Rebase to 4.0 update 4; add .pc files

- Resolves: #825402
2012-06-07 21:51:18 +02:00 · 2012-06-07 21:51:18 +02:00 · 657e0b6918
commit 657e0b6918
parent 89710d5275
8 changed files with 1291 additions and 1133 deletions
--- a/.gitignore
+++ b/.gitignore
@ -6,3 +6,4 @@ Getting_Started.pdf
 /Design_Patterns.pdf
 tbb*/
 /tbb40_20110809oss_src.tgz
+/tbb40_20120408oss_src.tgz
--- a/CHANGES.txt
+++ b/CHANGES.txt
@ -1,26 +1,143 @@
+TBB 4.0 Update 4
+
+Changes (w.r.t. TBB 4.0 Update 3):
+
+- The TBB memory allocator transparently supports large pages on Linux.
+- A new flow_graph example, logic_sim, was added.
+- Support for DirectX* 9 was added to GUI examples.
+
+Community Preview Features:
+
+- Added: aggregator, a new concurrency control mechanism.
+
+Bugs fixed:
+
+- The abort operation on concurrent_bounded_queue now leaves the queue
+    in a reusable state. If a bad_alloc or bad_last_alloc exception is
+    thrown while the queue is recovering from an abort, that exception
+    will be reported instead of user_abort on the thread on which it
+    occurred, and the queue will not be reusable.
+- Steal limiting heuristic fixed to avoid premature stealing disabling
+    when large amount of __thread data is allocated on thread stack.
+- Fixed a low-probability leak of arenas in the task scheduler.
+- In STL-compatible allocator classes, the method construct() was fixed
+    to comply with C++11 requirements.
+- Fixed a bug that prevented creation of fixed-size memory pools
+    smaller than 2M.
+- Significantly reduced the amount of warnings from various compilers.
+
+Open-source contributions integrated:
+
+- Multiple improvements by Raf Schietekat.
+- Basic support for Clang on Mac OS X* by Blas Rodriguez Somoza.
+- Fixes for warnings and corner-case bugs by Blas Rodriguez Somoza
+    and Edward Lam.
+
+------------------------------------------------------------------------
+TBB 4.0 Update 3
+
+Changes (w.r.t. TBB 4.0 Update 2):
+
+- Modifications to the low-level API for memory pools:
+    added support for aligned allocations;
+    pool policies reworked to allow backward-compatible extensions;
+    added a policy to not return memory space till destruction;
+    pool_reset() does not return memory space anymore.
+- Class tbb::flow::graph_iterator added to iterate over all nodes
+    registered with a graph instance.
+- multioutput_function_node has been renamed multifunction_node.
+    multifunction_node and split_node are now fully-supported features.
+- For the tagged join node, the policy for try_put of an item with
+    already existing tag has been defined: the item will be rejected.
+- Matching the behavior on Windows, on other platforms the optional
+    shared libraries (libtbbmalloc, libirml) now are also searched
+    only in the directory where libtbb is located.
+- The platform isolation layer based on GCC built-ins is extended.
+
+Backward-incompatible API changes:
+
+- a graph reference parameter is now required to be passed to the
+    constructors of the following flow graph nodes: overwrite_node, 
+    write_once_node, broadcast_node, and the CPF or_node.
+- the following tbb::flow node methods and typedefs have been renamed:
+       Old                             New
+    join_node and or_node:
+       inputs()                 ->     input_ports()
+       input_ports_tuple_type   ->     input_ports_type
+    multifunction_node and split_node:
+       ports_type               ->     output_ports_type
+
+Bugs fixed:
+
+- Not all logical processors were utilized on systems with more than
+    64 cores split by Windows into several processor groups.
+
+------------------------------------------------------------------------
+TBB 4.0 Update 2 commercial-aligned release
+
+Changes (w.r.t. TBB 4.0 Update 1 commercial-aligned release):
+
+- concurrent_bounded_queue now has an abort() operation that releases 
+    threads involved in pending push or pop operations. The released 
+    threads will receive a tbb::user_abort exception.
+- Added Community Preview Feature:  concurrent_lru_cache container, 
+    a concurrent implementation of LRU (least-recently-used) cache.
+
+Bugs fixed:
+
+- fixed a race condition in the TBB scalable allocator.
+- concurrent_queue counter wraparound bug was fixed, which occurred when
+    the number of push and pop operations exceeded ~>4 billion on IA32.
+- fixed races in the TBB scheduler that could put workers asleep too
+    early, especially in presense of affinitized tasks.
+
+------------------------------------------------------------------------
+TBB 4.0 Update 1 commercial-aligned release
+
+Changes (w.r.t. TBB 4.0 commercial-aligned release):
+
+- Memory leaks fixed in binpack example.
+- Improvements and fixes in the TBB allocator.
+
+------------------------------------------------------------------------
 TBB 4.0 commercial-aligned release

