Squashed 'thirdParty/mallocMC/' changes from 3531c29c0..4b779a34c

4b779a34c Merge pull request ComputationalRadiationPhysics#147 from ComputationalRadiationPhysics/dev
1ca54d657 Merge pull request ComputationalRadiationPhysics#146 from ax3l/doc-changelog023
07a316488 Version: Bump 0.2.3crp
6f2f6140d Add 0.2.3crp Changelog
1749d1cae Merge pull request ComputationalRadiationPhysics#145 from ax3l/fix-activeMask
68bf353de Fix V100 Active Lanes in Warp
80bf2b0d0 Merge pull request ComputationalRadiationPhysics#102 from ComputationalRadiationPhysics/dev
799d7d7 Merge pull request ComputationalRadiationPhysics#84 from ComputationalRadiationPhysics/dev
1314bf2 Merge pull request ComputationalRadiationPhysics#76 from ComputationalRadiationPhysics/dev
ddeae86 Merge pull request ComputationalRadiationPhysics#56 from ComputationalRadiationPhysics/dev

git-subtree-dir: thirdParty/mallocMC
git-subtree-split: 4b779a34cd8ba073b24f69435d71022f3988d42e

CHANGELOG.md

@@ -1,6 +1,42 @@
 Change Log / Release Log for mallocMC
 ================================================================
 
+2.3.0crp
+--------
+**Date:** 2018-06-11
+
+This release adds support for CUDA 9 and clang's -x cuda frontend and fixes several bugs.
+Global objects have been refactored to separate objects on host and device.
+
+### Changes to mallocMC 2.2.0crp
+
+**Features**
+ - CUDA 9 support #144 #145
+ - clang++ -x cuda support #133
+ - add `destructiveResize` method #136
+ - heap as separate object on host and device, no more globals #116
+ - use `BOOST_STATIC_CONSTEXPR` where possible #109
+
+**Bug fixes**
+ - fix uninitialized pointers #110 #112
+ - fix crash in getAvailableSlots #106 #107
+ - Fix `uint32_t` cstdint #104 #105
+ - fix missing boost include #142
+ - fix includes from C headers #121
+ - fix missing local size change in `finalizeHeap()` #135
+ - check heap pointer in Scatter creation policy #126
+
+**Misc:**
+ - better link usage and install docs #141
+ - self consistent allocator #140
+ - rename some shadowed variables in C++11 mode #108
+ - properly enforce `-Werror` in Travis-CI #128
+ - update Travis-CI image #119
+ - improved docs #125 #127
+
+Thanks to Carlchristian Eckert, René Widera, Axel Huebl and Alexander Grund for contributing to this release!
+
+
 2.2.0crp
 -------------
 **Date:** 2015-09-25

src/include/mallocMC/creationPolicies/Scatter_impl.hpp

@@ -619,7 +619,7 @@ namespace ScatterKernelDetail{
         void* res = 0;
         for(
 #if(__CUDACC_VER_MAJOR__ >= 9)
-          unsigned int __mask = __ballot_sync(0xFFFFFFFF, 1),
+          unsigned int __mask = __activemask(),
 #else
           unsigned int __mask = __ballot(1),
 #endif
@@ -936,7 +936,7 @@ namespace ScatterKernelDetail{
         int wId = threadIdx.x >> 5; //do not use warpid-function, since this value is not guaranteed to be stable across warp lifetime
 
 #if(__CUDACC_VER_MAJOR__ >= 9)
-        uint32 activeThreads  = __popc(__ballot_sync(0xFFFFFFFF, true));
+        uint32 activeThreads  = __popc(__activemask());
 #else
         uint32 activeThreads  = __popc(__ballot(true));
 #endif

src/include/mallocMC/distributionPolicies/XMallocSIMD_impl.hpp

@@ -101,7 +101,7 @@ namespace DistributionPolicies{
         //necessary for offset calculation
         bool coalescible = bytes > 0 && bytes < (pagesize / 32);
 #if(__CUDACC_VER_MAJOR__ >= 9)
-        threadcount = __popc(__ballot_sync(0xFFFFFFFF, coalescible));
+        threadcount = __popc(__ballot_sync(__activemask(), coalescible));
 #else
         threadcount = __popc(__ballot(coalescible));
 #endif

src/include/mallocMC/version.hpp

@@ -38,7 +38,7 @@
 
 /** the mallocMC version: major API changes should be reflected here */
 #define MALLOCMC_VERSION_MAJOR 2
-#define MALLOCMC_VERSION_MINOR 2
+#define MALLOCMC_VERSION_MINOR 3
 #define MALLOCMC_VERSION_PATCH 0
 
 /** the mallocMC flavor is used to differentiate the releases of the