-
Notifications
You must be signed in to change notification settings - Fork 98
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Stream support for Gauss-Seidel: Symbolic, Numeric, Apply (Twostage) #1980
base: develop
Are you sure you want to change the base?
Conversation
e10harvey
commented
Sep 26, 2023
•
edited
Loading
edited
- Move twostage GS apply onto streams
- Move sptrsv_solve onto streams (see Add sptrsv execution space overloads #1982)
- Add lightweight hint to kernel launches
- Move symbolic and numeric onto streams
- Update unit test to exercise twostage with streams
@@ -985,8 +986,11 @@ class TwostageGaussSeidel { | |||
Kokkos::subview(localZ, Kokkos::ALL(), range_type(j, j + 1)); | |||
single_vector_view_t Rj(localRj.data(), num_rows); | |||
single_vector_view_t Zj(localZj.data(), num_rows); | |||
my_exec_space | |||
.fence(); // Wait for writes to R and Z to land, TODO: remove | |||
sptrsv_solve(handle->get_gs_sptrsvL_handle(), crsmatL.graph.row_map, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
My preference would be to call a sptrsv_solve
overload that accepts an execution space instance. Alternatively, I could create std::vectors of size 1 and call sptrsv_solve_streams
. What is your preference @brian-kelley, @lucbv, and @vqd8a?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@e10harvey To simplify the function call, I have the same preference as yours.
8497ad2
to
dd098a3
Compare
Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection is Not Necessary for this Pull Request. |
Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects: Pull Request Auto Testing STARTING (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930_Tpls_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_Tpls_ARMPL2110
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_ROCM520
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_Tpls_ROCM520
Jenkins Parameters
Using Repos:
Pull Request Author: e10harvey |
Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run. Pull Request Auto Testing has FAILED (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930_Tpls_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_Tpls_ARMPL2110
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_ROCM520
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_Tpls_ROCM520
Jenkins Parameters
Console Output (last 100 lines) : KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight # 926 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930_Tpls_CLANG13CUDA10 # 517 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GNU1021 # 190 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GNU1021_Light_LayoutRight # 189 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GNU1021 # 189 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL19_solo # 195 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001_solo # 169 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_A64FX_Tpls_ARMPL2110 # 680 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_A64FX_GCC1020 # 675 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_VEGA908_ROCM520 # 673 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_VEGA908_Tpls_ROCM520 # 194 (click to expand)
|
Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection is Not Necessary for this Pull Request. |
Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_VEGA908_ROCM520 to start: Total Wait = 3603
|
Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection is Not Necessary for this Pull Request. |
Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_CLANG1001_solo to start: Total Wait = 3603
|
Status Flag 'Pull Request AutoTester' - User Requested Retest - Label AT: RETEST will be reset after testing. |
Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects: Pull Request Auto Testing STARTING (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930_Tpls_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_Tpls_ARMPL2110
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_ROCM520
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_Tpls_ROCM520
Jenkins Parameters
Using Repos:
Pull Request Author: e10harvey |
Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run. Pull Request Auto Testing has FAILED (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930_Tpls_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GNU1021_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GNU1021
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001_solo
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_Tpls_ARMPL2110
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_A64FX_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_ROCM520
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_VEGA908_Tpls_ROCM520
Jenkins Parameters
Console Output (last 100 lines) : KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight # 942 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930_Tpls_CLANG13CUDA10 # 531 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GNU1021 # 204 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GNU1021_Light_LayoutRight # 203 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GNU1021 # 203 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL19_solo # 209 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001_solo # 180 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_A64FX_Tpls_ARMPL2110 # 691 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_A64FX_GCC1020 # 686 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_VEGA908_ROCM520 # 682 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_VEGA908_Tpls_ROCM520 # 203 (click to expand)
|
@brian-kelley, @vqd8a, @lucbv: This one is ready to review. CI is failing due to the HIP OOM system issue. Note that hints and moving sptrsv onto streams will be done in a follow-on PR. |
@e10harvey I guess since #1980 is already open, it makes sense to wait for that, and take care of the two-stage impl TODOs before merging this? But everything here LGTM. |
- Note: everything except for KokkosGraph and sptrsv runs on streams.
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
29 similar comments
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |
All Jobs Finished; status = PASSED, However PR is now STALE, and must be retested. Set the AT: RETEST Label to force retest.... |