Created performance results from 2021/03/07
This commit is contained in:
17
evaluation/perf_2021_03_07/4c/afu_default.fit.summary
Normal file
17
evaluation/perf_2021_03_07/4c/afu_default.fit.summary
Normal file
@@ -0,0 +1,17 @@
|
||||
Fitter Status : Successful - Sat Mar 6 02:49:17 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) : 117,451 / 427,200 ( 27 % )
|
||||
Total registers : 173797
|
||||
Total pins : 310 / 826 ( 38 % )
|
||||
Total virtual pins : 0
|
||||
Total block memory bits : 4,356,616 / 55,562,240 ( 8 % )
|
||||
Total RAM Blocks : 713 / 2,713 ( 26 % )
|
||||
Total DSP Blocks : 112 / 1,518 ( 7 % )
|
||||
Total HSSI RX channels : 12 / 48 ( 25 % )
|
||||
Total HSSI TX channels : 12 / 48 ( 25 % )
|
||||
Total PLLs : 25 / 112 ( 22 % )
|
||||
6945
evaluation/perf_2021_03_07/4c/afu_default.sta.summary
Normal file
6945
evaluation/perf_2021_03_07/4c/afu_default.sta.summary
Normal file
File diff suppressed because it is too large
Load Diff
4
evaluation/perf_2021_03_07/4c/afu_default.syn.summary
Normal file
4
evaluation/perf_2021_03_07/4c/afu_default.syn.summary
Normal file
@@ -0,0 +1,4 @@
|
||||
Synthesis Status : Successful - Sat Mar 6 01:57:55 2021
|
||||
Revision Name : afu_default
|
||||
Top-level Entity Name : dcp_top
|
||||
Family : Arria 10
|
||||
36027
evaluation/perf_2021_03_07/4c/build.log
Normal file
36027
evaluation/perf_2021_03_07/4c/build.log
Normal file
File diff suppressed because it is too large
Load Diff
29
evaluation/perf_2021_03_07/4c/guassian.result
Normal file
29
evaluation/perf_2021_03_07/4c/guassian.result
Normal 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=4, 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_07/4c/nearn.result
Normal file
19
evaluation/perf_2021_03_07/4c/nearn.result
Normal 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=4, 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_07/4c/saxpy.result
Normal file
19
evaluation/perf_2021_03_07/4c/saxpy.result
Normal 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=4, 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_07/4c/sfilter.result
Normal file
19
evaluation/perf_2021_03_07/4c/sfilter.result
Normal 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=4, 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'
|
||||
146
evaluation/perf_2021_03_07/4c/sgemm.result
Normal file
146
evaluation/perf_2021_03_07/4c/sgemm.result
Normal file
@@ -0,0 +1,146 @@
|
||||
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=4, num_warps=4, num_threads=4
|
||||
Create context
|
||||
Create program from kernel source
|
||||
Upload source buffers
|
||||
Execute the kernel
|
||||
Elapsed time: 3 ms
|
||||
Download destination buffer
|
||||
Verify result
|
||||
PASSED!
