cuda 0.10.1.0 → 0.10.2.0

raw patch · 9 files changed

+100/−46 lines, 9 filessetup-changedPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• CHANGELOG.md +9/−2
• README.md +39/−1
• Setup.hs +4/−2
• cuda.cabal +13/−13
• src/Foreign/CUDA/Analysis/Device.chs +25/−9
• src/Foreign/CUDA/Analysis/Occupancy.hs +10/−9
• src/Foreign/CUDA/Driver/Device.chs +0/−2
• src/Foreign/CUDA/Driver/Exec.chs +0/−2
• src/Foreign/CUDA/Driver/Graph/Build.chs +0/−6

@@ -10,8 +10,14 @@ because NVIDIA are A-OK introducing breaking changes in minor updates.  -## [next]+## [0.10.2.0] - 2020-08-26 ### Added+  * Add support for CUDA-10.2+  * Add support for Cabal-3+  * Add device properties for SM7.x, SM8++## [0.10.1.0] - 2019-04-29+### Added   * Add support for CUDA-10.1  ### Changed@@ -154,7 +160,8 @@   * Add functions from CUDA-6.5  -[next]:       https://github.com/tmcdonell/cuda/compare/v0.10.0.0...HEAD+[0.10.2.0]:   https://github.com/tmcdonell/cuda/compare/v0.10.1.0...v0.10.2.0+[0.10.1.0]:   https://github.com/tmcdonell/cuda/compare/v0.10.0.0...v0.10.1.0 [0.10.0.0]:   https://github.com/tmcdonell/cuda/compare/0.9.0.3...v0.10.0.0 [0.9.0.3]:    https://github.com/tmcdonell/cuda/compare/0.9.0.2...0.9.0.3 [0.9.0.2]:    https://github.com/tmcdonell/cuda/compare/0.9.0.1...0.9.0.2

@@ -20,5 +20,43 @@  For important information on installing on Windows, see: -  <https://github.com/tmcdonell/cuda/blob/master/WINDOWS.markdown>+  <https://github.com/tmcdonell/cuda/blob/master/WINDOWS.md>+++## Missing functionality++An incomplete list of missing bindings. Pull requests welcome!++### CUDA-9++- cuLaunchCooperativeKernelMultiDevice++### CUDA-10.0++- cuDeviceGetLuid (windows only?)+- cuLaunchHostFunc+- cuGraphHostNode[Get/Set]Params+- cuGraphKernelNode[Get/Set]Params+- cuGraphMemcpyNode[Get/Set]Params+- cuGraphMemsetNode[Get/Set]Params++### CUDA-10.2++- cuDeviceGetNvSciSyncAttributes+- cuMemAddressFree+- cuMemAddressReserve+- cuMemCreate+- cuMemExportToShareableHandle+- cuMemGetAccess+- cuMemGetAllocationGranularity+- cuMemGetAllocationPrepertiesFromHandle+- cuMemImportFromShareableHandle+- cuMemMap+- cuMemRelease+- cuMemSetAccess+- cuMemUnmap+- cuGraphExecHostNodeSetParams+- cuGraphExecMemcpyNodeSetParams+- cuGraphExecMemsetNodeSetParams+- cuGraphExecUpdate 

@@ -64,7 +64,6 @@ main = defaultMainWithHooks customHooks   where     readHook get_verbosity a flags = do-        noExtraFlags a         getHookedBuildInfo (fromFlag (get_verbosity flags))      preprocessors = hookedPreProcessors simpleUserHooks@@ -105,7 +104,6 @@           currentPlatform = hostPlatform lbi           compilerId_     = compilerId (compiler lbi)       ---      noExtraFlags args       generateAndStoreBuildInfo           verbosity           profile@@ -196,7 +194,11 @@     , extraLibDirs        = extraLibDirs'     , frameworks          = frameworks'     , extraFrameworkDirs  = frameworkDirs'+#if MIN_VERSION_Cabal(3,0,0)+    , options             = PerCompilerFlavor (if os /= Windows then ghcOptions else []) []+#else     , options             = [(GHC, ghcOptions) | os /= Windows]+#endif     , customFieldsBI      = [c2hsExtraOptions]     } 

