parallel solver: various changes

- threading: adding btSequentialImpulseConstraintSolverMt - task scheduler: added parallelSum so that parallel solver can compute residuals - CommonRigidBodyMTBase: add slider for solver least squares residual and allow multithreading without needing OpenMP, TBB, or PPL - taskScheduler: don't wait for workers to sleep/signal at the end of each parallel block - parallel solver: convertContacts split into an allocContactConstraints and setupContactConstraints stage, the latter of which is done in parallel - parallel solver: rolling friction is now interleaved along with normal friction - parallel solver: batchified split impulse solving + some cleanup - parallel solver: sorting batches from largest to smallest - parallel solver: added parallel batch creation - parallel solver: added warmstartingWriteBackContacts func + other cleanup - task scheduler: truncate low bits to preserve determinism with parallelSum - parallel solver: reducing dynamic mem allocs and trying to parallelize more of the batch setup - parallel solver: parallelize updating constraint batch ids for merging - parallel solver: adding debug visualization - task scheduler: make TBB task scheduler parallelSum deterministic - parallel solver: split batch gen code into separate file; allow selection of batch gen method - task scheduler: add sleepWorkerThreadsHint() at end of simulation - parallel solver: added grain size per phase - task Scheduler: fix for strange threading issue; also no need for main thread to wait for workers to sleep - base constraint solver: break out joint setup into separate function for profiling/overriding - parallel solver: allow different batching method for contacts vs joints - base constraint solver: add convertJoint and convertBodies to make it possible to parallelize joint and body conversion - parallel solver: convert joints and bodies in parallel now - parallel solver: speed up batch creation with run-length encoding - parallel solver: batch gen: run-length expansion in parallel; collect constraint info in parallel - parallel solver: adding spatial grid batching method - parallel solver: enhancements to spatial grid batching - sequential solver: moving code for writing back into functions that derived classes can call - parallel solver: do write back of bodies and joints in parallel - parallel solver: removed all batching methods except for spatial grid (others were ineffective) - parallel solver: added 2D or 3D grid batching options; and a bit of cleanup - move btDefaultTaskScheduler into LinearMath project
2017-06-04 17:57:25 -07:00
parent 94bc897067
commit b8720f2161
25 changed files with 5236 additions and 767 deletions
--- a/src/LinearMath/TaskScheduler/btThreadSupportInterface.h
+++ b/src/LinearMath/TaskScheduler/btThreadSupportInterface.h
@@ -0,0 +1,75 @@
+/*
+Bullet Continuous Collision Detection and Physics Library
+Copyright (c) 2003-2018 Erwin Coumans  http://bulletphysics.com
+
+This software is provided 'as-is', without any express or implied warranty.
+In no event will the authors be held liable for any damages arising from the use of this software.
+Permission is granted to anyone to use this software for any purpose,
+including commercial applications, and to alter it and redistribute it freely,
+subject to the following restrictions:
+
+1. The origin of this software must not be misrepresented; you must not claim that you wrote the original software. If you use this software in a product, an acknowledgment in the product documentation would be appreciated but is not required.
+2. Altered source versions must be plainly marked as such, and must not be misrepresented as being the original software.
+3. This notice may not be removed or altered from any source distribution.
+*/
+
+#ifndef BT_THREAD_SUPPORT_INTERFACE_H
+#define BT_THREAD_SUPPORT_INTERFACE_H
+
+
+
+class btCriticalSection
+{
+public:
+    btCriticalSection() {}
+    virtual ~btCriticalSection() {}
+
+    virtual void lock() = 0;
+    virtual void unlock() = 0;
+};
+
+
+class btThreadSupportInterface
+{
+public:
+
+    virtual ~btThreadSupportInterface() {}
+
+    virtual int getNumWorkerThreads() const = 0;  // number of worker threads (total number of logical processors - 1)
+    virtual int getCacheFriendlyNumThreads() const = 0;  // the number of logical processors sharing a single L3 cache
+    virtual void runTask( int threadIndex, void* userData ) = 0;
+    virtual void waitForAllTasks() = 0;
+
+    virtual btCriticalSection* createCriticalSection() = 0;
+    virtual void deleteCriticalSection( btCriticalSection* criticalSection ) = 0;
+
+    virtual void* getThreadLocalMemory( int taskId ) { return NULL; }
+
+    typedef void( *ThreadFunc )( void* userPtr, void* lsMemory );
+    typedef void* ( *MemorySetupFunc )( );
+
+    struct ConstructionInfo
+    {
+        ConstructionInfo( const char* uniqueName,
+            ThreadFunc userThreadFunc,
+            MemorySetupFunc	lsMemoryFunc,
+            int threadStackSize = 65535
+        )
+            :m_uniqueName( uniqueName ),
+            m_userThreadFunc( userThreadFunc ),
+            m_lsMemoryFunc( lsMemoryFunc ),
+            m_threadStackSize( threadStackSize )
+        {
+        }
+
+        const char*     m_uniqueName;
+        ThreadFunc      m_userThreadFunc;
+        MemorySetupFunc m_lsMemoryFunc;
+        int             m_threadStackSize;
+    };
+
+    static btThreadSupportInterface* create( const ConstructionInfo& info );
+};
+
+#endif //BT_THREAD_SUPPORT_INTERFACE_H
+