rpm/openucx
SHA256
1
0
Fork 0
forked from pool/openucx
Code Pull Requests Activity
openucx/openucx-s390x-support.patch
Nicolas Morey-Chaisemartin 643404b991 Accepting request 921702 from home:NMoreyChaisemartin:branches:science:HPC 
- Update to v1.11.1 (jsc#SLE-19260)

  - Core:
    - Added support for UCX monitoring using virtual file system (VFS)/FUSE
    - Added support for applications with static CUDA runtime linking
    - Added support for a configuration file
    - Updated clang format configuration
  - UCP
    - Added rendezvous API for active messages
    - Added user-defined name to context, worker, and endpoint objects
    - Added flag to silence request leak check
    - Added API for endpoint performance evaluation
    - Added API - ucp_request_query
    - Added API - ucp_lib_query
    - Added bandwidth optimizations for new protocols multi-lane
    - Added support for multi-rail over lanes with BW ratio >= 1/4
    - Added support for tracking outstanding requests and aborting those in case of connection failure
    - Refactored keep-alive protocol
    - Added device id to wireup protocol
    - Added support up to 128 transport layer resources in UCP context
    - Added support CUDA memory allocations with ucp_mem_map
    - Increased UCP_WORKER_MAX_EP_CONFIG to 64
    - Adjusted memory type zcopy threshold when UCX_ZCOPY_THRESH set
    - Refactored wireup protocols, rendezvous, get, zcopy protocols
    - Added put zcopy multi-rail
    - Improved logging for new protocols
    - Added system topology information
    - Added new protocols for eager offload protocols
  - UCT
    - Extended connection establishment API

OBS-URL: https://build.opensuse.org/request/show/921702
OBS-URL: https://build.opensuse.org/package/show/science:HPC/openucx?expand=0&rev=46
2021-09-27 09:00:18 +00:00

431 lines
12 KiB
Diff
Raw Blame History

commit 71d28736870f46080b8187bf2ba64920c87dc7e4
Author: Nicolas Morey-Chaisemartin <nmoreychaisemartin@suse.com>
Date: Thu Aug 9 07:41:24 2018 +0200
openucx s390x support
Signed-off-by: Nicolas Morey-Chaisemartin <nmoreychaisemartin@suse.com>
diff --git config/m4/ucm.m4 config/m4/ucm.m4
index 1e229edc51f2..3f74fca02976 100644
--- config/m4/ucm.m4
+++ config/m4/ucm.m4
@@ -73,9 +73,20 @@ AC_CHECK_DECLS([SYS_ipc],
[ipc_hooks_happy=no],
[#include <sys/syscall.h>])
+
+SAVE_CFLAGS=$CFLAGS
+CFLAGS="$CLAGS -Isrc/"
+bistro_arch_happy=yes
+AC_CHECK_DECLS([ucm_bistro_patch],
+ [],
+ [bistro_arch_happy=no],
+ [#include <ucm/bistro/bistro.h>])
+CFLAGS=$SAVE_CFLAGS
+
AS_IF([test "x$mmap_hooks_happy" = "xyes"],
AS_IF([test "x$ipc_hooks_happy" = "xyes" -o "x$shm_hooks_happy" = "xyes"],
- [bistro_hooks_happy=yes]))
+ AS_IF([test "x$bistro_arch_happy" == "xyes"],
+ [bistro_hooks_happy=yes])))
AS_IF([test "x$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 7c355a264c2b..52efadec096c 100644
--- src/tools/info/sys_info.c
+++ src/tools/info/sys_info.c
@@ -44,7 +44,8 @@ static const char* cpu_vendor_names[] = {
[UCS_CPU_VENDOR_GENERIC_ARM] = "Generic ARM",
[UCS_CPU_VENDOR_GENERIC_PPC] = "Generic PPC",
[UCS_CPU_VENDOR_FUJITSU_ARM] = "Fujitsu ARM",
- [UCS_CPU_VENDOR_ZHAOXIN] = "Zhaoxin"
+ [UCS_CPU_VENDOR_ZHAOXIN] = "Zhaoxin",
+ [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 55784d0c31f4..a6003eda0333 100644
--- src/ucm/Makefile.am
+++ src/ucm/Makefile.am
@@ -31,7 +31,8 @@ noinst_HEADERS = \
bistro/bistro.h \
bistro/bistro_x86_64.h \
bistro/bistro_aarch64.h \
- bistro/bistro_ppc64.h
+ bistro/bistro_ppc64.h \
+ bistro/bistro_s390x.h
libucm_la_SOURCES = \
event/event.c \
diff --git src/ucm/bistro/bistro.h src/ucm/bistro/bistro.h
index 101000455e66..0ae947429796 100644