|
||||
PERF: core0: instrs=90890, cycles=51133, IPC=1.777521
|
||||
PERF: core0: ibuffer stalls=10132
|
||||
PERF: core0: scoreboard stalls=15251
|
||||
PERF: core0: alu unit stalls=2423
|
||||
PERF: core0: lsu unit stalls=3859
|
||||
PERF: core0: csr unit stalls=0
|
||||
PERF: core0: fpu unit stalls=0
|
||||
PERF: core0: gpu unit stalls=0
|
||||
PERF: core0: icache reads=23003
|
||||
PERF: core0: icache read misses=73 (hit ratio=99%)
|
||||
PERF: core0: icache pipeline stalls=7639
|
||||
PERF: core0: icache reponse stalls=10132
|
||||
PERF: core0: dcache reads=17502
|
||||
PERF: core0: dcache writes=293
|
||||
PERF: core0: dcache read misses=1041 (hit ratio=94%)
|
||||
PERF: core0: dcache write misses=289 (hit ratio=1%)
|
||||
PERF: core0: dcache bank stalls=8464 (utilization=67%)
|
||||
PERF: core0: dcache mshr stalls=4228
|
||||
PERF: core0: dcache pipeline stalls=9676
|
||||
PERF: core0: dcache reponse stalls=76
|
||||
PERF: core0: smem reads=2026
|
||||
PERF: core0: smem writes=1599
|
||||
PERF: core0: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core0: dram requests=479 (reads=186, writes=293)
|
||||
PERF: core0: dram stalls=789 (utilization=37%)
|
||||
PERF: core0: dram average latency=32 cycles
|
||||
PERF: core1: instrs=90890, cycles=51143, IPC=1.777174
|
||||
PERF: core1: ibuffer stalls=10158
|
||||
PERF: core1: scoreboard stalls=15244
|
||||
PERF: core1: alu unit stalls=2440
|
||||
PERF: core1: lsu unit stalls=3894
|
||||
PERF: core1: csr unit stalls=0
|
||||
PERF: core1: fpu unit stalls=0
|
||||
PERF: core1: gpu unit stalls=0
|
||||
PERF: core1: icache reads=23003
|
||||
PERF: core1: icache read misses=73 (hit ratio=99%)
|
||||
PERF: core1: icache pipeline stalls=7685
|
||||
PERF: core1: icache reponse stalls=10158
|
||||
PERF: core1: dcache reads=17502
|
||||
PERF: core1: dcache writes=293
|
||||
PERF: core1: dcache read misses=1101 (hit ratio=93%)
|
||||
PERF: core1: dcache write misses=289 (hit ratio=1%)
|
||||
PERF: core1: dcache bank stalls=8464 (utilization=67%)
|
||||
PERF: core1: dcache mshr stalls=4330
|
||||
PERF: core1: dcache pipeline stalls=9347
|
||||
PERF: core1: dcache reponse stalls=67
|
||||
PERF: core1: smem reads=2026
|
||||
PERF: core1: smem writes=1599
|
||||
PERF: core1: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core1: dram requests=509 (reads=216, writes=293)
|
||||
PERF: core1: dram stalls=715 (utilization=41%)
|
||||
PERF: core1: dram average latency=32 cycles
|
||||
PERF: core2: instrs=90890, cycles=51135, IPC=1.777452
|
||||
PERF: core2: ibuffer stalls=10120
|
||||
PERF: core2: scoreboard stalls=15237
|
||||
PERF: core2: alu unit stalls=2406
|
||||
PERF: core2: lsu unit stalls=3881
|
||||
PERF: core2: csr unit stalls=0
|
||||
PERF: core2: fpu unit stalls=0
|
||||
PERF: core2: gpu unit stalls=0
|
||||
PERF: core2: icache reads=23003
|
||||
PERF: core2: icache read misses=73 (hit ratio=99%)
|
||||
PERF: core2: icache pipeline stalls=7651
|
||||
PERF: core2: icache reponse stalls=10120
|
||||
PERF: core2: dcache reads=17502
|
||||
PERF: core2: dcache writes=293
|
||||
PERF: core2: dcache read misses=1040 (hit ratio=94%)
|
||||
PERF: core2: dcache write misses=289 (hit ratio=1%)
|
||||
PERF: core2: dcache bank stalls=8464 (utilization=67%)
|
||||
PERF: core2: dcache mshr stalls=4234
|
||||
PERF: core2: dcache pipeline stalls=9580
|
||||
PERF: core2: dcache reponse stalls=75
|
||||
PERF: core2: smem reads=2026
|
||||
PERF: core2: smem writes=1599
|
||||
PERF: core2: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core2: dram requests=478 (reads=185, writes=293)
|
||||
PERF: core2: dram stalls=776 (utilization=38%)
|
||||
PERF: core2: dram average latency=32 cycles
|
||||
PERF: core3: instrs=90892, cycles=51134, IPC=1.777526
|
||||
PERF: core3: ibuffer stalls=10116
|
||||
PERF: core3: scoreboard stalls=15282
|
||||
PERF: core3: alu unit stalls=2380
|
||||
PERF: core3: lsu unit stalls=3862
|
||||
PERF: core3: csr unit stalls=0
|
||||
PERF: core3: fpu unit stalls=0
|
||||
PERF: core3: gpu unit stalls=0
|
||||
PERF: core3: icache reads=23005
|
||||
PERF: core3: icache read misses=73 (hit ratio=99%)
|
||||
PERF: core3: icache pipeline stalls=7688
|
||||
PERF: core3: icache reponse stalls=10116
|
||||
PERF: core3: dcache reads=17502
|
||||
PERF: core3: dcache writes=293
|
||||
PERF: core3: dcache read misses=1040 (hit ratio=94%)
|
||||
PERF: core3: dcache write misses=289 (hit ratio=1%)
|
||||
PERF: core3: dcache bank stalls=8464 (utilization=67%)
|
||||
PERF: core3: dcache mshr stalls=4421
|
||||
PERF: core3: dcache pipeline stalls=9647
|
||||
PERF: core3: dcache reponse stalls=76
|
||||
PERF: core3: smem reads=2026
|
||||
PERF: core3: smem writes=1599
|
||||
PERF: core3: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core3: dram requests=478 (reads=185, writes=293)
|
||||
PERF: core3: dram stalls=684 (utilization=41%)
|
||||
PERF: core3: dram average latency=32 cycles
|
||||
PERF: instrs=363562, cycles=51143, IPC=7.108734
|
||||
PERF: ibuffer stalls=40526
|
||||
PERF: scoreboard stalls=61014
|
||||
PERF: alu unit stalls=9649
|
||||
PERF: lsu unit stalls=15496
|
||||
PERF: csr unit stalls=0
|
||||
PERF: fpu unit stalls=0
|
||||
PERF: gpu unit stalls=0
|
||||
PERF: icache reads=92014
|
||||
PERF: icache read misses=292 (hit ratio=99%)
|
||||
PERF: icache pipeline stalls=30663
|
||||
PERF: icache reponse stalls=40526
|
||||
PERF: dcache reads=70008
|
||||
PERF: dcache writes=1172
|
||||
PERF: dcache read misses=4222 (hit ratio=93%)
|
||||
PERF: dcache write misses=1156 (hit ratio=1%)
|
||||
PERF: dcache bank stalls=33856 (utilization=67%)
|
||||
PERF: dcache mshr stalls=17213
|
||||
PERF: dcache pipeline stalls=38250
|
||||
PERF: dcache reponse stalls=294
|
||||
PERF: smem reads=8104
|
||||
PERF: smem writes=6396
|
||||
PERF: smem bank stalls=0 (utilization=100%)
|
||||
PERF: dram requests=1944 (reads=772, writes=1172)
|
||||
PERF: dram stalls=2964 (utilization=39%)
|
||||
PERF: dram average latency=32 cycles
|
||||
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/sgemm'
|
||||
3
evaluation/perf_2021_03_07/4c/user_clock_freq.txt
Normal file
3
evaluation/perf_2021_03_07/4c/user_clock_freq.txt
Normal file
@@ -0,0 +1,3 @@
|
||||
# Generated by Platform Interface Manager user_clock_config.tcl
|
