jefflarkin

Background

OpenACC defines data acording to whether it is in discrete or shared memory. When in discrete, specific data operations are specified and implicit data clauses are defined. When in shared memory, data clauses may be ignored if they exist. As an optimization, an implementation may wish to use data clauses as optimization hints. I have historically thought of these in terms of CUDA Unified/Managed Memory with preferred location and prefetching hints. A few cases were brought to my attention that are potentially interesting examples of how this thinking may not be sufficient.

Modifying an allocation during an asynchronous region

I have been made aware of an application that extensively uses the pattern below. A temporary array is allocated locally, in the example below it is an automatic array, and dynamic data lifetimes are used to expose it to the device asynchronously. It is possible that the function would return, deallocting the automatic array, before all operations on that array have com

jefflarkin

# 
# Klipper configuration file for Anycubic i3 MEGA S
#
# This config file contains settings of all printer pins (steppers, sensors) for Anycubic i3 mega S with TMC2208 Drivers with stock plug orientation 
# Klipper firmware should be compiled for the atmega2560
#
# Config file includes
#  - Original or 2208(2209) rotated by cable drivers
#  - Mesh bed leveling: BLtouch (3DTouch sensor from Triangelab)
#  - Manual meshed bed leveling (commented out)

jefflarkin

Biography

Jeff Larkin is a Director in NVIDIA's HPC Software team, where he leads a team responsible for HPC programming models and standards and also technical marketing engineering. He is passionate about the advancement and adoption of parallel programming models for High Performance Computing. He was previously a member of NVIDIA's Developer Technology group, specializing in performance analysis and optimization of high performance computing applications. Jeff is also the chair of the OpenACC technical committee and has worked in both the OpenACC and OpenMP standards bodies. Before joining NVIDIA, Jeff worked in the Cray Supercomputing Center of Excellence, located at Oak Ridge National Laboratory. Jeff holds a B.S. in Computer Science from Furman University and a M.S. in Computer Science from the University of Tennessee, where he was a member of the Innovative Computing Lab.

Headshot

Social Links

• [LinkedIn](https://www.li

jefflarkin

jefflarkin

# This should be added AFTER the FindCUDA macro has been run
IF(USE_NVTX)
  IF(HAVE_CUDA)
    ADD_DEFINITIONS(-DUSE_NVTX)
    LINK_DIRECTORIES("${CUDA_TOOLKIT_ROOT_DIR}/lib64")
    LINK_LIBRARIES("nvToolsExt")
  ENDIF(HAVE_CUDA)
ENDIF(USE_NVTX)

jefflarkin

#!/bin/bash
# USAGE: Add between aprun options and executable
# For Example: aprun -n 16 -N 1 ./foo arg1 arg2
# Becomes: aprun -n 16 -N 1 ./cpu_profile.sh ./foo arg1 arg2

# Give each *rank* a separate file
LOG=cpu_profile_$ALPS_APP_PE.nvprof

# Stripe each profile file by 1 to share the load on large runs
if [ ! -f "$LOG" ] ; then

jefflarkin

#!/bin/bash
#FIXME Add usage() function to improve documentation

# Enable exposure of the specified GPIO pin (0-8)
gpio_enable()
{
  if [[("$1" -lt 0) || ("$1" -gt 8)]] ; then
    echo "Valid pins are 0-8"
    return -1;
  fi

jefflarkin

#!/bin/bash
# USAGE: Add between aprun options and executable
# For Example: aprun -n 16 -N 1 ./foo arg1 arg2
# Becomes: aprun -n 16 -N 1 ./nvprof.sh ./foo arg1 arg2
export PMI_NO_FORK=1

# Give each *rank* a separate file
LOG=timeline_$ALPS_APP_PE.nvprof

# Set the process and context names

jefflarkin

Keybase proof

I hereby claim:

• I am jefflarkin on github.
• I am jefflarkin (https://keybase.io/jefflarkin) on keybase.
• I have a public key whose fingerprint is 13D8 BCCC 1A50 57D3 FB4F E33A 950C 167F 0C1A 041D

To claim this, I am signing this object:

jefflarkin

#include <pthread.h>
#include <nvToolsExt.h>
#include <nvToolsExtCudaRt.h>
// Setup event category name
{{fn name MPI_Init}}
  nvtxNameCategoryA(999, "MPI");
  {{callfn}}
  int rank;
  PMPI_Comm_rank(MPI_COMM_WORLD, &rank);
  char name[256];