cancel
Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

ekondis
Adept II

Zero values for performance counters

I'm using the command line profiler (sprofile) included in the CodeXL 1.1 bundle to profile a program having multiple kernel calls. The problem is that the program stops execution unexpectedly after a few kernel calls(when not profiling it runs correctly) and secondly, it provides zero numbers for some essential performance counters which doesn't make sense. For instance, can the "Wavefronts" counter be zero for a multi workgroup kernel call?

Here is a part of the output:

#ProfileFileVersion=2.6

#ProfilerVersion=2.6.2153

#Application=/home/elias/mounts/smbhome/work/oclmicrobenchmarks/_profile/oclmicrobenchmarks

#ApplicationArgs=1

#Device AMD Athlon(tm) 64 X2 Dual Core Processor 4400+ Platform Vendor=Advanced Micro Devices, Inc.

#Device AMD Athlon(tm) 64 X2 Dual Core Processor 4400+ Platform Name=AMD Accelerated Parallel Processing

#Device AMD Athlon(tm) 64 X2 Dual Core Processor 4400+ Platform Version=OpenCL 1.2 AMD-APP (1113.2)

#Device AMD Athlon(tm) 64 X2 Dual Core Processor 4400+ CLDriver Version=1113.2 (sse2)

#Device AMD Athlon(tm) 64 X2 Dual Core Processor 4400+ CLRuntime Version=OpenCL 1.2 AMD-APP (1113.2)

#Device AMD Athlon(tm) 64 X2 Dual Core Processor 4400+ NumberAppAddressBits=32

#Device Capeverde Platform Vendor=Advanced Micro Devices, Inc.

#Device Capeverde Platform Name=AMD Accelerated Parallel Processing

#Device Capeverde Platform Version=OpenCL 1.2 AMD-APP (1113.2)

#Device Capeverde CLDriver Version=1113.2 (VM)

#Device Capeverde CLRuntime Version=OpenCL 1.2 AMD-APP (1113.2)

#Device Capeverde NumberAppAddressBits=32

#OS Version=Ubuntu 12.04.2 LTS \n \l

#DisplayName=

#ListSeparator=,

Method, ExecutionOrder, ThreadID, CallIndex, GlobalWorkSize, WorkGroupSize, Time, LocalMemSize, VGPRs, SGPRs, ScratchRegs, FCStacks, Wavefronts, VALUInsts, SALUInsts, VFetchInsts, SFetchInsts, VWriteInsts, LDSInsts, VALUUtilization, VALUBusy, SALUBusy, FetchSize, CacheHit, MemUnitBusy, MemUnitStalled, WriteUnitStalled, LDSBankConflict, WriteSize, GDSInsts

VectorReset__k1_Capeverde1, 1, 2379, 45, {16777216       1       1}, {   64     1     1},         1.77008, 0, 3, 18, 0, NA,    262144.00,         7.00,         1.00,         0.00,         3.00,         1.00,         0.00,       100.00,        12.97,         1.85,         1.00,         0.00,        84.59,        10.89,        30.89,         0.00,     65536.00,         0.00

VectorAdd__k2_Capeverde1, 2, 2379, 52, {16777216       1       1}, {   64     1     1},         3.74015, 0, 3, 24, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorRead__k3_Capeverde1, 3, 2379, 62, {16777216       1       1}, {   64     1     1},         2.36385, 0, 3, 20, 0, NA,    262144.00,         9.00,         3.00,         2.00,         7.00,         0.00,         0.00,       100.00,        12.38,         4.13,    131073.75,         0.00,        80.50,         0.00,         0.00,         0.00,         0.00,         0.00

VectorReduction__k4_Capeverde1, 4, 2379, 70, {16777216       1       1}, {   64     1     1},         2.47363, 256, 4, 14, 0, NA,    262144.00,        40.00,        33.00,         1.00,         7.00,         1.00,        13.00,        47.38,        52.80,        43.56,     65538.75,        20.01,        82.40,         5.10,         0.00,         0.00,         0.12,         0.00

VectorCalcPI__k5_Capeverde1, 5, 2379, 78, {268435456       1       1}, {   64     1     1},        38.28548, 256, 6, 18, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorSequentialCalcPI__k6_Capeverde1, 6, 2379, 85, {      1       1       1}, {    1     1     1},         2.80504, 0, 6, 18, 0, NA,         1.00,    229384.00,     32775.00,         0.00,         4.00,         1.00,         0.00,         1.56,         1.21,         0.14,         0.44,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorCalcPIDP__k7_Capeverde1, 7, 2379, 93, {268435456       1       1}, {   64     1     1},       209.16815, 512, 15, 20, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorReset__k1_Capeverde1, 8, 2379, 104, {16777216       1       1}, {  128     1     1},         1.83867, 0, 3, 18, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorAdd__k2_Capeverde1, 9, 2379, 111, {16777216       1       1}, {  128     1     1},         3.65896, 0, 3, 24, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorRead__k3_Capeverde1, 10, 2379, 121, {16777216       1       1}, {  128     1     1},         2.31111, 0, 3, 20, 0, NA,    262144.00,         9.00,         3.00,         2.00,         7.00,         0.00,         0.00,       100.00,        12.64,         4.21,    131073.75,         0.00,        51.14,         0.00,         0.00,         0.00,         0.00,         0.00

VectorReduction__k4_Capeverde1, 11, 2379, 129, {16777216       1       1}, {  128     1     1},         3.32178, 512, 4, 14, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

VectorCalcPI__k5_Capeverde1, 12, 2379, 137, {268435456       1       1}, {  128     1     1},        49.44948, 512, 6, 18, 0, NA,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00,         0.00

I'm using a 32bit Ubuntu 12.04 system with Catalyst 13.06 BETA installed and a Radeon HD7750.

0 Likes
1 Reply
pbailey
Staff

I am also experiencing this issue on a 64-bit Ubuntu 12.04.2 system with Catalyst 13.6 beta and an A10-5800K APU.  I've noticed that running with a smaller dataset on the GPU seems to reduce the effect.

0 Likes