pool/openucx
SHA256
2
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Accepting request 811684 from home:NMoreyChaisemartin:branches:science:HPC

Browse Source 
- Update to v1.8.0
  - Features:
    - Improved detection for DEVX support
    - Improved TCP scalability
    - Added support for ROCM to perftest
    - Added support for different source and target memory types to perftest
    - Added optimized memcpy for ROCM devices
    - Added hardware tag-matching for CUDA buffers
    - Added support for CUDA and ROCM managed memories
    - Added support for client/server disconnect protocol over rdma connection manager
    - Added support for striding receive queue for hardware tag-matching
    - Added XPMEM-based rendezvous protocol for shared memory
    - Added support shared memory communication between containers on same machine
    - Added support for multi-threaded RDMA memory registration for large regions
    - Added new test cases to Azure CI
    - Added support for multiple listening transports
    - Added UCT socket-based connection manager transport
    - Updated API for UCT component management
    - Added API to retrieve the listening port
    - Added UCP active message API
    - Removed deprecated API for querying UCT memory domains
    - Refactored server/client examples
    - Added support for dlopen interception in UCM
    - Added support for PCIe atomics
    - Updated Java API: added support for most of UCP layer operations
    - Updated support for Mellanox DevX API
    - Added multiple UCT/TCP transport performance optimizations
    - Optimized memcpy() for Intel platforms
    - Added protection from non-UCX socket based app connections
    - Improved search time for PKEY object
    - Enabled gtest over IPv6 interfaces
    - Updated Mellanox and Bull device IDs
    - Added support for CUDA_VISIBLE_DEVICES
    - Increased limits for CUDA IPC registration
  - Bugfixes:
    - Multiple fixes in JUCX
    - Fixes in UCP thread safety
    - Fixes for most recent versions GCC, PGI, and ICC
    - Fixes for CPU affinity on Azure instances
    - Fixes in XPMEM support on PPC64
    - Performance fixes in CUDA IPC
    - Fixes in RDMA CM flows
    - Multiple fixes in TCP transport
    - Multiple fixes in documentation
    - Fixes in transport lane selection logic
    - Fixes in Java jar build
    - Fixes in socket connection manager for Nvidia DGX-2 platform
    - Multiple fixes in UCP, UCT, UCM libraries
    - Multiple fixes for BSD and Mac OS systems
    - Fixes for Clang compiler
    - Fix CPU optimization configuration options
    - Fix JUCX build on GPU nodes
    - Fix in Azure release pipeline flow
    - Fix in CUDA memory hooks management
    - Fix in GPU memory peer direct gtest
    - Fix in TCP connection establishment flow
    - Fix in GPU IPC check
    - Fix in CUDA Jenkins test flow
    - Multiple fixes in CUDA IPC flow
    - Fix adding missing header files
    - Fix to prevent failures in presence of VPN enabled Ethernet interfaces
- Refresh openucx-s390x-support.patch against new version

OBS-URL: https://build.opensuse.org/request/show/811684
OBS-URL: https://build.opensuse.org/package/show/science:HPC/openucx?expand=0&rev=37
This commit is contained in:
Jan Engelhardt 2020-06-05 08:02:58 +00:00 committed by Git OBS Bridge
parent f5ac91c2bc
commit 9033dd246f
5 changed files with 253 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