@@ -1,5 +1,5 @@ Name:                   cuda-Version:                0.10.1.0+Version:                0.10.2.0 Synopsis:               FFI binding to the CUDA interface for programming NVIDIA GPUs Description:     The CUDA library provides a direct, general purpose C-like SPMD programming@@ -28,7 +28,7 @@     .     * "Foreign.CUDA.Runtime"     .-    Tested with library versions up to CUDA-9.2. See also the+    Tested with library versions up to CUDA-10.2. See also the     <https://travis-ci.org/tmcdonell/cuda travis-ci.org> build matrix for     version compatibility.     .@@ -65,7 +65,7 @@ Bug-reports:            https://github.com/tmcdonell/cuda/issues Category:               Foreign Cabal-version:          >= 1.24-Tested-with:            GHC >= 7.8+Tested-with:            GHC >= 8.0 Build-type:             Custom  Extra-tmp-files:@@ -86,7 +86,7 @@  Library   hs-source-dirs:       src-  Exposed-Modules:+  exposed-modules:       Foreign.CUDA       Foreign.CUDA.Path       Foreign.CUDA.Ptr@@ -138,16 +138,16 @@       -- Extras       Foreign.C.Extra -  Other-modules:+  other-modules:       Foreign.CUDA.Internal.C2HS       Text.Show.Describe -  Include-dirs:         .-  C-sources:            cbits/stubs.c+  include-dirs:         .+  c-sources:            cbits/stubs.c                         cbits/init.c -  Build-tools:          c2hs >= 0.21-  Build-depends:+  build-tools:          c2hs >= 0.21+  build-depends:       base              >= 4.7 && < 5     , bytestring        >= 0.10.4     , filepath          >= 1.0@@ -155,7 +155,7 @@     , uuid-types        >= 1.0    default-language:     Haskell98-  Extensions:+   ghc-options:       -Wall       -O2@@ -172,10 +172,10 @@   Executable nvidia-device-query-  Main-is:              DeviceQuery.hs+  main-is:              DeviceQuery.hs   hs-source-dirs:       examples/src/deviceQueryDrv -  Build-depends:+  build-depends:       base              >= 4 && < 5     , cuda     , pretty@@ -190,6 +190,6 @@ source-repository this     type:               git     location:           https://github.com/tmcdonell/cuda-    tag:                v0.10.1.0+    tag:                v0.10.2.0  -- vim: nospell

@@ -150,6 +150,8 @@ -- wikipedia entry: <https://en.wikipedia.org/wiki/CUDA#Version_features_and_specifications> -- data Allocation      = Warp | Block+  deriving Show+ data DeviceResources = DeviceResources   { threadsPerWarp          :: !Int         -- ^ Warp size   , coresPerMP              :: !Int         -- ^ Number of SIMD arithmetic units per multiprocessor@@ -168,6 +170,7 @@   , warpRegAllocUnit        :: !Int         -- ^ Warp register allocation granularity   , maxGridsPerDevice       :: !Int         -- ^ Maximum number of resident grids per device (concurrent kernels)   }+  deriving Show   -- |@@ -322,8 +325,7 @@         , maxGridsPerDevice     = 16         } -      Compute 7 0 -> resources (Compute 7 2)      -- Volta GV100-      Compute 7 2 -> DeviceResources+      Compute 7 0 -> DeviceResources              -- Volta GV100         { threadsPerWarp        = 32         , coresPerMP            = 64         , warpsPerMP            = 64@@ -342,21 +344,35 @@         , maxGridsPerDevice     = 128         } -      Compute 7 5 -> DeviceResources              -- Turing TU1xx-        { threadsPerWarp        = 32-        , coresPerMP            = 64-        , warpsPerMP            = 32-        , threadsPerMP          = 1024+      Compute 7 2 -> (resources (Compute 7 0))    -- Volta GV10B+        { maxGridsPerDevice     = 16+        , maxSharedMemPerBlock  = 49152+        }++      Compute 7 5 -> (resources (Compute 7 0))    -- Turing TU1xx+        { warpsPerMP            = 32         , threadBlocksPerMP     = 16+        , threadsPerMP          = 1024+        , maxGridsPerDevice     = 128         , sharedMemPerMP        = 65536           -- of 96KB         , maxSharedMemPerBlock  = 65536+        }++      Compute 8 0 -> DeviceResources              -- Ampere GA100+        { threadsPerWarp        = 32+        , coresPerMP            = 64+        , warpsPerMP            = 64+        , threadsPerMP          = 2048+        , threadBlocksPerMP     = 32+        , sharedMemPerMP        = 167936          -- of 192KB+        , maxSharedMemPerBlock  = 163840         , regFileSizePerMP      = 65536         , maxRegPerBlock        = 65536         , regAllocUnit          = 256         , regAllocationStyle    = Warp         , maxRegPerThread       = 255-        , sharedMemAllocUnit    = 256-        , warpAllocUnit         = 2+        , sharedMemAllocUnit    = 128+        , warpAllocUnit         = 4         , warpRegAllocUnit      = 256         , maxGridsPerDevice     = 128         }

