Entering directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
rm -rf libvortex.so *.o .depend
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
make: Entering directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/saxpy'
LD_LIBRARY_PATH=/opt/pocl/runtime/lib:/nethome/lcooper43/vortex-dev-old/driver/opae:/opt/opae/1.1.2/lib:/opt/inteldevstack/a10_gx_pac_ias_1_2_1_pv/opencl/opencl_bsp/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/host/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/linux64/lib: ./saxpy
enter demo main
[VXDRV] DEVCAPS: version=0, num_cores=2, num_warps=4, num_threads=4
Attempting to create program from binary...
Read program from binary.
attempting to create input buffer
attempting to create output buffer
attempting to create kernel
setting up kernel args
attempting to enqueue write buffer
attempting to enqueue kernel
Elapsed time: 4 ms
Download destination buffer
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/saxpy'

19
evaluation/perf_2021_03_07/2c/sfilter.result Normal file
View File

@@ -0,0 +1,19 @@
CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=2 -DNUM_WARPS=4 -DNUM_THREADS=4 -DL2_ENABLE=0 -DL3_ENABLE=0 -DPERF_ENABLE
make: Entering directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
rm -rf libvortex.so *.o .depend
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
make: Entering directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/sfilter'
LD_LIBRARY_PATH=/opt/pocl/runtime/lib:/nethome/lcooper43/vortex-dev-old/driver/opae:/opt/opae/1.1.2/lib:/opt/inteldevstack/a10_gx_pac_ias_1_2_1_pv/opencl/opencl_bsp/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/host/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/linux64/lib: ./sfilter
enter demo main
[VXDRV] DEVCAPS: version=0, num_cores=2, num_warps=4, num_threads=4
Attempting to create program from binary...
Read program from binary.
attempting to create input buffer
attempting to create output buffer
attempting to create kernel
setting up kernel args
attempting to enqueue write buffer
attempting to enqueue kernel
Elapsed time: 4 ms
Download destination buffer
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/sfilter'

