[GSoC 2016][Polly][FIX] Determination of statements that contain matrix multiplication

[gareevroman]

Summary

Fix small issues related to characters, operators and descriptions of tests.

[jdoerfert]

• msg-15076-52.txt6 KBDownload
• signature.asc219 BDownload

polly/trunk/include/polly/ScheduleOptimizer.h

private:
   /// are true:
   /// 1. the partial schedule contains only one statement.
   /// 2. there are exactly three input dimensions.
   /// 3. all memory accesses of the statement will have stride 0 or 1, if we
   ///    interchange loops (switch the variable used in the inner loop to
   ///    the outer loop).
   /// 4. all memory accesses of the statement except from the last one, are
   ///    read memory access and the last one is write memory access.
-  /// 5. all subscripts of the last memory access of the statement don’t
+  /// 5. all subscripts of the last memory access of the statement don't
   ///    contain the variable used in the inner loop.
   /// If this is the case, we could try to use an approach that is similar to
   /// the one used to get close-to-peak performance of matrix multiplications.
   ///
   /// @param Node The node to check.
   static bool isMatrMultPattern(__isl_keep isl_schedule_node *Node);
 };
 
 #endif

polly/trunk/lib/Transform/ScheduleOptimizer.cpp

 ///
 /// We build a set of partial tile prefixes, which are prefixes of the vector
 /// loop that have exactly VectorWidth iterations.
 ///
 /// 1. Get all prefixes of the vector loop.
 /// 2. Extend it to a set, which has exactly VectorWidth iterations for
 ///    any prefix from the set that was built on the previous step.
 /// 3. Subtract loop domain from it, project out the vector loop dimension and
-///    get a set of prefixes, which don’t have exactly VectorWidth iterations.
+///    get a set of prefixes, which don't have exactly VectorWidth iterations.
 /// 4. Subtract it from all prefixes of the vector loop and get the desired
 ///    set.
 ///
 /// @param ScheduleRange A range of a map, which describes a prefix schedule
 ///                      relation.
 static __isl_give isl_set *
 getPartialTilePrefixes(__isl_take isl_set *ScheduleRange, int VectorWidth) {
   auto Dims = isl_set_dim(ScheduleRange, isl_dim_set);

 ///
 /// containsMatrMult tries to determine whether the following conditions
 /// are true:
 /// 1. all memory accesses of the statement will have stride 0 or 1,
 ///    if we interchange loops (switch the variable used in the inner
 ///    loop to the outer loop).
 /// 2. all memory accesses of the statement except from the last one, are
 ///    read memory access and the last one is write memory access.
-/// 3. all subscripts of the last memory access of the statement don’t contain
+/// 3. all subscripts of the last memory access of the statement don't contain
 ///    the variable used in the inner loop.
 ///
 /// @param PartialSchedule The PartialSchedule that contains a SCoP statement
 ///        to check.
 static bool containsMatrMult(__isl_keep isl_map *PartialSchedule) {
   auto InputDimsId = isl_map_get_tuple_id(PartialSchedule, isl_dim_in);
   auto *ScpStmt = static_cast<ScopStmt *>(isl_id_get_user(InputDimsId));
   isl_id_free(InputDimsId);
   if (ScpStmt->size() <= 1)
     return false;
   auto MemA = ScpStmt->begin();
   for (unsigned i = 0; i < ScpStmt->size() - 2 && MemA != ScpStmt->end();
        i++, MemA++)
-    if (!(*MemA)->isRead() or
-        ((*MemA)->isArrayKind() and
-         !((*MemA)->isStrideOne(isl_map_copy(PartialSchedule)) or
+    if (!(*MemA)->isRead() ||
+        ((*MemA)->isArrayKind() &&
+         !((*MemA)->isStrideOne(isl_map_copy(PartialSchedule)) ||
            (*MemA)->isStrideZero(isl_map_copy(PartialSchedule)))))
       return false;
   MemA++;
-  if (!(*MemA)->isWrite() or !(*MemA)->isArrayKind() or
-      !((*MemA)->isStrideOne(isl_map_copy(PartialSchedule)) or
+  if (!(*MemA)->isWrite() || !(*MemA)->isArrayKind() ||
+      !((*MemA)->isStrideOne(isl_map_copy(PartialSchedule)) ||
         (*MemA)->isStrideZero(isl_map_copy(PartialSchedule))))
     return false;
   auto DimNum = isl_map_dim(PartialSchedule, isl_dim_in);
   return !isInputDimUsed((*MemA)->getAccessRelation(), DimNum - 1);
 }
 
 /// @brief Circular shift of output dimensions of the integer map.
 ///

polly/trunk/test/ScheduleOptimizer/pattern-matching-based-opts.ll

 ; RUN: opt %loadPolly -polly-opt-isl -debug < %s 2>&1| FileCheck %s
 ; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -debug < %s 2>&1| FileCheck %s --check-prefix=PATTERN-MATCHING-OPTS
 ; REQUIRES: asserts
+;
+;    /* C := alpha*A*B + beta*C */
+;    for (i = 0; i < _PB_NI; i++)
+;      for (j = 0; j < _PB_NJ; j++)
+;        {
+;    C[i][j] *= beta;
+;    for (k = 0; k < _PB_NK; ++k)
+;      C[i][j] += alpha * A[i][k] * B[k][j];
+;        }
+;
 ; CHECK-NOT: The matrix multiplication pattern was detected
 ; PATTERN-MATCHING-OPTS: The matrix multiplication pattern was detected
+;
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1024 x double]* %arg6, [1056 x double]* %arg7) {
 bb:
   br label %bb8
 
 bb8:                                              ; preds = %bb39, %bb
   %tmp = phi i32 [ 0, %bb ], [ %tmp40, %bb39 ]
   %tmp9 = icmp slt i32 %tmp, 1056

polly/trunk/test/ScheduleOptimizer/pattern-matching-based-opts_2.ll

 ; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -debug < %s 2>&1 | FileCheck %s
 ; REQUIRES: asserts
+;
+;    /* C := alpha*A*B + beta*C */
+;    for (i = 0; i < _PB_NI; i++)
+;      for (j = 0; j < _PB_NJ; j += 2)
+;        {
+;    C[i][j] *= beta;
+;    for (k = 0; k < _PB_NK; ++k)
+;      C[i][j] += alpha * A[i][k] * B[k][j];
+;        }
+;
+; Check that we won’t detect the matrix multiplication pattern,
+; if, for example, there are memory accesses that have stride 2
+; after the interchanging of loops.
+;
 ; CHECK-NOT: The matrix multiplication pattern was detected
+;
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
 define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1024 x double]* %arg6, [1056 x double]* %arg7) {
 bb:
   br label %bb8
 
 bb8:                                              ; preds = %bb39, %bb
   %tmp = phi i32 [ 0, %bb ], [ %tmp40, %bb39 ]
   %tmp9 = icmp slt i32 %tmp, 1056