Back to bug 1871395
| Who | When | What | Removed | Added |
|---|---|---|---|---|
| Red Hat Bugzilla | 2020-08-23 02:45:19 UTC | Pool ID | sst_platform_tools_rhel_8 | |
| Carlos O'Donell | 2020-08-25 20:15:37 UTC | Assignee | glibc-bugzilla | pfrankli |
| Carlos O'Donell | 2020-09-08 20:40:45 UTC | Blocks | 1877115 | |
| Carlos O'Donell | 2020-09-10 04:50:08 UTC | Doc Type | If docs needed, set a value | Enhancement |
| Carlos O'Donell | 2020-09-10 04:59:31 UTC | Status | NEW | ASSIGNED |
| Sergey Kolosov | 2020-09-17 07:16:25 UTC | CC | skolosov | |
| Martin Cermak | 2020-10-01 14:54:59 UTC | CC | mcermak | |
| Patsy Griffin | 2020-10-04 16:19:23 UTC | Doc Text | Feature: Performance improvements for IBM zSeries. Reason: Instructions (pfd) intended to improve copies greater than or equal to 64kb were being used for smaller copies, resulting in slower performance for smaller memcpy functions. In the case of memset, the 256b-mvc was relying on the result of the previous 256b-mvc rather than just a stc which was counterproductive. Result: For memcpy, less than 64kb we now use a loop rather than the pfd instructions. For memset, we replaced the dependency on 256b-mvc with a stc instruction. |
|
| Patsy Griffin | 2020-10-04 16:20:31 UTC | Status | ASSIGNED | MODIFIED |
| Fixed In Version | glibc-2.28-131.el8 | |||
| Florian Weimer | 2020-10-05 08:11:56 UTC | CC | sipoyare | |
| Patsy Griffin | 2020-10-05 15:09:24 UTC | Doc Text | Feature: Performance improvements for IBM zSeries. Reason: Instructions (pfd) intended to improve copies greater than or equal to 64kb were being used for smaller copies, resulting in slower performance for smaller memcpy functions. In the case of memset, the 256b-mvc was relying on the result of the previous 256b-mvc rather than just a stc which was counterproductive. Result: For memcpy, less than 64kb we now use a loop rather than the pfd instructions. For memset, we replaced the dependency on 256b-mvc with a stc instruction. | Feature: Performance improvements for IBM zSeries. Reason: Applications working with in-memory data could see less than acceptable performance for small pieces of data (< 64KiB)." Result: The core library implementation for the memcpy and memset APIs were adjusted to accelerate small data copies (< 64KiB) and likewise larger data copies were adjusted. Applications working with in-memory data should see significantly improved preformance across a wide variety of workloads |
| Red Hat One Jira (issues.redhat.com) | 2020-10-14 13:52:50 UTC | Link ID | Red Hat Issue Tracker - Private RHELPLAN-51913 | |
| Valentina Mukhamedzhanova | 2020-10-14 15:51:06 UTC | CC | vmukhame | |
| Martin Cermak | 2020-10-16 08:21:08 UTC | QA Contact | qe-baseos-tools-bugs | skolosov |
| errata-xmlrpc | 2020-10-27 07:34:38 UTC | Status | MODIFIED | ON_QA |
| Petr Kovar | 2020-11-03 12:33:31 UTC | Docs Contact | zzoubkov | |
| Sergey Kolosov | 2020-11-06 20:12:59 UTC | Status | ON_QA | VERIFIED |
| Zuzana Zoubkova | 2020-11-26 13:47:24 UTC | Flags | needinfo?(pfrankli) | |
| Patsy Griffin | 2020-11-26 13:56:00 UTC | Flags | needinfo?(pfrankli) | needinfo?(codonell) |
| Florian Weimer | 2020-11-26 14:07:58 UTC | Summary | glibc: Improve IBM zSeries (s390x) Performance | glibc: Improve IBM Z (s390x) Performance |
| Carlos O'Donell | 2020-11-27 18:06:53 UTC | Flags | needinfo?(codonell) | |
| Carlos O'Donell | 2020-11-27 18:07:18 UTC | Keywords | FutureFeature | |
| Type | Bug | Enhancement | ||
| Zuzana Zoubkova | 2020-11-30 10:26:43 UTC | Doc Text | Feature: Performance improvements for IBM zSeries. Reason: Applications working with in-memory data could see less than acceptable performance for small pieces of data (< 64KiB)." Result: The core library implementation for the memcpy and memset APIs were adjusted to accelerate small data copies (< 64KiB) and likewise larger data copies were adjusted. Applications working with in-memory data should see significantly improved preformance across a wide variety of workloads | .Optimized performance of `memcpy` and `memset` on IBM Z With this enhancement, the core library implementation for the `memcpy` and `memset` APIs were adjusted to accelerate both small (< 64KiB) and larger data copies on IBM Z processors. As a result, applications working with in-memory data now benefit from significantly improved performance across a wide variety of workloads. |
| Matt Newsome | 2021-03-18 11:13:59 UTC | Keywords | Triaged | |
| errata-xmlrpc | 2021-05-18 00:31:04 UTC | Status | VERIFIED | RELEASE_PENDING |
| errata-xmlrpc | 2021-05-18 14:36:39 UTC | Status | RELEASE_PENDING | CLOSED |
| Resolution | --- | ERRATA | ||
| Last Closed | 2021-05-18 14:36:39 UTC | |||
| Pavel Najman | 2021-09-17 12:24:26 UTC | Pool ID | sst_platform_tools_rhel_8 | sst_pt_pcp_rhel_8 |
| Pavel Najman | 2021-09-17 12:34:06 UTC | Pool ID | sst_pt_pcp_rhel_8 | sst_pt_gcc_glibc_rhel_8 |
| Mark O'Brien | 2023-07-18 14:30:35 UTC | Pool ID | sst_pt_glibc_rhel_8 | sst_pt_libraries_rhel_8 |
Back to bug 1871395