94
evaluation/perf_2021_03_07/2c/sgemm.result Normal file
View File

@@ -0,0 +1,94 @@
CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=2 -DNUM_WARPS=4 -DNUM_THREADS=4 -DL2_ENABLE=0 -DL3_ENABLE=0 -DPERF_ENABLE
make: Entering directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
rm -rf libvortex.so *.o .depend
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
make: Entering directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/sgemm'
LD_LIBRARY_PATH=/opt/pocl/runtime/lib:/nethome/lcooper43/vortex-dev-old/driver/opae:/opt/opae/1.1.2/lib:/opt/inteldevstack/a10_gx_pac_ias_1_2_1_pv/opencl/opencl_bsp/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/host/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/linux64/lib: ./sgemm -n32
[VXDRV] DEVCAPS: version=0, num_cores=2, num_warps=4, num_threads=4
Create context
Create program from kernel source
Upload source buffers
Execute the kernel
Elapsed time: 4 ms
Download destination buffer
Verify result
PASSED!
PERF: core0: instrs=180750, cycles=84306, IPC=2.143975
PERF: core0: ibuffer stalls=0
PERF: core0: scoreboard stalls=0
PERF: core0: alu unit stalls=0
PERF: core0: lsu unit stalls=0
PERF: core0: csr unit stalls=0
PERF: core0: fpu unit stalls=0
PERF: core0: gpu unit stalls=0
PERF: core0: icache reads=0
PERF: core0: icache read misses=0 (hit ratio=-2147483648%)
PERF: core0: icache pipeline stalls=0
PERF: core0: icache reponse stalls=0
PERF: core0: dcache reads=0
PERF: core0: dcache writes=0
PERF: core0: dcache read misses=0 (hit ratio=-2147483648%)
PERF: core0: dcache write misses=0 (hit ratio=-2147483648%)
PERF: core0: dcache bank stalls=0 (utilization=-2147483648%)
PERF: core0: dcache mshr stalls=0
PERF: core0: dcache pipeline stalls=0
PERF: core0: dcache reponse stalls=0
PERF: core0: smem reads=0
PERF: core0: smem writes=0
PERF: core0: smem bank stalls=0 (utilization=-2147483648%)
PERF: core0: dram requests=0 (reads=0, writes=0)
PERF: core0: dram stalls=0 (utilization=-2147483648%)
PERF: core0: dram average latency=-2147483648 cycles
PERF: core1: instrs=180752, cycles=84131, IPC=2.148459
PERF: core1: ibuffer stalls=0
PERF: core1: scoreboard stalls=0
PERF: core1: alu unit stalls=0
PERF: core1: lsu unit stalls=0
PERF: core1: csr unit stalls=0
PERF: core1: fpu unit stalls=0
PERF: core1: gpu unit stalls=0
PERF: core1: icache reads=0
PERF: core1: icache read misses=0 (hit ratio=-2147483648%)
PERF: core1: icache pipeline stalls=0
PERF: core1: icache reponse stalls=0
PERF: core1: dcache reads=0
PERF: core1: dcache writes=0
PERF: core1: dcache read misses=0 (hit ratio=-2147483648%)
PERF: core1: dcache write misses=0 (hit ratio=-2147483648%)
PERF: core1: dcache bank stalls=0 (utilization=-2147483648%)
PERF: core1: dcache mshr stalls=0
PERF: core1: dcache pipeline stalls=0
PERF: core1: dcache reponse stalls=0
PERF: core1: smem reads=0
PERF: core1: smem writes=0
PERF: core1: smem bank stalls=0 (utilization=-2147483648%)
PERF: core1: dram requests=0 (reads=0, writes=0)
PERF: core1: dram stalls=0 (utilization=-2147483648%)
PERF: core1: dram average latency=-2147483648 cycles
PERF: instrs=361502, cycles=84306, IPC=4.287975
PERF: ibuffer stalls=0
PERF: scoreboard stalls=0
PERF: alu unit stalls=0
PERF: lsu unit stalls=0
PERF: csr unit stalls=0
PERF: fpu unit stalls=0
PERF: gpu unit stalls=0
PERF: icache reads=0
PERF: icache read misses=0 (hit ratio=-2147483648%)
PERF: icache pipeline stalls=0
PERF: icache reponse stalls=0
PERF: dcache reads=0
PERF: dcache writes=0
PERF: dcache read misses=0 (hit ratio=-2147483648%)
PERF: dcache write misses=0 (hit ratio=-2147483648%)
PERF: dcache bank stalls=0 (utilization=-2147483648%)
PERF: dcache mshr stalls=0
PERF: dcache pipeline stalls=0
PERF: dcache reponse stalls=0
PERF: smem reads=0
PERF: smem writes=0
PERF: smem bank stalls=0 (utilization=-2147483648%)
PERF: dram requests=0 (reads=0, writes=0)
PERF: dram stalls=0 (utilization=-2147483648%)
PERF: dram average latency=-2147483648 cycles
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/sgemm'

3
evaluation/perf_2021_03_07/2c/user_clock_freq.txt Normal file
View File

@@ -0,0 +1,3 @@
# Generated by Platform Interface Manager user_clock_config.tcl
afu-image/clock-frequency-low:92.0
afu-image/clock-frequency-high:184

95
evaluation/perf_2021_03_07/2c/vecadd.result Normal file
View File

@@ -0,0 +1,95 @@
CONFIGS=-DNUM_CLUSTERS=1 -DNUM_CORES=2 -DNUM_WARPS=4 -DNUM_THREADS=4 -DL2_ENABLE=0 -DL3_ENABLE=0 -DPERF_ENABLE
make: Entering directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
rm -rf libvortex.so *.o .depend
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/driver/opae'
make: Entering directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/vecadd'
LD_LIBRARY_PATH=/opt/pocl/runtime/lib:/nethome/lcooper43/vortex-dev-old/driver/opae:/opt/opae/1.1.2/lib:/opt/inteldevstack/a10_gx_pac_ias_1_2_1_pv/opencl/opencl_bsp/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/host/linux64/lib:/opt/intelFPGA_pro/quartus_19.2.0b57/hld/linux64/lib: ./vecadd -n64
[VXDRV] DEVCAPS: version=0, num_cores=2, num_warps=4, num_threads=4
Create context
Allocate device buffers
Create program from kernel source
Upload source buffers
Execute the kernel
Elapsed time: 4 ms
Download destination buffer
Verify result
PASSED!
PERF: core0: instrs=2981, cycles=5416, IPC=0.550406
PERF: core0: ibuffer stalls=0
PERF: core0: scoreboard stalls=0
PERF: core0: alu unit stalls=0
PERF: core0: lsu unit stalls=0
PERF: core0: csr unit stalls=0
PERF: core0: fpu unit stalls=0
PERF: core0: gpu unit stalls=0
PERF: core0: icache reads=0
PERF: core0: icache read misses=0 (hit ratio=-2147483648%)
PERF: core0: icache pipeline stalls=0
PERF: core0: icache reponse stalls=0
PERF: core0: dcache reads=0
PERF: core0: dcache writes=0
PERF: core0: dcache read misses=0 (hit ratio=-2147483648%)
PERF: core0: dcache write misses=0 (hit ratio=-2147483648%)
PERF: core0: dcache bank stalls=0 (utilization=-2147483648%)
PERF: core0: dcache mshr stalls=0
PERF: core0: dcache pipeline stalls=0
PERF: core0: dcache reponse stalls=0
PERF: core0: smem reads=0
PERF: core0: smem writes=0
PERF: core0: smem bank stalls=0 (utilization=-2147483648%)
PERF: core0: dram requests=0 (reads=0, writes=0)
PERF: core0: dram stalls=0 (utilization=-2147483648%)
PERF: core0: dram average latency=-2147483648 cycles
PERF: core1: instrs=2983, cycles=5353, IPC=0.557258
PERF: core1: ibuffer stalls=0
PERF: core1: scoreboard stalls=0
PERF: core1: alu unit stalls=0
PERF: core1: lsu unit stalls=0
PERF: core1: csr unit stalls=0
PERF: core1: fpu unit stalls=0
PERF: core1: gpu unit stalls=0
PERF: core1: icache reads=0
PERF: core1: icache read misses=0 (hit ratio=-2147483648%)
PERF: core1: icache pipeline stalls=0
PERF: core1: icache reponse stalls=0
PERF: core1: dcache reads=0
PERF: core1: dcache writes=0
PERF: core1: dcache read misses=0 (hit ratio=-2147483648%)
PERF: core1: dcache write misses=0 (hit ratio=-2147483648%)
PERF: core1: dcache bank stalls=0 (utilization=-2147483648%)
PERF: core1: dcache mshr stalls=0
PERF: core1: dcache pipeline stalls=0
PERF: core1: dcache reponse stalls=0
PERF: core1: smem reads=0
PERF: core1: smem writes=0
PERF: core1: smem bank stalls=0 (utilization=-2147483648%)
PERF: core1: dram requests=0 (reads=0, writes=0)
PERF: core1: dram stalls=0 (utilization=-2147483648%)
PERF: core1: dram average latency=-2147483648 cycles
PERF: instrs=5964, cycles=5416, IPC=1.101182
PERF: ibuffer stalls=0
PERF: scoreboard stalls=0
PERF: alu unit stalls=0
PERF: lsu unit stalls=0
PERF: csr unit stalls=0
PERF: fpu unit stalls=0
PERF: gpu unit stalls=0
PERF: icache reads=0
PERF: icache read misses=0 (hit ratio=-2147483648%)
PERF: icache pipeline stalls=0
PERF: icache reponse stalls=0
PERF: dcache reads=0
PERF: dcache writes=0
PERF: dcache read misses=0 (hit ratio=-2147483648%)
PERF: dcache write misses=0 (hit ratio=-2147483648%)
PERF: dcache bank stalls=0 (utilization=-2147483648%)
PERF: dcache mshr stalls=0
PERF: dcache pipeline stalls=0
PERF: dcache reponse stalls=0
PERF: smem reads=0
PERF: smem writes=0
PERF: smem bank stalls=0 (utilization=-2147483648%)
PERF: dram requests=0 (reads=0, writes=0)
PERF: dram stalls=0 (utilization=-2147483648%)
PERF: dram average latency=-2147483648 cycles
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/vecadd'