Hi In the following code, I would like to collect the SM IDs that have executed the kernel. The kernel is a simple addition one and I have written this code: __device__ uint get_smid(void) { uint ret; asm("mov.u32 %0, %smid;" : "=r"(ret) ); return ret; } __global__ void simpleAdd(fl…

That is no surprise, is it? nsmid is simply an upper bound for smid. they are not equivalent. This code will print a histogram of used sm ids. #include <iostream> #include <map> __device__ int get_smid(void) { int ret; asm("mov.u32 %0, %smid;" : "=r"(ret) ); return ret; } __global__…

Collecting busy SM IDs

Accelerated Computing CUDA CUDA Programming and Performance

mahmood.nt March 12, 2024, 12:59pm 5

OK Thank you very much.
I also found an answer to the first question with an example in this page

gist.github.com

https://gist.github.com/allanmac/4751080

smid.cu

#include <stdio.h>

//
//
//

#define DEVICE_INTRINSIC_QUALIFIERS   __device__ __forceinline__

DEVICE_INTRINSIC_QUALIFIERS
unsigned int

This file has been truncated. show original

SM Used by a particular program

Topic		Replies	Views
any way to know on which SM a thread is running? CUDA Programming and Performance	22	11983	July 17, 2017
How to get SM number? CUDA Programming and Performance	1	1016	January 4, 2011
Block ids and SM ids CUDA Programming and Performance	0	4564	April 14, 2011
visibility what thread contains to what SM CUDA Programming and Performance	5	1806	August 5, 2013
Identifying SM number of a block CUDA Programming and Performance	1	4194	May 3, 2010
Block ids and SM ids CUDA Programming and Performance	4	2111	April 15, 2011
Question about threads and SMs CUDA Programming and Performance	1	570	February 4, 2014
using %smid? (compiling a ptx?) CUDA Programming and Performance	2	6599	June 7, 2010
Global Timing and Kernels CUDA Programming and Performance	9	1458	July 17, 2013
Which SM is each block using? CUDA Programming and Performance	1	826	July 15, 2013

Collecting busy SM IDs

Related topics