@@ -57,7 +57,7 @@ import Data.Ord import Data.List -import Foreign.CUDA.Analysis.Device+import Foreign.CUDA.Analysis.Device                                 hiding ( maxSharedMemPerBlock )   -- GPU Occupancy per multiprocessor@@ -97,7 +97,8 @@      -- Physical resources     ---    gpu = deviceResources dev+    gpu                  = deviceResources dev+    maxSharedMemPerBlock = fromIntegral (sharedMemPerBlock dev) -- 2080Ti reports 48KB, but should be 64KB !      -- Allocated resource limits     --@@ -116,16 +117,16 @@      -- Maximum thread blocks per multiprocessor     ---    limitDueToWarps                     = threadBlocksPerMP gpu `min` (warpsPerMP gpu `div` limitWarpsPerBlock)+    limitDueToWarps                 = threadBlocksPerMP gpu `min` (warpsPerMP gpu `div` limitWarpsPerBlock)     limitDueToRegs-      | regs > maxRegPerThread gpu      = 0-      | regs > 0                        = (limitRegsPerSM `div` limitRegsPerBlock) * (regFileSizePerMP gpu `div` maxRegPerBlock gpu)-      | otherwise                       = threadBlocksPerMP gpu+      | regs > maxRegPerThread gpu  = 0+      | regs > 0                    = (limitRegsPerSM `div` limitRegsPerBlock) * (regFileSizePerMP gpu `div` maxRegPerBlock gpu)+      | otherwise                   = threadBlocksPerMP gpu      limitDueToSMem-      | smem > maxSharedMemPerBlock gpu = 0-      | smem > 0                        = sharedMemPerMP gpu `div` limitSMemPerBlock-      | otherwise                       = threadBlocksPerMP gpu+      | smem > maxSharedMemPerBlock = 0+      | smem > 0                    = sharedMemPerMP gpu `div` limitSMemPerBlock+      | otherwise                   = threadBlocksPerMP gpu   -- |

@@ -290,8 +290,6 @@ #endif  --- TODO: cuDeviceGetLuid, introduced CUDA-10.0 (windows only)- -- | -- Return the properties of the selected device --

@@ -352,8 +352,6 @@   } -> `Status' cToEnum #} #endif --- TODO: cuLaunchCooperativeKernelMultiDevice introduced CUDA-9.0--- TODO: cuLaunchHostFunc introduced CUDA-10.0  -------------------------------------------------------------------------------- -- Deprecated

@@ -659,12 +659,6 @@ #endif  --- TODO: since CUDA-10.0---  * cuGraphHostNode[Get/Set]Params---  * cuGraphKernelNode[Get/Set]Params---  * cuGraphMemcpyNode[Get/Set]Params---  * cuGraphMemsetNode[Get/Set]Params- -------------------------------------------------------------------------------- -- Internal --------------------------------------------------------------------------------