192
openucx-s390x-support.patch
View File

@ -1,4 +1,4 @@
commit 7efd75794d17351fbcfdd2759fc9abf22af0d631
commit 02e9e9daa1adf26573bfb0d35c26cca46fb0e777
Author: Nicolas Morey-Chaisemartin <nmoreychaisemartin@suse.com>
Date: Thu Aug 9 07:41:24 2018 +0200
@ -32,6 +32,20 @@ index 9c7c820d9fff..8297fc7e6ec2 100644
AS_IF([test "x$bistro_hooks_happy" = "xyes"],
[AC_DEFINE([UCM_BISTRO_HOOKS], [1], [Enable BISTRO hooks])],
diff --git src/tools/info/sys_info.c src/tools/info/sys_info.c
index 435e5a6feb8b..9b3beed68ea4 100644
--- src/tools/info/sys_info.c
+++ src/tools/info/sys_info.c
@@ -37,7 +37,8 @@ static const char* cpu_vendor_names[] = {
[UCS_CPU_VENDOR_INTEL] = "Intel",
[UCS_CPU_VENDOR_AMD] = "AMD",
[UCS_CPU_VENDOR_GENERIC_ARM] = "Generic ARM",
- [UCS_CPU_VENDOR_GENERIC_PPC] = "Generic PPC"
+ [UCS_CPU_VENDOR_GENERIC_PPC] = "Generic PPC",
+ [UCS_CPU_VENDOR_GENERIC_IBM] = "Generic IBM"
};
static double measure_memcpy_bandwidth(size_t size)
diff --git src/ucm/Makefile.am src/ucm/Makefile.am
index e53a30a46916..21bce848045d 100644
--- src/ucm/Makefile.am
@ -79,10 +93,10 @@ index 000000000000..334c0474e8b6
+
+#endif
diff --git src/ucm/mmap/install.c src/ucm/mmap/install.c
index c58afb37e029..a9cfd5865278 100644
index 6824a6247bef..81d0375a4132 100644
--- src/ucm/mmap/install.c
+++ src/ucm/mmap/install.c
@@ -254,7 +254,11 @@ static ucs_status_t ucs_mmap_install_reloc(int events)
@@ -258,7 +258,11 @@ static ucs_status_t ucs_mmap_install_reloc(int events)
status = ucm_reloc_modify(&entry->patch);
} else {
ucs_assert(ucm_mmap_hook_mode() == UCM_MMAP_HOOK_BISTRO);
@ -95,10 +109,18 @@ index c58afb37e029..a9cfd5865278 100644
if (status != UCS_OK) {
ucm_warn("failed to install %s hook for '%s'",
diff --git src/ucs/Makefile.am src/ucs/Makefile.am
index 7e8153a4fd07..d41842711a5e 100644
index 2bd0a8d50c4b..4a60658f34d8 100644
--- src/ucs/Makefile.am
+++ src/ucs/Makefile.am
@@ -56,6 +56,8 @@ noinst_HEADERS = \
@@ -58,6 +58,7 @@ nobase_dist_libucs_la_HEADERS = \
arch/x86_64/global_opts.h \
arch/aarch64/global_opts.h \
arch/ppc64/global_opts.h \
+ arch/s390x/global_opts.h \
arch/global_opts.h
noinst_HEADERS = \
@@ -67,6 +68,8 @@ noinst_HEADERS = \
arch/generic/cpu.h \
arch/ppc64/bitops.h \
arch/ppc64/cpu.h \
@ -107,8 +129,16 @@ index 7e8153a4fd07..d41842711a5e 100644
arch/x86_64/atomic.h \
arch/x86_64/bitops.h \
arch/x86_64/cpu.h \
@@ -108,6 +111,7 @@ libucs_la_SOURCES = \
algorithm/qsort_r.c \
arch/aarch64/cpu.c \
arch/aarch64/global_opts.c \
+ arch/s390x/global_opts.c \
arch/ppc64/timebase.c \
arch/ppc64/global_opts.c \
arch/x86_64/cpu.c \
diff --git src/ucs/arch/atomic.h src/ucs/arch/atomic.h
index 0caea9b1f3ba..d9afa780bbc5 100644
index 99e53ca5d0f7..dfa83b757bb0 100644
