Stack Overflow
Stack Overflow

Questions tagged [papi]

PAPI (Performance Application Programming Interface) provides the tool designer and application engineer with a consistent interface and methodology for use of the performance counter hardware found in most major microprocessors. PAPI enables software engineers to see, in near real time, the relation between software performance and processor events.

86 questions
2
votes
1 answer

Event does not exist for py-papi but event is available for papi_avail

I am following the tutorial here for a python wrapper for the Performance Application Programming Interface. I can see via papi_avail that my system does have hardware counters (Number Hardware Counters: 11) and that the event I am interested in…
user1887919
  • 829
  • 2
  • 9
  • 24
2
votes
1 answer

Cross-compiling for arm64

I'm trying to install papi tools on juno arm development board, I have installed 64-bit Linaro `ack-armlt' Android Common Kernel plus Android filesystem on that board (I followed this tutorial to accomplish that). My system is: Linux…
LuisM
  • 111
  • 2
  • 3
  • 9
2
votes
1 answer

can we instrument UPC code with PAPI API calls

I want to instrument my UPC program with PAPI APIs to get information on hardware counters during the execution of UPC program. But i keep getting linking errors for eg, "undefined reference to PAPI_read" undefined reference to PAPI_library_init…
Sharat Chandra
  • 4,434
  • 7
  • 49
  • 66
2
votes
1 answer

Monitor performance counters of running process using papi

How I can monitor the hardware counters of already running process using PAPI? Any help will be highly appreciated. Thanks Shuja
David
  • 481
  • 5
  • 14
2
votes
1 answer

Pedantic raising error when linking PAPI

I am trying to build some project that uses the PAPI 5.4.3.0 library, in an Arch Linux x86_64. For simplicity sake, I reproduced the things that I don't understand in these two files: A.cpp #include "string.h" #include "papi.h" int main() { }…
yZaph
  • 169
  • 1
  • 10
2
votes
1 answer

Total Cache misses fewer than data cache misses (PAPI_L1_DCM > PAPI_L1_TCM)

For my application (SpMV) I have more data cache misses (PAPI_L1_DCM) than total cache misses (PAPI_L1_TCM) in level 1 cache. How can that be? For Level 2 the values are ok. That is, what the PAPI counters offer: [PAPI_L1_ICM ][PAPI_L1_DCM…
SScholl
  • 598
  • 6
  • 19
2
votes
1 answer

Unable to link PAPI library with opt llvm

I am working on a project where I need to generate just the bitcode using clang, run some optimization passes using opt and then create an executable and measure its hardware counters. I am able to link through clang directly using: clang -g -O0 -w…
goyalankit
  • 843
  • 8
  • 23
2
votes
1 answer

papi_test.h: no file or directory

I was trying a PAPI code to attach itself to an already running code but on compilation it gives an error papi_test.h : no such file or directory #include "papi_test.h" #include #include // #include …
sol
  • 95
  • 1
  • 12
2
votes
2 answers

How to read power consumption using CUPTI?

I know that there's a way to read the power consumption of a GPU using CUPTI. Do you know of any method I can use? and where I can find examples?
user1730250
  • 582
  • 2
  • 9
  • 26
2
votes
1 answer

Why am I getting an “Undefined reference” error when I run my Makefile on some computers, but not others?

I am doing some research on parallel processing and need to test counter output with different parallel-ization APIs. Every time I try to make my code, I get undefined reference to 'PAPI_.... I am using PAPI 5.1.1 and already know which directories…
user2307421
  • 51
  • 1
  • 2
  • 6
2
votes
3 answers

PAPI and native events

Is it possible to find the set of native events (CPU counter registers) that maps to a PAPI event ?
user1511956
  • 784
  • 3
  • 9
  • 22
2
votes
2 answers

Unexpectedly large number of TLB misses in simple PAPI profiling on x86

I am using the PAPI high level API to check TLB misses in a simple program looping through an array, but seeing larger numbers than expected. In other simple test cases, the results seem quite reasonable, which leads me to think the results are real…
jmetcalfe
  • 1,296
  • 9
  • 17
2
votes
1 answer

PAPI performance counters issues on a AMD Opteron 6172

I've been trying to analyze certain applications(written in C) with performance counters on a AMD Opteron 6172 processor, running Red Hat Enterprise Linux Workstation release 6.2 (Santiago). I'm using PAPI v4.1.3.0 which uses the AMD native events…
Aleksr9
  • 1,233
  • 2
  • 9
  • 7
1
vote
1 answer

How to read from the file descriptor returned by __NR_perf_event_open

I am reading the code written by Lemire which makes a benchmark of number of CPU cycles and instructions. The following is the main logic: #define N_CONFIG 2 int CONFIGS[N_CONFIG] = {PERF_COUNT_HW_CPU_CYCLES, PERF_COUNT_HW_INSTRUCTIONS}; …
chenzhongpu
  • 6,193
  • 8
  • 41
  • 79
1
vote
0 answers

C# and C/C++ integration for profiling

I am trying to do some profiles on some applications regarding low-level efficiency in OO frameworks, namely, instruction counts, cache-miss, TLB misses, and things of the sort. So far I was able to do these kind of measurements in Java mixing the…
nuno
  • 1,771
  • 1
  • 19
  • 48
1 2
3
4 5 6