 Changes (w.r.t. TBB 3.0 Update 8 commercial-aligned release):

-Improvements:
- concurrent_priority_queue is now a supported feature. Capacity control methods were removed.
- Flow graph is now a supported feature of TBB, rather than being a community preview feature.
- A new memory backend has been implemented in the TBB allocator. It can return small memory blocks to the OS and thus later reuse that memory for large object allocation.
- Improved partitioning algorithms for parallel_for and parallel_reduce to better handle load imbalance.
- The convex_hull example has been refactored to produce reproducible performance results.
- The Major Interface version has changed from 5 to 6. Deprecated interfaces might be removed in future releases.
+- concurrent_priority_queue is now a fully supported feature.
+    Capacity control methods were removed.
+- Flow graph is now a fully supported feature.
+- A new memory backend has been implemented in the TBB allocator.
+    It can reuse freed memory for both small and large objects, and
+    returns unused memory blocks to the OS more actively.
+- Improved partitioning algorithms for parallel_for and parallel_reduce
+    to better handle load imbalance.
+- The convex_hull example has been refactored for reproducible
+    performance results.
+- The major interface version has changed from 5 to 6.
+    Deprecated interfaces might be removed in future releases.

 Community Preview Features:
- Added Community Preview Feature: serial subset of TBB for modeling a sequential execution of a parallel algorithm. This release introduces serial parallel_for.
- Added Community Preview Feature: or_node (accepts multiple inputs, forwarding each input separately to successors), split_node (accepts tuples, and forwards each element to a corresponding successor), and multioutput_function_node (accepts one input, and passes the input and a tuple of output ports to the function body to support outputs to multiple successors).
- Added Community Preview Feature: Scalable Memory Pools (more control on memory source, grouping, collective deallocatation).
+
+- Added: serial subset, i.e. sequential implementations of TBB generic
+    algorithms (currently, only provided for parallel_for).
+- Preview of new flow graph nodes:
+    or_node (accepts multiple inputs, forwards each input separately
+      to all successors),
+    split_node (accepts tuples, and forwards each element of a tuple
+      to a corresponding successor), and
+    multioutput_function_node (accepts one input, and passes the input
+    and a tuple of output ports to the function body to support outputs
+    to multiple successors).
+- Added: memory pools for more control on memory source, grouping,
+    and collective deallocation.

 ------------------------------------------------------------------------
 TBB 3.0 Update 8 commercial-aligned release

 Changes (w.r.t. TBB 3.0 Update 7 commercial-aligned release):

- Task priorities has become an official feature of TBB,
+- Task priorities become an official feature of TBB,
    not community preview as before.
 - Atomics API extended, and implementation refactored.
 - Added task::set_parent() method.
@ -37,12 +154,12 @@ Community Preview Features:

 - Graph community preview feature was renamed to flow graph.
    Multiple improvements in the implementation.
-    Binpack example of the feature was added.
+    Binpack example was added for the feature.
 - A number of improvements to concurrent_priority_queue.
    Shortpath example was added for the feature.
- TBB runtime loader functionality was added (Windows*-only).
-    This allows set exact versions of TBB library to be used in run-time,
-    while setting directories for the library search.
+- TBB runtime loaded functionality was added (Windows*-only).
+    It allows to specify which versions of TBB should be used,
+    as well as to set directories for the library search.
 - parallel_deterministic_reduce template function was added.

 ------------------------------------------------------------------------
@ -56,8 +173,8 @@ Changes (w.r.t. TBB 3.0 Update 6 commercial-aligned release):

 Community Preview Features:

- Graph's dining_philosophers example added
- A number of improvements to graph and concurrent_priority_queue
+- Graph's dining_philosophers example added.
+- A number of improvements to graph and concurrent_priority_queue.


