cory-master/BabelStream
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
922 Commits 1 Branch 0 Tags 2.5 MiB
e7774c1372
Commit Graph

922 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
GeorgeWeb
a2e53d6728 remove use of pre-built kernel in parallel_for as is not conformant with the SYCL spec. (yet) 2019-06-18 17:31:40 +01:00
Georgi Mirazchiyski
60817e25a1 fix deprecated use of get_global() and get_local() 2019-06-18 17:22:49 +01:00
Tom Deakin
289a2c204c Version bump 2019-04-10 14:12:00 +01:00
Tom Deakin
decc44f04a
Merge pull request #56 from UoB-HPC/base2 
Add a --mibibytes flag to output bandwidth and array sizes in base 2
 2019-04-10 14:09:24 +01:00
Tom Deakin
dd6f3af98b Update changelog 2019-04-10 14:06:50 +01:00
Tom Deakin
08348d1f0f Use ternary operator for simpler base 2 output checks 2019-04-10 14:06:05 +01:00
Patrick Atkinson
c50eba9caf fix for mibibytes in printing 2019-04-10 11:04:29 +00:00
Tom Deakin
5a1396671e Add a --mibibytes flag to output bandwidth and array sizes in base 2 
This sets MiB = 2^20, GiB = 2^30 rather than the default of
MB = 10^6 and GB = 10^9.
 2019-04-09 09:50:44 +01:00
Tom Deakin
db2a4c40d8 [OpenACC] Add PGI support for Power 9 2019-03-14 15:56:51 +00:00
Tom Deakin
7ec2108896 [OpenMP] Use -qarch=auto with XL compiler 2019-03-14 15:39:45 +00:00
Tom Deakin
c8098a5cc0 [OpenACC] Add KNL support 2019-03-14 09:11:16 -05:00
Tom Deakin
f1f31d2a9b [OpenACC] Add PGI compiler support for Skylake 2019-03-13 04:14:11 -05:00
Tom Deakin
db9bf78530 [OpenMP] Add PGI compiler support 2019-03-13 04:13:38 -05:00
Tom Deakin
6229b83e62 update changelog 2019-03-11 17:40:33 +00:00
Tom Deakin
8275c97050 [OpenMP] Add NEC compiler flags 2019-03-11 11:11:18 +00:00
Tom Deakin
da085f3f59
Add logo to README 2018-10-17 09:50:20 +01:00
Tom Deakin
02bcd9b762 Fix trailing comma in CSV output 2018-10-04 14:37:27 +01:00
Tom Deakin
a1f7b94820 Support CSV output for triad only running mode 
Fixes #54
 2018-10-04 14:36:59 +01:00
Tom Deakin
96216628bf
Update CHANGELOG.md 2018-09-14 12:57:14 +01:00
Tom Deakin
a88ebd7b38
Merge pull request #51 from Ruyk/master 
Minor SYCL and OpenCL fixes
 2018-09-14 12:56:07 +01:00
Tom Deakin
e5d54dd521 Use parallel loop for OpenACC instead of kernels 
Closes #53.
 2018-07-25 15:53:50 +00:00
Tom Deakin
d9b089a0f9
Merge pull request #52 from plavin/master 
Add Titan Xp numbers
 2018-05-08 10:43:45 +01:00
Patrick Robert Lavin
b92c01c650 Add Titan Xp numbers 2018-05-07 11:42:11 -04:00
Ruyman Reyes
8920cfd633 Split compilation lines for SYCL Stream 
The Makefile for SYCL Stream compilation is now split with
individual lines for each file. This facilitates identifying
compile time errors and avoids warnings on unused symbols.
 2018-05-02 15:22:20 +01:00
Ruyman Reyes
63f32fcb51 Manually clearing the global device vector 
The vector of devices is a global object, which destruction order is
undefined. In some platforms, the OpenCL library has been unloaded
before this destructor is hit, which causes a segmentation fault after
the program ends.  By clearing the global vector of devices on
destruction of the OpenCL and SYCL Stream benchmarks we avoid the
problem.
 2018-05-02 15:21:41 +01:00
Tom Deakin
54fc326097 Add mcpu=native flag to GNU OpenMP builds 2018-04-27 13:21:30 +01:00
Tom Deakin
54b8a549c1
Update CHANGELOG.md 
Add notice to changelog about #49.
