Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
one
TransferBench
Commits
5b380b89
Unverified
Commit
5b380b89
authored
Dec 16, 2024
by
Swati Rawat
Committed by
GitHub
Dec 16, 2024
Browse files
Merge pull request #154 from SwRaw/swraw/docs
updating metadata in the docs
parents
ea8107d6
06789888
Changes
7
Show whitespace changes
Inline
Side-by-side
Showing
7 changed files
with
16 additions
and
16 deletions
+16
-16
docs/api.rst
docs/api.rst
+0
-5
docs/doxygen/Doxyfile
docs/doxygen/Doxyfile
+2
-2
docs/how to/use-transferbench.rst
docs/how to/use-transferbench.rst
+1
-1
docs/index.rst
docs/index.rst
+1
-1
docs/install/install.rst
docs/install/install.rst
+1
-1
docs/reference/api.rst
docs/reference/api.rst
+1
-1
src/header/TransferBench.hpp
src/header/TransferBench.hpp
+10
-5
No files found.
docs/api.rst
deleted
100644 → 0
View file @
ea8107d6
-----
API
-----
.. doxygenindex::
docs/doxygen/Doxyfile
View file @
5b380b89
...
...
@@ -775,7 +775,7 @@ WARN_LOGFILE =
# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING
# Note: If this tag is empty the current directory is searched.
INPUT = ../../src/ \
INPUT = ../../src/
header
\
../../src/include
# This tag can be used to specify the character encoding of the source files
...
...
docs/how to/use-transferbench.rst
View file @
5b380b89
.. meta::
:description: TransferBench is a utility to benchmark simultaneous transfers between user-specified devices (CPUs or GPUs)
:keywords:
Using
TransferBench, TransferBench
Usag
e, TransferBench
How To, API, ROCm, documentation, HIP
:keywords:
TransferBench usage,
TransferBench
how to
, TransferBench
user guid
e, TransferBench
user manual
.. _using-transferbench:
...
...
docs/index.rst
View file @
5b380b89
.. meta::
:description: TransferBench is a utility to benchmark simultaneous transfers between user-specified devices (CPUs or GPUs)
:keywords:
TransferBench, API, ROCm, documentation, HIP
:keywords:
Benchmarking utility, Memory transfers, Device transfers
****************************
TransferBench documentation
...
...
docs/install/install.rst
View file @
5b380b89
.. meta::
:description: TransferBench is a utility to benchmark simultaneous transfers between user-specified devices (CPUs or GPUs)
:keywords: Build TransferBench, Install TransferBench
, API, ROCm, HIP
:keywords: Build TransferBench, Install TransferBench
.. _install-transferbench:
...
...
docs/reference/api.rst
View file @
5b380b89
.. meta::
:description: TransferBench is a utility to benchmark simultaneous transfers between user-specified devices (CPUs or GPUs)
:keywords: TransferBench
API
, TransferBench
library, documentation, HIP
:keywords: TransferBench
library
, TransferBench
functions, Transferbench API, Transferbench interface
.. _transferbench-api:
...
...
src/header/TransferBench.hpp
View file @
5b380b89
...
...
@@ -20,6 +20,7 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
*/
/// @cond
#pragma once
#include <cstring>
#include <future>
...
...
@@ -41,6 +42,7 @@ THE SOFTWARE.
#include <hsa/hsa.h>
#include <hsa/hsa_ext_amd.h>
#endif
/// @endcond
namespace
TransferBench
{
...
...
@@ -118,7 +120,7 @@ namespace TransferBench
*/
struct
Transfer
{
size_t
numBytes
=
(
1
<<
26
);
///<
#
of bytes to Transfer
size_t
numBytes
=
(
1
<<
26
);
///<
Number
of bytes to Transfer
vector
<
MemDevice
>
srcs
=
{};
///< List of source memory devices
vector
<
MemDevice
>
dsts
=
{};
///< List of destination memory devices
ExeDevice
exeDevice
=
{};
///< Executor to use
...
...
@@ -132,8 +134,8 @@ namespace TransferBench
*/
struct
GeneralOptions
{
int
numIterations
=
10
;
///<
#
of timed iterations to perform. If negative, run for -numIterations seconds instead
int
numSubIterations
=
1
;
///<
#
of sub-iterations per iteration
int
numIterations
=
10
;
///<
Number
of timed iterations to perform. If negative, run for -numIterations seconds instead
int
numSubIterations
=
1
;
///<
Number
of sub-iterations per iteration
int
numWarmups
=
3
;
///< Number of un-timed warmup iterations to perform
int
recordPerIteration
=
0
;
///< Record per-iteration timing information
int
useInteractive
=
0
;
///< Pause for user-input before starting transfer loop
...
...
@@ -459,6 +461,8 @@ namespace TransferBench
namespace
TransferBench
{
/// @cond
// Helper functions ('hidden' in anonymous namespace)
//========================================================================================
namespace
{
...
...
@@ -468,8 +472,8 @@ namespace {
int
constexpr
MAX_BLOCKSIZE
=
512
;
// Max threadblock size
int
constexpr
MAX_WAVEGROUPS
=
MAX_BLOCKSIZE
/
64
;
// Max wavegroups/warps
int
constexpr
MAX_UNROLL
=
8
;
// Max unroll factor
int
constexpr
MAX_SRCS
=
8
;
// Max
#
srcs per Transfer
int
constexpr
MAX_DSTS
=
8
;
// Max
#
dsts per Transfer
int
constexpr
MAX_SRCS
=
8
;
// Max
number of
srcs per Transfer
int
constexpr
MAX_DSTS
=
8
;
// Max
number of
dsts per Transfer
int
constexpr
MEMSET_CHAR
=
75
;
// Value to memset (char)
float
constexpr
MEMSET_VAL
=
13323083.0
f
;
// Value to memset (double)
...
...
@@ -2108,6 +2112,7 @@ namespace {
}
// End of anonymous namespace
//========================================================================================
/// @endcond
ErrResult
::
ErrResult
(
ErrType
err
)
:
errType
(
err
),
errMsg
(
""
)
{};
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment