[SYCL] Enable range rounding for unnamed lambdas (#10736)

Author: sergey-semenov

sycl/include/sycl/handler.hpp

@@ -1063,7 +1063,8 @@ class __SYCL_EXPORT handler {
 
     // Disable the rounding-up optimizations under these conditions:
     // 1. The env var SYCL_DISABLE_PARALLEL_FOR_RANGE_ROUNDING is set.
-    // 2. The kernel is provided via an interoperability method.
+    // 2. The kernel is provided via an interoperability method (this uses a
+    // different code path).
     // 3. The range is already a multiple of the rounding factor.
     //
     // Cases 2 and 3 could be supported with extra effort.
@@ -1076,17 +1077,10 @@ class __SYCL_EXPORT handler {
     // call-graph to make this_item calls kernel-specific but this is
     // not considered worthwhile.
 
-    // Get the kernel name to check condition 2.
-    std::string KName = typeid(NameT *).name();
-    using KI = detail::KernelInfo<KernelName>;
-    bool DisableRounding =
-        this->DisableRangeRounding() ||
-        (KI::getName() == nullptr || KI::getName()[0] == '\0');
-
     // Perform range rounding if rounding-up is enabled
     // and there are sufficient work-items to need rounding
     // and the user-specified range is not a multiple of a "good" value.
-    if (!DisableRounding && (NumWorkItems[0] >= MinRangeX) &&
+    if (!this->DisableRangeRounding() && (NumWorkItems[0] >= MinRangeX) &&
         (NumWorkItems[0] % MinFactorX != 0)) {
       // It is sufficient to round up just the first dimension.
       // Multiplying the rounded-up value of the first dimension

sycl/test-e2e/Basic/parallel_for_range_roundup.cpp

@@ -145,6 +145,27 @@ void try_id3(size_t size) {
   check("Counter = ", Counter, size * 10 * 10);
 }
 
+void try_unnamed_lambda(size_t size) {
+  range<3> Size{size, 10, 10};
+  int Counter = 0;
+  {
+    buffer<range<3>, 1> BufRange(&Range3, 1);
+    buffer<int, 1> BufCounter(&Counter, 1);
+    queue myQueue;
+
+    myQueue.submit([&](handler &cgh) {
+      auto AccRange = BufRange.get_access<access::mode::read_write>(cgh);
+      auto AccCounter = BufCounter.get_access<access::mode::atomic>(cgh);
+      cgh.parallel_for(Size, [=](id<3> ID) {
+        AccCounter[0].fetch_add(1);
+        AccRange[0][0] = ID[0];
+      });
+    });
+    myQueue.wait();
+  }
+  check("Counter = ", Counter, size * 10 * 10);
+}
+
 int main() {
   int x;
 
@@ -155,6 +176,7 @@ int main() {
   try_id1(x);
   try_id2(x);
   try_id3(x);
+  try_unnamed_lambda(x);
 
   x = 256;
   try_item1(x);
@@ -163,6 +185,7 @@ int main() {
   try_id1(x);
   try_id2(x);
   try_id3(x);
+  try_unnamed_lambda(x);
 
   return 0;
 }
@@ -182,6 +205,8 @@ int main() {
 // CHECK-NEXT:  Counter = 15000
 // CHECK-NEXT:  parallel_for range adjusted from 1500 to 1504
 // CHECK-NEXT:  Counter = 150000
+// CHECK-NEXT:  parallel_for range adjusted from 1500 to 1504
+// CHECK-NEXT:  Counter = 150000
 // CHECK-NEXT:  Size seen by user = 256
 // CHECK-NEXT:  Counter = 256
 // CHECK-NEXT:  Size seen by user = 256
@@ -191,3 +216,4 @@ int main() {
 // CHECK-NEXT:  Counter = 256
 // CHECK-NEXT:  Counter = 2560
 // CHECK-NEXT:  Counter = 25600
+// CHECK-NEXT:  Counter = 25600