--- src/ucs/arch/atomic.h
+++ src/ucs/arch/atomic.h
@@ -15,6 +15,8 @@
@ -121,7 +151,7 @@ index 0caea9b1f3ba..d9afa780bbc5 100644
# error "Unsupported architecture"
#endif
diff --git src/ucs/arch/bitops.h src/ucs/arch/bitops.h
index af7bb93392d4..6639045ae0b6 100644
index 91d4573c1faf..8b092b023639 100644
--- src/ucs/arch/bitops.h
+++ src/ucs/arch/bitops.h
@@ -14,6 +14,8 @@
@ -133,11 +163,46 @@ index af7bb93392d4..6639045ae0b6 100644
#else
# error "Unsupported architecture"
#endif
diff --git src/ucs/arch/cpu.c src/ucs/arch/cpu.c
index e81f540a899d..40b89907664a 100644
--- src/ucs/arch/cpu.c
+++ src/ucs/arch/cpu.c
@@ -57,7 +57,11 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = {
[UCS_CPU_VENDOR_GENERIC_PPC] = {
.min = UCS_MEMUNITS_INF,
.max = UCS_MEMUNITS_INF
- }
+ },
+ [UCS_CPU_VENDOR_GENERIC_IBM] = {
+ .min = UCS_MEMUNITS_INF,
+ .max = UCS_MEMUNITS_INF
+ },
};
const size_t ucs_cpu_est_bcopy_bw[UCS_CPU_VENDOR_LAST] = {
@@ -65,7 +69,8 @@ const size_t ucs_cpu_est_bcopy_bw[UCS_CPU_VENDOR_LAST] = {
[UCS_CPU_VENDOR_INTEL] = 5800 * UCS_MBYTE,
[UCS_CPU_VENDOR_AMD] = 5008 * UCS_MBYTE,
[UCS_CPU_VENDOR_GENERIC_ARM] = 5800 * UCS_MBYTE,
- [UCS_CPU_VENDOR_GENERIC_PPC] = 5800 * UCS_MBYTE
+ [UCS_CPU_VENDOR_GENERIC_PPC] = 5800 * UCS_MBYTE,
+ [UCS_CPU_VENDOR_GENERIC_IBM] = 5800 * UCS_MBYTE,
};
static void ucs_sysfs_get_cache_size()
diff --git src/ucs/arch/cpu.h src/ucs/arch/cpu.h
index 58a83825ee4a..a30456ba441d 100644
index c1f1cc826b6b..e9d5c5b32ca3 100644
--- src/ucs/arch/cpu.h
+++ src/ucs/arch/cpu.h
@@ -59,6 +59,8 @@ typedef enum ucs_cpu_flag {
@@ -58,6 +58,7 @@ typedef enum ucs_cpu_vendor {
UCS_CPU_VENDOR_AMD,
UCS_CPU_VENDOR_GENERIC_ARM,
UCS_CPU_VENDOR_GENERIC_PPC,
+ UCS_CPU_VENDOR_GENERIC_IBM,
UCS_CPU_VENDOR_LAST
} ucs_cpu_vendor_t;
@@ -91,6 +92,8 @@ typedef struct ucs_cpu_builtin_memcpy {
# include "ppc64/cpu.h"
#elif defined(__aarch64__)
# include "aarch64/cpu.h"
@ -146,6 +211,19 @@ index 58a83825ee4a..a30456ba441d 100644
#else
# error "Unsupported architecture"
#endif
diff --git src/ucs/arch/global_opts.h src/ucs/arch/global_opts.h
index 8786f130290a..0d251fb91868 100644
--- src/ucs/arch/global_opts.h
+++ src/ucs/arch/global_opts.h
@@ -15,6 +15,8 @@
# include "ppc64/global_opts.h"
#elif defined(__aarch64__)
# include "aarch64/global_opts.h"
+#elif defined(__s390x__)
+# include "s390x/global_opts.h"
#else
# error "Unsupported architecture"
#endif
diff --git src/ucs/arch/s390x/bitops.h src/ucs/arch/s390x/bitops.h
new file mode 100644
index 000000000000..39ad125107e9
@ -186,10 +264,10 @@ index 000000000000..39ad125107e9
+#endif
diff --git src/ucs/arch/s390x/cpu.h src/ucs/arch/s390x/cpu.h
new file mode 100644
index 000000000000..b8ab713d6e21
index 000000000000..4f0a87006118
