|
@@ -57,7 +57,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the profiler's report. [Download the profiler output](../../source_code/openmp/rdf_offload_split.qdrep) and open it via the GUI. Now, right click on the kernel and click on \"Analyze the Selected Kernel with NVIDIA Nsight Compute\" (see below screenshot). \n",
|
|
|
+ "Let's checkout the profiler's report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_offload_split.qdrep) and open it via the GUI. Now, right click on the kernel and click on \"Analyze the Selected Kernel with NVIDIA Nsight Compute\" (see below screenshot). \n",
|
|
|
"\n",
|
|
|
"<img src=\"../images/compute_analyz.png\">\n",
|
|
|
"\n",
|
|
@@ -84,7 +84,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout Nsight Compute report. [Download the profiler output](../../source_code/openmp/rdf_offload_split.ncu-rep) and open it via the GUI. Have a look at the example expected profiler report below:\n",
|
|
|
+ "Let's checkout Nsight Compute report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_offload_split.ncu-rep) and open it via the GUI. Have a look at the example expected profiler report below:\n",
|
|
|
"\n",
|
|
|
"<img src=\"../images/openmp_offload_split_cmp.png\">\n",
|
|
|
"\n",
|
|
@@ -171,7 +171,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the profiler's report. [Download the profiler output](../../source_code/openmp/rdf_offload_split_num.qdrep) and open it via the GUI. Let's dig deeper and profile the `pair_gpu` kernel with Nsight Compute and compare it with the baseline."
|
|
|
+ "Let's checkout the profiler's report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_offload_split_num.qdrep) and open it via the GUI. Let's dig deeper and profile the `pair_gpu` kernel with Nsight Compute and compare it with the baseline."
|
|
|
]
|
|
|
},
|
|
|
{
|
|
@@ -188,7 +188,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the Nsight Compute report. [Download the profiler output](../../source_code/openmp/rdf_offload_split_num.ncu-rep) and open it via the GUI. \n",
|
|
|
+ "Let's checkout the Nsight Compute report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_offload_split_num.ncu-rep) and open it via the GUI. \n",
|
|
|
"\n",
|
|
|
"<img src=\"../images/openmp_offload_split_cmp2.png\">\n",
|
|
|
"\n",
|
|
@@ -285,7 +285,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the profiler's report. [Download the profiler output](../../source_code/openmp/rdf_collapse.qdrep) and open it via the GUI. Have a look at the example expected profiler report below:\n",
|
|
|
+ "Let's checkout the profiler's report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_collapse.qdrep) and open it via the GUI. Have a look at the example expected profiler report below:\n",
|
|
|
"\n",
|
|
|
"<img src=\"../images/openmp_gpu_collapse.png\">\n",
|
|
|
"\n",
|
|
@@ -308,7 +308,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the Nsight Compute report. [Download the profiler output](../../source_code/openmp/rdf_collapse.ncu-rep) and open it via the GUI. Have a look at the example expected profiler report below (yellow is the base version, blue is the current):\n",
|
|
|
+ "Let's checkout the Nsight Compute report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_collapse.ncu-rep) and open it via the GUI. Have a look at the example expected profiler report below (yellow is the base version, blue is the current):\n",
|
|
|
"\n",
|
|
|
"<img src=\"../images/openmp_offload_collapse.png\">\n",
|
|
|
"\n",
|
|
@@ -378,7 +378,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the profiler's report. [Download the profiler output](../../source_code/openmp/rdf_collapse_regcount.qdrep) and open it via the GUI. Let's dig deeper and profile the `pair_gpu` kernel with Nsight Compute and compare it with the baseline."
|
|
|
+ "Let's checkout the profiler's report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_collapse_regcount.qdrep) and open it via the GUI. Let's dig deeper and profile the `pair_gpu` kernel with Nsight Compute and compare it with the baseline."
|
|
|
]
|
|
|
},
|
|
|
{
|
|
@@ -395,7 +395,7 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "Let's checkout the Nsight Compute report. [Download the profiler output](../../source_code/openmp/rdf_collapse_regcount.ncu-rep) and open it via the GUI. Have a look at the example expected profiler report below (pink is the previous version using `collapse` clause, blue is the current after limiting the register count):\n",
|
|
|
+ "Let's checkout the Nsight Compute report. Download and save the report file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../../source_code/openmp/rdf_collapse_regcount.ncu-rep) and open it via the GUI. Have a look at the example expected profiler report below (pink is the previous version using `collapse` clause, blue is the current after limiting the register count):\n",
|
|
|
"\n",
|
|
|
"<img src=\"../images/openmp_collapse_reg.png\">\n",
|
|
|
"\n",
|
|
@@ -450,7 +450,9 @@
|
|
|
"cell_type": "markdown",
|
|
|
"metadata": {},
|
|
|
"source": [
|
|
|
- "**After** executing the above zip command, you should be able to download the zip file [here](../nways_files.zip). Let us now go back to parallelizing our code using other approaches.\n",
|
|
|
+ "**After** executing the above zip command, you should be able to download and save the zip file by holding down <mark>Shift</mark> and <mark>Right-Clicking</mark> [Here](../nways_files.zip).\n",
|
|
|
+ "\n",
|
|
|
+ "Let us now go back to parallelizing our code using other approaches.\n",
|
|
|
"\n",
|
|
|
"**IMPORTANT**: Please click on **HOME** to go back to the main notebook for *N ways of GPU programming for MD* code.\n",
|
|
|
"\n",
|
|
@@ -498,7 +500,7 @@
|
|
|
"name": "python",
|
|
|
"nbconvert_exporter": "python",
|
|
|
"pygments_lexer": "ipython3",
|
|
|
- "version": "3.7.4"
|
|
|
+ "version": "3.6.9"
|
|
|
}
|
|
|
},
|
|
|
"nbformat": 4,
|