 ------------------------------------------------------------------------
@ -77,11 +194,11 @@ Open-source contributions integrated:

 Bugs fixed:

- Failure to locate Cilk runtime library to enable Cilk/TBB interop.
+- Failure to enable interoperability with Intel(R) Cilk(tm) Plus runtime
+    library, and a crash caused by invoking the interoperability layer
+    after one of the libraries was unloaded.
 - Data race that could result in concurrent_unordered_map structure
    corruption after call to clear() method.
- Crash caused by invoking Cilk/TBB interop after one of the libraries
-    is unloaded.
 - Stack corruption caused by PIC version of 64-bit CAS compiled by Intel
    compiler on Linux.
 - Inconsistency of exception propagation mode possible when application
@ -178,8 +295,8 @@ Changes (w.r.t. TBB 3.0 Update 1 commercial-aligned release):

 - Destructor of tbb::task_group class throws missing_wait exception
    if there are tasks running when it is invoked.
- Cilk-TBB interop layer added to protect TBB TLS in case of
-    "Cilk-TBB-Cilk nesting" usage model.
+- Interoperability layer with Intel Cilk Plus runtime library added
+    to protect TBB TLS in case of nested usage with Intel Cilk Plus.
 - Compilation fix for dependent template names in concurrent_queue.
 - Memory allocator code refactored to ease development and maintenance.

@ -1087,8 +1204,8 @@ Features / APIs:
 - Timers.

 Tools Support:
- Thread Checker 3.0.
- Thread Profiler 3.0.
+- Intel(R) Thread Checker 3.0.
+- Intel(R) Thread Profiler 3.0.

 Documentation:
 - First Use Documents: README.txt, INSTALL.txt, Release_Notes.txt,
@ -1119,4 +1236,7 @@ Packaging:
    are provided separately on Intel(R) Premier.

 ------------------------------------------------------------------------
+Intel and Cilk are registered trademarks or trademarks of Intel Corporation or its
+subsidiaries in the United States and other countries.
+
 * Other names and brands may be claimed as the property of others.
--- a/8
+++ b/8
@ -1,5 +1,5 @@
-c3c66663c10261ff03d1b071ab74e659  tbb40_20110809oss_src.tgz
 683109a2b732ecd56185d9019667718f  Design_Patterns.pdf
-907eed2e81e0d29a93848a26e0fbfa5d  Getting_Started.pdf
-131f0f2ae4311794dfa37b7a9172c54e  Reference.pdf
-74fca4778a2c624631c157b07beab7ec  Tutorial.pdf
+6c2a2838cdaf55f7af57788d97b43b8b  Getting_Started.pdf
+56f3f5407481402e7653e57525f2c79b  Reference.pdf
+08d5cbf5d6ba946784aa578b03586c5e  Tutorial.pdf
+734b356da7fe0ed308741f3e6018251e  tbb40_20120408oss_src.tgz
--- a/tbb-3.0-cxxflags.patch
+++ b/tbb-3.0-cxxflags.patch
@ -5,7 +5,7 @@ diff -up tbb30_20110419oss/build/linux.gcc.inc\~ tbb30_20110419oss/build/linux.g
 
 ITT_NOTIFY = -DDO_ITT_NOTIFY
 ifeq ($(cfg), release)
-        CPLUS_FLAGS = $(ITT_NOTIFY) -O2 -DUSE_PTHREAD
+-        CPLUS_FLAGS = $(ITT_NOTIFY) -g -O2 -DUSE_PTHREAD
 +        CPLUS_FLAGS = $(CXXFLAGS) $(ITT_NOTIFY) -O2 -DUSE_PTHREAD
 endif
 ifeq ($(cfg), debug)
@ -13,6 +13,6 @@ diff -up tbb30_20110419oss/build/linux.gcc.inc\~ tbb30_20110419oss/build/linux.g
 +        CPLUS_FLAGS = $(CXXFLAGS) -DTBB_USE_DEBUG $(ITT_NOTIFY) -g -O0 -DUSE_PTHREAD
 endif
 
- ifneq (0,$(cpp0x))
+ ifneq (00,$(lambdas)$(cpp0x))

 Diff finished.  Tue Jul 26 14:02:54 2011
--- a/tbb.pc
+++ b/tbb.pc
@ -0,0 +1,5 @@
+Name: Threading Building Blocks
+Description: The Threading Building Blocks library abstracts low-level threading details
+URL: http://www.threadingbuildingblocks.org/
+Version: _FEDORA_VERSION
+Libs: -ltbb
--- a/tbb.spec
+++ b/tbb.spec
@ -1,18 +1,20 @@
-%define releasedate 20110809
+%define releasedate 20120408
 %define major 4
 %define minor 0
+%define update 4
 %define dotver %{major}.%{minor}
 %define sourcebasename tbb%{major}%{minor}_%{releasedate}oss
+
 %define sourcefilename %{sourcebasename}_src.tgz