||||
afu-image/clock-frequency-low:93.0
|
||||
afu-image/clock-frequency-high:186
|
||||
147
evaluation/perf_2021_03_07/4c/vecadd.result
Normal file
147
evaluation/perf_2021_03_07/4c/vecadd.result
Normal file
@@ -0,0 +1,147 @@
|
||||
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=4, 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=2019, cycles=5042, IPC=0.400436
|
||||
PERF: core0: ibuffer stalls=86
|
||||
PERF: core0: scoreboard stalls=451
|
||||
PERF: core0: alu unit stalls=68
|
||||
PERF: core0: lsu unit stalls=53
|
||||
PERF: core0: csr unit stalls=0
|
||||
PERF: core0: fpu unit stalls=0
|
||||
PERF: core0: gpu unit stalls=0
|
||||
PERF: core0: icache reads=804
|
||||
PERF: core0: icache read misses=65 (hit ratio=91%)
|
||||
PERF: core0: icache pipeline stalls=469
|
||||
PERF: core0: icache reponse stalls=86
|
||||
PERF: core0: dcache reads=114
|
||||
PERF: core0: dcache writes=65
|
||||
PERF: core0: dcache read misses=28 (hit ratio=75%)
|
||||
PERF: core0: dcache write misses=60 (hit ratio=7%)
|
||||
PERF: core0: dcache bank stalls=72 (utilization=71%)
|
||||
PERF: core0: dcache mshr stalls=56
|
||||
PERF: core0: dcache pipeline stalls=88
|
||||
PERF: core0: dcache reponse stalls=1
|
||||
PERF: core0: smem reads=70
|
||||
PERF: core0: smem writes=63
|
||||
PERF: core0: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core0: dram requests=109 (reads=44, writes=65)
|
||||
PERF: core0: dram stalls=53 (utilization=67%)
|
||||
PERF: core0: dram average latency=31 cycles
|
||||
PERF: core1: instrs=2019, cycles=5041, IPC=0.400516
|
||||
PERF: core1: ibuffer stalls=86
|
||||
PERF: core1: scoreboard stalls=451
|
||||
PERF: core1: alu unit stalls=68
|
||||
PERF: core1: lsu unit stalls=53
|
||||
PERF: core1: csr unit stalls=0
|
||||
PERF: core1: fpu unit stalls=0
|
||||
PERF: core1: gpu unit stalls=0
|
||||
PERF: core1: icache reads=804
|
||||
PERF: core1: icache read misses=65 (hit ratio=91%)
|
||||
PERF: core1: icache pipeline stalls=470
|
||||
PERF: core1: icache reponse stalls=86
|
||||
PERF: core1: dcache reads=114
|
||||
PERF: core1: dcache writes=65
|
||||
PERF: core1: dcache read misses=28 (hit ratio=75%)
|
||||
PERF: core1: dcache write misses=60 (hit ratio=7%)
|
||||
PERF: core1: dcache bank stalls=72 (utilization=71%)
|
||||
PERF: core1: dcache mshr stalls=56
|
||||
PERF: core1: dcache pipeline stalls=88
|
||||
PERF: core1: dcache reponse stalls=1
|
||||
PERF: core1: smem reads=70
|
||||
PERF: core1: smem writes=63
|
||||
PERF: core1: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core1: dram requests=109 (reads=44, writes=65)
|
||||
PERF: core1: dram stalls=52 (utilization=67%)
|
||||
PERF: core1: dram average latency=31 cycles
|
||||
PERF: core2: instrs=2019, cycles=5040, IPC=0.400595
|
||||
PERF: core2: ibuffer stalls=86
|
||||
PERF: core2: scoreboard stalls=451
|
||||
PERF: core2: alu unit stalls=68
|
||||
PERF: core2: lsu unit stalls=53
|
||||
PERF: core2: csr unit stalls=0
|
||||
PERF: core2: fpu unit stalls=0
|
||||
PERF: core2: gpu unit stalls=0
|
||||
PERF: core2: icache reads=804
|
||||
PERF: core2: icache read misses=65 (hit ratio=91%)