--- /dev/null
+++ src/ucs/arch/s390x/cpu.h
@@ -0,0 +1,53 @@
@@ -0,0 +1,84 @@
+/**
+* Copyright (C) Mellanox Technologies Ltd. 2001-2013. ALL RIGHTS RESERVED.
+* Copyright (C) ARM Ltd. 2016-2017. ALL RIGHTS RESERVED.
@ -204,10 +282,14 @@ index 000000000000..b8ab713d6e21
+#include <ucs/sys/compiler.h>
+#include <ucs/arch/generic/cpu.h>
+#include <stdint.h>
+#include <string.h>
+#include <ucs/type/status.h>
+
+
+#define UCS_ARCH_CACHE_LINE_SIZE 256
+
+BEGIN_C_DECLS
+
+/* Assume the worst - weak memory ordering */
+#define ucs_memory_bus_fence() asm volatile (""::: "memory")
+#define ucs_memory_bus_store_fence() ucs_memory_bus_fence()
@ -233,6 +315,11 @@ index 000000000000..b8ab713d6e21
+ return UCS_CPU_MODEL_UNKNOWN;
+}
+
+static inline ucs_cpu_vendor_t ucs_arch_get_cpu_vendor()
+{
+ return UCS_CPU_VENDOR_GENERIC_IBM;
+}
+
+static inline int ucs_arch_get_cpu_flag()
+{
+ return UCS_CPU_FLAG_UNKNOWN;
@ -242,4 +329,87 @@ index 000000000000..b8ab713d6e21
+
+#define ucs_arch_wait_mem ucs_arch_generic_wait_mem
+
+static inline void ucs_cpu_init()
+{
+}
+
+static inline void *ucs_memcpy_relaxed(void *dst, const void *src, size_t len)
+{
+ return memcpy(dst, src, len);
+}
+
+static UCS_F_ALWAYS_INLINE void
+ucs_memcpy_nontemporal(void *dst, const void *src, size_t len)
+{
+ memcpy(dst, src, len);
+}
+
+static inline ucs_status_t ucs_arch_get_cache_size(size_t *cache_sizes)
+{
+ return UCS_ERR_UNSUPPORTED;
+}
+
+END_C_DECLS
+
+#endif
diff --git src/ucs/arch/s390x/global_opts.c src/ucs/arch/s390x/global_opts.c
new file mode 100644
index 000000000000..4fa0c74034a7
--- /dev/null
+++ src/ucs/arch/s390x/global_opts.c
@@ -0,0 +1,24 @@
+/**
+* Copyright (C) Mellanox Technologies Ltd. 2019. ALL RIGHTS RESERVED.
+*
+* See file LICENSE for terms.
+*/
+
+#if defined(__s390x__)
+
+#ifdef HAVE_CONFIG_H
+# include "config.h"
+#endif
+
+#include <ucs/arch/global_opts.h>
+#include <ucs/config/parser.h>
+
+ucs_config_field_t ucs_arch_global_opts_table[] = {
+ {NULL}
+};
+
+void ucs_arch_print_memcpy_limits(ucs_arch_global_opts_t *config)
+{
+}
+
+#endif
diff --git src/ucs/arch/s390x/global_opts.h src/ucs/arch/s390x/global_opts.h
new file mode 100644
index 000000000000..225e4e5e896a
--- /dev/null
+++ src/ucs/arch/s390x/global_opts.h
@@ -0,0 +1,25 @@
+/**
+* Copyright (C) Mellanox Technologies Ltd. 2019. ALL RIGHTS RESERVED.
+*
+* See file LICENSE for terms.
+*/
+
+
+#ifndef UCS_PPC64_GLOBAL_OPTS_H_
+#define UCS_PPC64_GLOBAL_OPTS_H_
+
+#include <ucs/sys/compiler_def.h>
+
+BEGIN_C_DECLS
+
+#define UCS_ARCH_GLOBAL_OPTS_INITALIZER {}
+
+/* built-in memcpy config */
+typedef struct ucs_arch_global_opts {
+ char dummy;
+} ucs_arch_global_opts_t;
+
+END_C_DECLS
+
+#endif
+

