Merge pull request #96 from kirillgarbar/spmspvmasked

SpMSpVMasked

src/GraphBLAS-sharp.Backend/Algorithms/BFS.fs

@@ -135,7 +135,7 @@ module internal BFS =
             Operations.SpMVInPlace add mul clContext workGroupSize
 
         let spMSpV =
-            Operations.SpMSpVBool add mul clContext workGroupSize
+            Operations.SpMSpVMaskedBool add mul clContext workGroupSize
 
         let zeroCreate =
             Vector.zeroCreate clContext workGroupSize
@@ -145,13 +145,11 @@ module internal BFS =
         let maskComplementedInPlace =
             Vector.map2InPlace Mask.complementedOp clContext workGroupSize
 
-        let maskComplemented =
-            Vector.map2Sparse Mask.complementedOp clContext workGroupSize
-
         let fillSubVectorInPlace =
             Vector.assignByMaskInPlace (Mask.assign) clContext workGroupSize
 
-        let toSparse = Vector.toSparse clContext workGroupSize
+        let toSparse =
+            Vector.toSparseUnsorted clContext workGroupSize
 
         let toDense = Vector.toDense clContext workGroupSize
 
@@ -190,28 +188,21 @@ module internal BFS =
                 match frontier with
                 | ClVector.Sparse _ ->
                     //Getting new frontier
-                    match spMSpV queue matrix frontier with
+                    match spMSpV queue matrix frontier levels with
                     | None ->
                         frontier.Dispose()
                         stop <- true
-                    | Some newFrontier ->
+                    | Some newMaskedFrontier ->
                         frontier.Dispose()
-                        //Filtering visited vertices
-                        match maskComplemented queue DeviceOnly newFrontier levels with
-                        | None ->
-                            stop <- true
-                            newFrontier.Dispose()
-                        | Some newMaskedFrontier ->
-                            newFrontier.Dispose()
-
-                            //Push/pull
-                            let NNZ = getNNZ queue newMaskedFrontier
-
-                            if (push NNZ newMaskedFrontier.Size) then
-                                frontier <- newMaskedFrontier
-                            else
-                                frontier <- toDense queue DeviceOnly newMaskedFrontier
-                                newMaskedFrontier.Dispose()
+
+                        //Push/pull
+                        let NNZ = getNNZ queue newMaskedFrontier
+
+                        if (push NNZ newMaskedFrontier.Size) then
+                            frontier <- newMaskedFrontier
+                        else
+                            frontier <- toDense queue DeviceOnly newMaskedFrontier
+                            newMaskedFrontier.Dispose()
                 | ClVector.Dense oldFrontier ->
                     //Getting new frontier
                     spMVInPlace queue matrix frontier frontier

src/GraphBLAS-sharp.Backend/Common/ClArray.fs

@@ -362,7 +362,7 @@ module ClArray =
 
                 let gid = ndRange.GlobalID0
 
-                if gid < length then
+                if gid < length && not result.Value then
                     let isExist = (%predicate) vector.[gid]
 
                     if isExist then result.Value <- true @>
@@ -902,22 +902,40 @@ module ClArray =
 
     let count<'a> (predicate: Expr<'a -> bool>) (clContext: ClContext) workGroupSize =
 
-        let sum =
-            Reduce.reduce <@ (+) @> clContext workGroupSize
+        let count =
+            <@ fun (ndRange: Range1D) (length: int) (array: ClArray<'a>) (count: ClCell<int>) ->
+                let gid = ndRange.GlobalID0
+                let mutable countLocal = 0
+                let step = ndRange.GlobalWorkSize
+
+                let mutable i = gid
 
-        let getBitmap =
-            Map.map<'a, int> (Map.predicateBitmap predicate) clContext workGroupSize
+                while i < length do
+                    let res = (%predicate) array.[i]
+                    if res then countLocal <- countLocal + 1
+                    i <- i + step
+
+                atomic (+) count.Value countLocal |> ignore @>
+
+        let count = clContext.Compile count
 
         fun (processor: RawCommandQueue) (array: ClArray<'a>) ->
 
-            let bitmap = getBitmap processor DeviceOnly array
+            let result = clContext.CreateClCell<int>(0)
 
-            let result =
-                (sum processor bitmap).ToHostAndFree processor
+            let numberOfGroups =
+                Utils.divUpClamp array.Length workGroupSize 1 1024
 
-            bitmap.Free()
+            let ndRange =
+                Range1D.CreateValid(workGroupSize * numberOfGroups, workGroupSize)
 
-            result
+            let kernel = count.GetKernel()
+
+            kernel.KernelFunc ndRange array.Length array result
+
+            processor.RunKernel kernel
+
+            result.ToHostAndFree processor
 
