Analyzers
Talk to fellow users of Intel Analyzer tools (Intel VTune™ Profiler, Intel Advisor)
5137 Discussions

VTune: Clarification regarding "Vector Capacity Usage"

HarshVardhanKumar
New Contributor I
2,374 Views

The VTune docs describes this metric as "how the application code vectorization relates to the floating point computations. A value of 100% means that all floating point instructions are vectorized with the full vector capacity."

 

The last phrase "full vector capacity" is bugging me. What exactly does it mean? Full capacity of what - Vector hardware or vector instructions?

 

Harsh

Labels (1)
0 Kudos
1 Solution
Dmitry_P_Intel1
Employee
2,352 Views

Hello,

"Vector Capacity Usage" metric was an attempt to show both vectorizaton efficiency and SIMD utilization efficiency in one metric. For example, if you have 100% of FP instructions vectorized, but the vector instructions used in the application  are 128-bit with the processor capable to execute 256-bit instructions - Vector Capacity metric will show 50%. If 50% of FP instructions are vectorized and vector instructions used in the application  are 128-bit with the processor capable to execute 256-bit instructions - Vector Capacity metric will show 25%. In the latest product versions this metric was replaced with more straightforward metrics. 

Thanks & Regards, Dmitry

View solution in original post

5 Replies
Dmitry_P_Intel1
Employee
2,353 Views

Hello,

"Vector Capacity Usage" metric was an attempt to show both vectorizaton efficiency and SIMD utilization efficiency in one metric. For example, if you have 100% of FP instructions vectorized, but the vector instructions used in the application  are 128-bit with the processor capable to execute 256-bit instructions - Vector Capacity metric will show 50%. If 50% of FP instructions are vectorized and vector instructions used in the application  are 128-bit with the processor capable to execute 256-bit instructions - Vector Capacity metric will show 25%. In the latest product versions this metric was replaced with more straightforward metrics. 

Thanks & Regards, Dmitry

Zakhar_M_Intel1
Employee
2,304 Views

Also, for in-depth SIMD / Vectorization analysis you can use Intel (Vectorization) Advisor, available for individual download or as a part of oneAPI base toolkit/Parallel Studio

Zakhar_M_Intel1_0-1631557174398.png

 

See:

https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/advisor.html

https://software.intel.com/content/www/us/en/develop/documentation/advisor-user-guide/top/analyze-vectorization-perspective.html

 

RaviranjanK_Intel
Moderator
2,274 Views

Hi HarshVardhanKumar,


We have not heard from you. Has the solution provided helped? Could you please give us an update?


Thanks


0 Kudos
HarshVardhanKumar
New Contributor I
2,246 Views

The provided solution has helped. I've selected the answer which helped me as the accepted solution. Thanks.

0 Kudos
RaviranjanK_Intel
Moderator
2,227 Views

Hi,


Thanks for accepting our solution. If you need any additional information, please post a new question as this thread will no longer be monitored by Intel.


Thanks


0 Kudos
Reply