 Summary: The Threading Building Blocks library abstracts low-level threading details
 Name: tbb
 Version: %{dotver}
-Release: 3.%{releasedate}%{?dist}
+Release: 4.%{releasedate}%{?dist}
 License: GPLv2 with exceptions
 Group: Development/Tools
 URL: http://threadingbuildingblocks.org/
-Source0: http://threadingbuildingblocks.org/uploads/77/175/4.0/tbb40_20110809oss_src.tgz
+Source0: http://threadingbuildingblocks.org/uploads/77/185/4.0%%20update%%204/tbb40_20120408oss_src.tgz

 # Upstream regularly replaces the "Latest" documentation with what's
 # actually Latest at that point.  These sources may no longer match
@ -29,6 +31,11 @@ Source3: %{docurl}/%{source_3}
 Source4: %{docurl}/%{source_4}
 Source5: %{docurl}/%{source_5}

+# These two are downstream sources.
+Source6: tbb.pc
+Source7: tbbmalloc.pc
+Source8: tbbmalloc_proxy.pc
+
 Patch1: tbb-3.0-cxxflags.patch
 Patch2: tbb-4.0-mfence.patch
 BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root-%(%{__id_u} -n)
@ -75,7 +82,10 @@ C++ library.

 %build
 make %{?_smp_mflags} CXXFLAGS="$RPM_OPT_FLAGS" tbb_build_prefix=obj
-
+for file in %{SOURCE6} %{SOURCE7} %{SOURCE8}; do
+    sed 's/_FEDORA_VERSION/%{major}.%{minor}.%{update}/' ${file} \
+        > $(basename ${file})
+done
 cp -p "%{SOURCE1}" "%{SOURCE2}" "%{SOURCE3}" "%{SOURCE4}" "%{SOURCE5}" .

 %install
@ -84,7 +94,7 @@ mkdir -p $RPM_BUILD_ROOT/%{_libdir}
 mkdir -p $RPM_BUILD_ROOT/%{_includedir}

 pushd build/obj_release
-    for file in libtbb{,malloc}; do
+    for file in libtbb{,malloc{,_proxy}}; do
        install -p -D -m 755 ${file}.so.2 $RPM_BUILD_ROOT/%{_libdir}
        ln -s $file.so.2 $RPM_BUILD_ROOT/%{_libdir}/$file.so
    done
@ -96,6 +106,11 @@ pushd include
    \;
 popd

+for file in %{SOURCE6} %{SOURCE7} %{SOURCE8}; do
+    install -p -D -m 644 $(basename ${file}) \
+	$RPM_BUILD_ROOT/%{_libdir}/pkgconfig/$(basename ${file})
+done
+
 %post -p /sbin/ldconfig

 %postun -p /sbin/ldconfig
@ -113,6 +128,7 @@ rm -rf ${RPM_BUILD_ROOT}
 %doc %{source_1}
 %{_includedir}/tbb
 %{_libdir}/*.so
+%{_libdir}/pkgconfig/*.pc

 %files doc
 %defattr(-,root,root,-)
@ -122,6 +138,12 @@ rm -rf ${RPM_BUILD_ROOT}
 %doc %{source_5}

 %changelog
+* Thu Jun  7 2012 Petr Machata <pmachata@redhat.com> - 4.0-4.20120408
+- Rebase to 4.0 update 4
+- Refresh Getting_Started.pdf, Reference.pdf, Tutorial.pdf
+- Provide pkg-config files
+- Resolves: #825402
+
 * Thu Apr 05 2012 Karsten Hopp <karsten@redhat.com> 4.0-3.20110809
 - tbb builds now on PPC(64)

--- a/tbbmalloc.pc
+++ b/tbbmalloc.pc
@ -0,0 +1,5 @@
+Name: Threading Building Blocks Scalable Allocator
+Description: Implementation of Scalable Memory Allocator of Threading Building Blocks
+URL: http://www.threadingbuildingblocks.org/
+Version: _FEDORA_VERSION
+Libs: -ltbbmalloc
--- a/tbbmalloc_proxy.pc
+++ b/tbbmalloc_proxy.pc
@ -0,0 +1,5 @@
+Name: Threading Building Blocks Scallable Malloc Proxy
+Description: Implementation of proxy that redirects memory allocation calls to TBB Scalable Memory Allocator
+URL: http://www.threadingbuildingblocks.org/
+Version: _FEDORA_VERSION
+Libs: -ltbbmalloc_proxy