     /// <summary>
     /// Builds a new array whose elements are the results of applying the given function

src/GraphBLAS-sharp.Backend/Common/Sort/Bitonic.fs

@@ -12,6 +12,7 @@ module Bitonic =
                 int (clContext.ClDevice.LocalMemSize)
                 / (sizeof<uint64> + sizeof<'a>)
             )
+            / 2
 
         let maxThreadsPerBlock =
             min (clContext.ClDevice.MaxWorkGroupSize) (localSize / 2)
@@ -257,6 +258,7 @@ module Bitonic =
                 int (clContext.ClDevice.LocalMemSize)
                 / (sizeof<int> + sizeof<'a>)
             )
+            / 2
 
         let maxThreadsPerBlock =
             min (clContext.ClDevice.MaxWorkGroupSize) (localSize / 2)
@@ -476,4 +478,4 @@ module Bitonic =
 
                 kernelGlobal.KernelFunc ndRangeGlobal rows values values.Length (localSize * 2)
 
-                queue.RunKernel(kernelGlobal)
+                queue.RunKernel(kernelGlobal)

src/GraphBLAS-sharp.Backend/Common/Utils.fs

@@ -19,6 +19,10 @@ module internal Utils =
         >> fun x -> x ||| (x >>> 16)
         >> fun x -> x + 1
 
+    let divUp x y = x / y + (if x % y = 0 then 0 else 1)
+
+    let divUpClamp x y left right = min (max (divUp x y) left) right
+
     let floorToMultiple multiple x = x / multiple * multiple
 
     let ceilToMultiple multiple x = ((x - 1) / multiple + 1) * multiple

src/GraphBLAS-sharp.Backend/Operations/Operations.fs

@@ -331,7 +331,7 @@ module Operations =
             | _ -> failwith "Not implemented yet"
 
     /// <summary>
-    /// CSR Matrix - sparse vector multiplication. Optimized for bool OR and AND operations.
+    /// CSR Matrix - sparse vector multiplication. Optimized for bool OR and AND operations by skipping reduction stage.
     /// </summary>
     /// <param name="add">Type of binary function to reduce entries.</param>
     /// <param name="mul">Type of binary function to combine entries.</param>
@@ -352,6 +352,50 @@ module Operations =
             | ClMatrix.CSR m, ClVector.Sparse v -> Option.map ClVector.Sparse (run queue m v)
             | _ -> failwith "Not implemented yet"
 
+    /// <summary>
+    /// CSR Matrix - sparse vector multiplication with mask. Mask is complemented.
+    /// </summary>
+    /// <param name="add">Type of binary function to reduce entries.</param>
+    /// <param name="mul">Type of binary function to combine entries.</param>
+    /// <param name="clContext">OpenCL context.</param>
+    /// <param name="workGroupSize">Should be a power of 2 and greater than 1.</param>
+    let SpMSpVMasked
+        (add: Expr<'c option -> 'c option -> 'c option>)
+        (mul: Expr<'a option -> 'b option -> 'c option>)
+        (clContext: ClContext)
+        workGroupSize
+        =
+
+        let run =
+            SpMSpV.Masked.runMasked add mul clContext workGroupSize
+
+        fun (queue: RawCommandQueue) (matrix: ClMatrix<'a>) (vector: ClVector<'b>) (mask: ClVector<'d>) ->
+            match matrix, vector, mask with
+            | ClMatrix.CSR m, ClVector.Sparse v, ClVector.Dense mask -> Option.map ClVector.Sparse (run queue m v mask)
+            | _ -> failwith "Not implemented yet"
+
+    /// <summary>
+    /// CSR Matrix - sparse vector multiplication with mask. Mask is complemented. Optimized for bool OR and AND operations by skipping reduction stage.
+    /// </summary>
+    /// <param name="add">Type of binary function to reduce entries.</param>
+    /// <param name="mul">Type of binary function to combine entries.</param>
+    /// <param name="clContext">OpenCL context.</param>
+    /// <param name="workGroupSize">Should be a power of 2 and greater than 1.</param>
+    let SpMSpVMaskedBool
+        (add: Expr<bool option -> bool option -> bool option>)
+        (mul: Expr<bool option -> bool option -> bool option>)
+        (clContext: ClContext)
+        workGroupSize
+        =
+
+        let run =
+            SpMSpV.Masked.runMaskedBoolStandard add mul clContext workGroupSize
+
+        fun (queue: RawCommandQueue) (matrix: ClMatrix<'a>) (vector: ClVector<'b>) (mask: ClVector<'d>) ->
+            match matrix, vector, mask with
+            | ClMatrix.CSR m, ClVector.Sparse v, ClVector.Dense mask -> Option.map ClVector.Sparse (run queue m v mask)
+            | _ -> failwith "Not implemented yet"
+
     /// <summary>
     /// CSR Matrix - sparse vector multiplication.
     /// </summary>