Merge pull request #48947 from fwyzard/update_warpsize_for_ROCm_7.0

Update the compile-time warp size constant for ROCm 7.0

Author: cmsbuild

HeterogeneousCore/AlpakaInterface/interface/warpsize.h

@@ -12,8 +12,20 @@ namespace cms::alpakatools {
   // CUDA always has a warp size of 32
   inline constexpr int warpSize = 32;
 #elif defined(__HIP_DEVICE_COMPILE__)
-  // HIP/ROCm defines warpSize as a constant expression in device code, with value 32 or 64 depending on the target device
-  inline constexpr int warpSize = ::warpSize;
+  // HIP/ROCm may have a warp size of 32 or 64 depending on the target device
+#if defined(__gfx900__) or defined(__gfx902__) or defined(__gfx903__) or defined(__gfx906__) or defined(__gfx908__) or \
+    defined(__gfx909__) or defined(__gfx90a__) or defined(__gfx90c__) or defined(__gfx942__) or defined(__gfx950__)
+  inline constexpr int warpSize = 64;
+#elif defined(__gfx1010__) or defined(__gfx1011__) or defined(__gfx1012__) or defined(__gfx1013__) or \
+    defined(__gfx1030__) or defined(__gfx1031__) or defined(__gfx1032__) or defined(__gfx1033__) or   \
+    defined(__gfx1034__) or defined(__gfx1035__) or defined(__gfx1036__) or defined(__gfx1100__) or   \
+    defined(__gfx1101__) or defined(__gfx1102__) or defined(__gfx1103__) or defined(__gfx1150__) or   \
+    defined(__gfx1151__) or defined(__gfx1152__) or defined(__gfx1153__) or defined(__gfx1200__) or   \
+    defined(__gfx1201__) or defined(__gfx1250__) or defined(__gfx1251__)
+  inline constexpr int warpSize = 32;
+#else
+#error "Unknown AMDGCN architecture"
+#endif
 #else
   // CPU back-ends always have a warp size of 1
   inline constexpr int warpSize = 1;

HeterogeneousCore/AlpakaInterface/test/alpaka/testPrefixScan.dev.cc

@@ -12,6 +12,7 @@
 #include "HeterogeneousCore/AlpakaInterface/interface/memory.h"
 #include "HeterogeneousCore/AlpakaInterface/interface/workdivision.h"
 #include "HeterogeneousCore/AlpakaInterface/interface/prefixScan.h"
+#include "HeterogeneousCore/AlpakaInterface/interface/warpsize.h"
 
 using namespace cms::alpakatools;
 using namespace ALPAKA_ACCELERATOR_NAMESPACE;
@@ -33,17 +34,8 @@ struct format_traits<float> {
 template <typename T>
 struct testPrefixScan {
   ALPAKA_FN_ACC void operator()(Acc1D const& acc, unsigned int size) const {
-    // alpaka::warp::getSize(acc) is runtime, but we need a compile-time or constexpr value
-#if defined(__CUDA_ARCH__)
-    // CUDA always has a warp size of 32
-    auto& ws = alpaka::declareSharedVar<T[32], __COUNTER__>(acc);
-#elif defined(__HIP_DEVICE_COMPILE__)
-    // HIP/ROCm defines warpSize as a constant expression with value 32 or 64 depending on the target device
-    auto& ws = alpaka::declareSharedVar<T[warpSize], __COUNTER__>(acc);
-#else
-    // CPU back-ends always have a warp size of 1
-    auto& ws = alpaka::declareSharedVar<T[1], __COUNTER__>(acc);
-#endif
+    // alpaka::warp::getSize(acc) is runtime, but we need a compile-time or constexpr value, so we use cms::alpakatools::warpSize
+    auto& ws = alpaka::declareSharedVar<T[cms::alpakatools::warpSize], __COUNTER__>(acc);
     auto& c = alpaka::declareSharedVar<T[1024], __COUNTER__>(acc);
     auto& co = alpaka::declareSharedVar<T[1024], __COUNTER__>(acc);