 2018-03-19 11:07:32 +00:00
Tom Deakin
c5b64b9cad
Merge pull request #49 from mangupta/fix_hip_build 
Make hip-stream buildable with latest version of HIP
 2018-03-19 11:06:25 +00:00
Maneesh Gupta
1dc35f0d99 [HIP] Search for hipcc in the preferred way 2018-03-19 15:34:07 +05:30
Maneesh Gupta
d664544afd [HIP] Fixes to work with latest HIP 
- Remove hipLaunchParm lp from __global__ kernels
- Replace hipLaunchKernel with hipLaunchKernelGGL
- Pass on template parameters to kernels
 2018-03-19 15:18:57 +05:30
Peter Žužek
6958f070b1 Removed host_buffer target 2018-03-09 11:07:18 +00:00
Tom Deakin
cc5ceb76f2 [Kokkos] Remove test for Kokkos around now fixed multiple template specializations 2018-02-15 03:40:36 +00:00
Tom Deakin
dead6d0d44 [Kokkos] Use tempate type throughout instead of double 
Fixes #44. Also requires the typedef keyword in a few places.
 2018-02-15 03:32:27 +00:00
Tom Deakin
6803a141ee [Kokkos] Rearrange Makefile variables on liner line. 
Fixes #40. The issue was the library flags came before the object
files causing lots of undefined references.
 2018-02-15 03:06:35 +00:00
Tom Deakin
5f20c119bc [Kokkos] Set some meaningful output with --list argument. 
The string is mangled by the linker, but should say something useful.
 2018-02-14 22:22:57 +00:00
Tom Deakin
45df09010c [Kokkos] Fix minor formatting 2018-02-14 22:17:10 +00:00
Tom Deakin
0092d23461 [Kokkos] Remove defining View layout as Kokkos does it correctly by default. 
This fixes #43.
 2018-02-14 22:14:47 +00:00
Tom Deakin
b93ac5d7cf [Kokkos] Rename files to match Kokkos case conventions 2018-02-14 22:05:50 +00:00
Tom Deakin
4e2450e6ac [Kokkos] Change case of implementation string define 2018-02-14 22:01:57 +00:00
Tom Deakin
3925c71851 [Kokkos] Remove global use of gobal namespace 2018-02-14 22:00:21 +00:00
Tom Deakin
1d84002cb6
Fix GitHub formatting in CHANGELOG 2018-02-07 16:54:18 +00:00
Tom Deakin
53e8f408ad
Fix GitHub formatting in CHANGELOG 2018-02-07 16:53:00 +00:00
Tom Deakin
88c8854a54 Add unreleased changes to CHANGELOG 2018-02-07 16:51:57 +00:00
Tom Deakin
710a18916c Add a Changelog file to document project changes 2018-02-07 16:46:18 +00:00
Tom Deakin
288fabc0d1 [Kokkos] Use seperate build and link in Kokkos Makefile 
Fixes #40.
The Kokkos programming model examples now recommend using seperate
build and link stages.
 2018-02-07 15:34:19 +00:00
Tom Deakin
72ca26ac94 Add better link to SC17 publication in README 2018-02-07 15:22:04 +00:00
Tom Deakin
4d3f1ff0b2 Add new reference to README 2018-02-07 15:17:23 +00:00
Tom Deakin
a11cb21bac Add new reference to README 2018-02-07 15:15:30 +00:00
Tom Deakin
73f122089d [OpenMP 4.5] Remove superfluous map clauses 
Fixes #41.
OpenMP 4.5 does not require the map clauses on the target region
if the data has been previously defined using unstructured data
enter/exit clauses. Removing this clauses works fine with the
Clang compiler, however we noticed issues with the Cray compiler.
The issue is that the Cray compiler does not block the target
region "kernel calls" and so the timing is incorrect. This was
not noticed before due to the presence of the map clauses.
For now, we have had to add an update from clause of a scalar
value to ensure that the kenel blocks. It is hoped that we can
remove this in due course. But in the vein of showing how the
models work we want to keep the minimum required correct code
(which is without the map clause) but need the code to also
work correctly.
 2018-02-07 15:05:06 +00:00
Tom Deakin
cfb89018f6 Update README with new Kokkos building instructions 2018-02-07 14:34:22 +00:00