-
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
ROTMG: adding rotmg implementation to KokkosBlas #1560
Conversation
blas/src/KokkosBlas1_rotmg.hpp
Outdated
template <class execution_space, class DXView, class YView, class PView> | ||
void rotmg(execution_space& space, DXView& d1, DXView& d2, DXView& x1, const YView& y1, PView param) { | ||
Kokkos::Profiling::pushRegion("KokkosBlas::rotmg"); | ||
Impl::Rotmg<Scalar>::rotmg(a, b, c, s); |
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.
Where do a,b,c,s come from? Also shouldn't the input views be converted to unmanaged and unified layout?
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.
nvm I see this is a WIP
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.
Yep, I need to write a unit-test and exercise this, hopefully sometime tonight x)
I was just curious if the interface that uses Kokkos::View for all the input parameters looks reasonable.
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.
Yes, I think the interface is fine.
@srajama1 @brian-kelley |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930 # 87 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight # 95 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020 # 48 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020_Light_LayoutRight # 47 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC1020 # 10 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL19 # 97 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 146 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG13CUDA10 # 37 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020 # 41 (click to expand)
|
This should be fine now, just need to wait for kokkos/kokkos#5534 to be fixed via kokkos/kokkos#5535 before this can be tested. |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930 # 89 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight # 97 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020 # 50 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020_Light_LayoutRight # 49 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC1020 # 12 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL19 # 99 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 148 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG13CUDA10 # 39 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020 # 43 (click to expand)
|
This adds a full implementation for rotmg, its ETI and TPLs.
Status Flag 'Pull Request AutoTester' - User Requested Retest - Label AT: RETEST will be reset after testing. |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930 # 91 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight # 99 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020 # 52 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020_Light_LayoutRight # 51 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC1020 # 14 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL19 # 101 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 150 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG13CUDA10 # 40 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020 # 44 (click to expand)
|
// We may spread out definitions (see _DEF macro below) across one or | ||
// more .cpp files. | ||
// | ||
#define KOKKOSBLAS1_ROTMG_ETI_SPEC_DECL(SCALAR, LAYOUT, EXEC_SPACE, MEM_SPACE) \ |
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.
You could get away with not instantiating for different layouts, since everything is rank 0 or 1. But the code is really small so it's not a big deal
(GetUnifiedLayout will give you a layout that is enabled in ETI, if possible)
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.
Yeah, I need to study our ETI a bit better to get this case just right, I will put that on the to-do list. Thanks for looking at it.
The Intel19 TPLs build shows small diffs in values (see below), increasing the tolerance a bit should be fine.
The ARM TPL build requires a bit more investigation, at first glance, having diffs in param(0) which is a flag looks problematic...
|
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930 # 116 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight # 124 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020 # 77 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC1020_Light_LayoutRight # 76 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC1020 # 39 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL19 # 126 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 175 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG13CUDA10 # 65 (click to expand)
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020 # 69 (click to expand)
|
The TPLs have their own slightly different way of implementing rotmg, the changes here are handling that by disabling ARMPL and losening the tolerance when running with MKL. Overall this is not a very big deal...
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
Status Flag 'Pull Request AutoTester' - Jenkins Testing: all Jobs PASSED Pull Request Auto Testing has PASSED (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
|
Status Flag 'Pre-Merge Inspection' - - This Pull Request Requires Inspection... The code must be inspected by a member of the Team before Testing/Merging |
All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur... |
namespace KokkosBlas { | ||
namespace Impl { | ||
|
||
// Generic Host side BLAS (could be MKL or whatever) |
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.
Maybe make a note here about why ARMPL is disabled
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.
Yep, I expended the comment to mention ARMPL
blas/unit_test/Test_Blas1_rotmg.hpp
Outdated
|
||
constexpr int num_test_cases = 9; | ||
for (int test_case = 0; test_case < num_test_cases; ++test_case) { | ||
#if defined(KOKKOSKERNELS_ENABLE_TPL_ARMPL) |
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.
Can take this if defined branch out if ARMPL is never used
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.
Sure, I removed that #ifdef
since it is no longer required.
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_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
NOTICE: The AutoTester has encountered an internal error (usually a Communications Timeout), testing will be restarted, previous tests may still be running but will be ignored by the AutoTester... |
Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects: Pull Request Auto Testing STARTING (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
Using Repos:
Pull Request Author: lucbv |
Status Flag 'Pull Request AutoTester' - Jenkins Testing: all Jobs PASSED Pull Request Auto Testing has PASSED (click to expand)Build InformationTest Name: KokkosKernels_PullRequest_GCC930_Light_Tpls_GCC930
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CUDA11_CUDA11_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_GCC1020_Light_LayoutRight
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_GCC1020
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_INTEL19
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG1001
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_CLANG13CUDA10
Jenkins Parameters
Build InformationTest Name: KokkosKernels_PullRequest_Tpls_ARMPL2110_Tpls_ARMPL2030_GCC1020
Jenkins Parameters
|
Status Flag 'Pre-Merge Inspection' - SUCCESS: The last commit to this Pull Request has been INSPECTED AND APPROVED by [ brian-kelley ]! |
Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge |
This adds a full implementation for rotmg, its ETI and TPLs. At the moment no unit-tests are added and the GPU TPLs are not correctly implemented but the Host TPL and the fallback implementation should be complete.
@srajama1 @brian-kelley
I created a different interface and implementation from what is done in
KokkosBlas::rotg
, let me know if this looks reasonable. It is more inline with the rest of the library, it makes TPL and ETI support more clear.I am including the stream interface already.
I plan to work on cublas/rocblas next and maybe a device callable implementation to have something that can be used in device level algorithm such as batched solvers, etc...