66
openucx.changes
View File

@ -1,3 +1,69 @@
-------------------------------------------------------------------
Thu Jun 4 08:18:26 UTC 2020 - Nicolas Morey-Chaisemartin <nmoreychaisemartin@suse.com>
- Update to v1.8.0
- Features:
- Improved detection for DEVX support
- Improved TCP scalability
- Added support for ROCM to perftest
- Added support for different source and target memory types to perftest
- Added optimized memcpy for ROCM devices
- Added hardware tag-matching for CUDA buffers
- Added support for CUDA and ROCM managed memories
- Added support for client/server disconnect protocol over rdma connection manager
- Added support for striding receive queue for hardware tag-matching
- Added XPMEM-based rendezvous protocol for shared memory
- Added support shared memory communication between containers on same machine
- Added support for multi-threaded RDMA memory registration for large regions
- Added new test cases to Azure CI
- Added support for multiple listening transports
- Added UCT socket-based connection manager transport
- Updated API for UCT component management
- Added API to retrieve the listening port
- Added UCP active message API
- Removed deprecated API for querying UCT memory domains
- Refactored server/client examples
- Added support for dlopen interception in UCM
- Added support for PCIe atomics
- Updated Java API: added support for most of UCP layer operations
- Updated support for Mellanox DevX API
- Added multiple UCT/TCP transport performance optimizations
- Optimized memcpy() for Intel platforms
- Added protection from non-UCX socket based app connections
- Improved search time for PKEY object
- Enabled gtest over IPv6 interfaces
- Updated Mellanox and Bull device IDs
- Added support for CUDA_VISIBLE_DEVICES
- Increased limits for CUDA IPC registration
- Bugfixes:
- Multiple fixes in JUCX
- Fixes in UCP thread safety
- Fixes for most recent versions GCC, PGI, and ICC
- Fixes for CPU affinity on Azure instances
- Fixes in XPMEM support on PPC64
- Performance fixes in CUDA IPC
- Fixes in RDMA CM flows
- Multiple fixes in TCP transport
- Multiple fixes in documentation
- Fixes in transport lane selection logic
- Fixes in Java jar build
- Fixes in socket connection manager for Nvidia DGX-2 platform
- Multiple fixes in UCP, UCT, UCM libraries
- Multiple fixes for BSD and Mac OS systems
- Fixes for Clang compiler
- Fix CPU optimization configuration options
- Fix JUCX build on GPU nodes
- Fix in Azure release pipeline flow
- Fix in CUDA memory hooks management
- Fix in GPU memory peer direct gtest
- Fix in TCP connection establishment flow
- Fix in GPU IPC check
- Fix in CUDA Jenkins test flow
- Multiple fixes in CUDA IPC flow
- Fix adding missing header files
- Fix to prevent failures in presence of VPN enabled Ethernet interfaces
- Refresh openucx-s390x-support.patch against new version
-------------------------------------------------------------------
Fri Oct 4 08:11:49 UTC 2019 - Jan Engelhardt <jengelh@inai.de>

6
openucx.spec
View File

@ -1,7 +1,7 @@
#
# spec file for package openucx
#
# Copyright (c) 2019 SUSE LINUX GmbH, Nuernberg, Germany.
# Copyright (c) 2020 SUSE LLC
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
@ -20,9 +20,9 @@ Name: openucx
Summary: Unifieid Communication X
License: BSD-3-Clause
Group: Development/Libraries/C and C++
Version: 1.6.0
Version: 1.8.0
Release: 0
Url: http://openucx.org/
URL: http://openucx.org/
#Git-Clone: git://github.com/openucx/ucx
#Git-Web: https://github.com/openucx/ucx

3
ucx-1.6.0.tar.gz
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:360e885dd7f706a19b673035a3477397d100a02eb618371697c7f3ee4e143e2c
size 2078802

3
ucx-1.8.0.tar.gz Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e400f7aa5354971c8f5ac6b881dc2846143851df868088c37d432c076445628d
size 2352265