--- src/ucm/bistro/bistro.h
+++ src/ucm/bistro/bistro.h
@@ -20,6 +20,8 @@ typedef struct ucm_bistro_restore_point ucm_bistro_restore_point_t;
# include "bistro_aarch64.h"
#elif defined(__x86_64__)
# include "bistro_x86_64.h"
+#elif defined(__s390x__)
+# include "bistro_s390x.h"
#else
# error "Unsupported architecture"
#endif
diff --git src/ucm/bistro/bistro_s390x.h src/ucm/bistro/bistro_s390x.h
new file mode 100644
index 000000000000..c0f427f4984a
--- /dev/null
+++ src/ucm/bistro/bistro_s390x.h
@@ -0,0 +1,18 @@
+#ifndef UCM_BISTRO_BISTRO_S390X_H_
+#define UCM_BISTRO_BISTRO_S390X_H_
+
+#include <stdint.h>
+
+#include <ucs/type/status.h>
+#include <ucs/sys/compiler_def.h>
+
+#define UCM_BISTRO_PROLOGUE
+#define UCM_BISTRO_EPILOGUE
+
+static inline ucs_status_t ucm_bistro_patch(void *func_ptr, void *hook, const char *symbol,
+ void **orig_func_p,
+ ucm_bistro_restore_point_t **rp){
+ return UCS_ERR_UNSUPPORTED;
+}
+
+#endif
diff --git src/ucs/Makefile.am src/ucs/Makefile.am
index 8cc77e87da3f..2fbb53188a58 100644
--- src/ucs/Makefile.am
+++ src/ucs/Makefile.am
@@ -21,6 +21,7 @@ libucs_la_LIBADD = $(LIBM) $(top_builddir)/src/ucm/libucm.la
nobase_dist_libucs_la_HEADERS = \
arch/aarch64/bitops.h \
arch/ppc64/bitops.h \
+ arch/s390x/bitops.h \
arch/x86_64/bitops.h \
arch/bitops.h \
algorithm/crc.h \
@@ -77,12 +78,14 @@ nobase_dist_libucs_la_HEADERS = \
arch/aarch64/global_opts.h \
arch/generic/atomic.h \
arch/ppc64/global_opts.h \
+ arch/s390x/global_opts.h \
arch/global_opts.h
noinst_HEADERS = \
arch/aarch64/cpu.h \
arch/generic/cpu.h \
arch/ppc64/cpu.h \
+ arch/s390x/cpu.h \
arch/x86_64/cpu.h \
arch/cpu.h \
datastruct/arbiter.h \
@@ -127,6 +130,7 @@ 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 6a8551f592e1..e3a9f4641383 100644
--- src/ucs/arch/atomic.h
+++ src/ucs/arch/atomic.h
@@ -15,6 +15,8 @@
# include "generic/atomic.h"
#elif defined(__aarch64__)
# include "generic/atomic.h"
+#elif defined(__s390x__)
+# include "generic/atomic.h"
#else
# error "Unsupported architecture"
#endif
diff --git src/ucs/arch/bitops.h src/ucs/arch/bitops.h
index a890cd255295..badc12419b5b 100644
--- src/ucs/arch/bitops.h
+++ src/ucs/arch/bitops.h
@@ -20,6 +20,8 @@ BEGIN_C_DECLS
# include "ppc64/bitops.h"
#elif defined(__aarch64__)
# include "aarch64/bitops.h"
+#elif defined(__s390x__)
+# include "s390x/bitops.h"
#else
# error "Unsupported architecture"
#endif
diff --git src/ucs/arch/cpu.c src/ucs/arch/cpu.c
index 210a49c8e717..4018392ebed3 100644
--- src/ucs/arch/cpu.c
+++ src/ucs/arch/cpu.c
@@ -61,6 +61,10 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = {
.min = UCS_MEMUNITS_INF,
.max = UCS_MEMUNITS_INF
},
+ [UCS_CPU_VENDOR_GENERIC_IBM] = {
+ .min = UCS_MEMUNITS_INF,
+ .max = UCS_MEMUNITS_INF
+ },
[UCS_CPU_VENDOR_FUJITSU_ARM] = {
.min = UCS_MEMUNITS_INF,
.max = UCS_MEMUNITS_INF
@@ -77,6 +81,7 @@ const size_t ucs_cpu_est_bcopy_bw[UCS_CPU_VENDOR_LAST] = {
[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_IBM] = 5800 * UCS_MBYTE,
[UCS_CPU_VENDOR_FUJITSU_ARM] = 5800 * UCS_MBYTE
};
diff --git src/ucs/arch/cpu.h src/ucs/arch/cpu.h
index e06f6b95ebb1..15f3198976a9 100644
--- src/ucs/arch/cpu.h
+++ src/ucs/arch/cpu.h
@@ -62,6 +62,7 @@ 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_FUJITSU_ARM,
UCS_CPU_VENDOR_ZHAOXIN,
UCS_CPU_VENDOR_LAST
@@ -97,6 +98,8 @@ typedef struct ucs_cpu_builtin_memcpy {
# include "ppc64/cpu.h"
#elif defined(__aarch64__)
# include "aarch64/cpu.h"
+#elif defined(__s390x__)
+# include "s390x/cpu.h"
#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
--- /dev/null
+++ src/ucs/arch/s390x/bitops.h
@@ -0,0 +1,32 @@
+/**
+* Copyright (C) Mellanox Technologies Ltd. 2001-2015. ALL RIGHTS RESERVED.