|
||||
PERF: core2: icache pipeline stalls=470
|
||||
PERF: core2: icache reponse stalls=86
|
||||
PERF: core2: dcache reads=114
|
||||
PERF: core2: dcache writes=65
|
||||
PERF: core2: dcache read misses=28 (hit ratio=75%)
|
||||
PERF: core2: dcache write misses=60 (hit ratio=7%)
|
||||
PERF: core2: dcache bank stalls=72 (utilization=71%)
|
||||
PERF: core2: dcache mshr stalls=56
|
||||
PERF: core2: dcache pipeline stalls=88
|
||||
PERF: core2: dcache reponse stalls=1
|
||||
PERF: core2: smem reads=70
|
||||
PERF: core2: smem writes=63
|
||||
PERF: core2: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core2: dram requests=109 (reads=44, writes=65)
|
||||
PERF: core2: dram stalls=51 (utilization=68%)
|
||||
PERF: core2: dram average latency=31 cycles
|
||||
PERF: core3: instrs=2021, cycles=5043, IPC=0.400754
|
||||
PERF: core3: ibuffer stalls=102
|
||||
PERF: core3: scoreboard stalls=496
|
||||
PERF: core3: alu unit stalls=73
|
||||
PERF: core3: lsu unit stalls=53
|
||||
PERF: core3: csr unit stalls=0
|
||||
PERF: core3: fpu unit stalls=0
|
||||
PERF: core3: gpu unit stalls=0
|
||||
PERF: core3: icache reads=806
|
||||
PERF: core3: icache read misses=65 (hit ratio=91%)
|
||||
PERF: core3: icache pipeline stalls=439
|
||||
PERF: core3: icache reponse stalls=102
|
||||
PERF: core3: dcache reads=114
|
||||
PERF: core3: dcache writes=65
|
||||
PERF: core3: dcache read misses=28 (hit ratio=75%)
|
||||
PERF: core3: dcache write misses=60 (hit ratio=7%)
|
||||
PERF: core3: dcache bank stalls=72 (utilization=71%)
|
||||
PERF: core3: dcache mshr stalls=56
|
||||
PERF: core3: dcache pipeline stalls=88
|
||||
PERF: core3: dcache reponse stalls=1
|
||||
PERF: core3: smem reads=70
|
||||
PERF: core3: smem writes=63
|
||||
PERF: core3: smem bank stalls=0 (utilization=100%)
|
||||
PERF: core3: dram requests=109 (reads=44, writes=65)
|
||||
PERF: core3: dram stalls=50 (utilization=68%)
|
||||
PERF: core3: dram average latency=30 cycles
|
||||
PERF: instrs=8078, cycles=5043, IPC=1.601824
|
||||
PERF: ibuffer stalls=360
|
||||
PERF: scoreboard stalls=1849
|
||||
PERF: alu unit stalls=277
|
||||
PERF: lsu unit stalls=212
|
||||
PERF: csr unit stalls=0
|
||||
PERF: fpu unit stalls=0
|
||||
PERF: gpu unit stalls=0
|
||||
PERF: icache reads=3218
|
||||
PERF: icache read misses=260 (hit ratio=91%)
|
||||
PERF: icache pipeline stalls=1848
|
||||
PERF: icache reponse stalls=360
|
||||
PERF: dcache reads=456
|
||||
PERF: dcache writes=260
|
||||
PERF: dcache read misses=112 (hit ratio=75%)
|
||||
PERF: dcache write misses=240 (hit ratio=7%)
|
||||
PERF: dcache bank stalls=288 (utilization=71%)
|
||||
PERF: dcache mshr stalls=224
|
||||
PERF: dcache pipeline stalls=352
|
||||
PERF: dcache reponse stalls=4
|
||||
PERF: smem reads=280
|
||||
PERF: smem writes=252
|
||||
PERF: smem bank stalls=0 (utilization=100%)
|
||||
PERF: dram requests=436 (reads=176, writes=260)
|
||||
PERF: dram stalls=206 (utilization=67%)
|
||||
PERF: dram average latency=30 cycles
|
||||
make: Leaving directory '/nethome/lcooper43/vortex-dev-old/benchmarks/opencl/vecadd'
|
||||
Reference in New Issue
Block a user