+*
+* See file LICENSE for terms.
+*/
+
+#ifndef UCS_S390X_BITOPS_H_
+#define UCS_S390X_BITOPS_H_
+
+#include <stdint.h>
+
+
+static inline unsigned __ucs_ilog2_u32(uint32_t n)
+{
+ if (!n)
+ return 0;
+ return 31 - __builtin_clz(n);
+}
+
+static inline unsigned __ucs_ilog2_u64(uint64_t n)
+{
+ if (!n)
+ return 0;
+ return 63 - __builtin_clz(n);
+}
+
+static inline unsigned ucs_ffs64(uint64_t n)
+{
+ return __ucs_ilog2_u64(n & -n);
+}
+
+#endif
diff --git src/ucs/arch/s390x/cpu.h src/ucs/arch/s390x/cpu.h
new file mode 100644
index 000000000000..4f0a87006118
--- /dev/null
+++ src/ucs/arch/s390x/cpu.h
@@ -0,0 +1,84 @@
+/**
+* Copyright (C) Mellanox Technologies Ltd. 2001-2013. ALL RIGHTS RESERVED.
+* Copyright (C) ARM Ltd. 2016-2017. ALL RIGHTS RESERVED.
+*
+* See file LICENSE for terms.
+*/
+
+
+#ifndef UCS_S390X_CPU_H_
+#define UCS_S390X_CPU_H_
+
+#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()
+#define ucs_memory_bus_load_fence() ucs_memory_bus_fence()
+#define ucs_memory_bus_wc_flush() ucs_memory_bus_fence()
+#define ucs_memory_cpu_fence() ucs_memory_bus_fence()
+#define ucs_memory_cpu_store_fence() ucs_memory_bus_fence()
+#define ucs_memory_cpu_load_fence() ucs_memory_bus_fence()
+#define ucs_memory_cpu_wc_fence() ucs_memory_bus_fence()
+
+
+static inline uint64_t ucs_arch_read_hres_clock()
+{
+ unsigned long clk;
+ asm volatile("stck %0" : "=Q" (clk) : : "cc");
+ return clk >> 2;
+}
+#define ucs_arch_get_clocks_per_sec ucs_arch_generic_get_clocks_per_sec
+
+
+static inline ucs_cpu_model_t ucs_arch_get_cpu_model()
+{
+ 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;
+}
+
+double ucs_arch_get_clocks_per_sec();
+
+#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
+
diff --git src/ucs/sys/sys.c src/ucs/sys/sys.c
index 59836aaa51c2..3975db7f6be3 100644
--- src/ucs/sys/sys.c
+++ src/ucs/sys/sys.c
@@ -1223,8 +1223,19 @@ void *ucs_sys_realloc(void *old_ptr, size_t old_length, size_t new_length)
if (old_ptr == NULL) {
/* Note: Must pass the 0 offset as "long", otherwise it will be
* partially undefined when converted to syscall arguments */
+#if defined(__s390x__)
+ long int _args[6] = {
+ (long int) NULL,
+ (long int) new_length,
+ (long int) PROT_READ|PROT_WRITE,
+ (long int) MAP_PRIVATE|MAP_ANONYMOUS,
+ (long int) -1,
+ (long int) 0ul};
+ ptr = (void*)syscall(__NR_mmap, _args);
+#else
ptr = (void*)syscall(__NR_mmap, NULL, new_length, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0ul);
+#endif
if (ptr == MAP_FAILED) {
ucs_log_fatal_error("mmap(NULL, %zu, READ|WRITE, PRIVATE|ANON) failed: %m",
new_length);
View Git Blame Copy Permalink