From 10165a56e3b8b681f5778a89e348322662692c05 Mon Sep 17 00:00:00 2001
From: Tapish <narwal83@hzdr.de>
Date: Mon, 23 Sep 2024 09:30:13 +0200
Subject: [PATCH 1/2] For a single thread acc if the WorkDiv number of threads
 per block is more than one, throw a runtime error

---
 include/alpaka/acc/AccCpuOmp2Blocks.hpp | 7 +++++++
 include/alpaka/acc/AccCpuSerial.hpp     | 7 +++++++
 include/alpaka/acc/AccCpuTbbBlocks.hpp  | 7 +++++++
 3 files changed, 21 insertions(+)

diff --git a/include/alpaka/acc/AccCpuOmp2Blocks.hpp b/include/alpaka/acc/AccCpuOmp2Blocks.hpp
index df52d90d03bc..27661f58432a 100644
--- a/include/alpaka/acc/AccCpuOmp2Blocks.hpp
+++ b/include/alpaka/acc/AccCpuOmp2Blocks.hpp
@@ -189,6 +189,13 @@ namespace alpaka
                 TKernelFnObj const& kernelFnObj,
                 TArgs&&... args)
             {
+                if(workDiv.m_blockThreadExtent.prod() != static_cast<TIdx>(1u))
+                {
+                    throw std::runtime_error(
+                        "The given work division is not valid for a single thread Acc: "
+                        + getAccName<AccCpuOmp2Blocks<TDim, TIdx>>() + ". Threads per block should be 1!");
+                }
+
                 return TaskKernelCpuOmp2Blocks<TDim, TIdx, TKernelFnObj, TArgs...>(
                     workDiv,
                     kernelFnObj,
diff --git a/include/alpaka/acc/AccCpuSerial.hpp b/include/alpaka/acc/AccCpuSerial.hpp
index 4a4e8f0621a6..e1b223f89158 100644
--- a/include/alpaka/acc/AccCpuSerial.hpp
+++ b/include/alpaka/acc/AccCpuSerial.hpp
@@ -182,6 +182,13 @@ namespace alpaka
                 TKernelFnObj const& kernelFnObj,
                 TArgs&&... args)
             {
+                if(workDiv.m_blockThreadExtent.prod() != static_cast<TIdx>(1u))
+                {
+                    throw std::runtime_error(
+                        "The given work division is not valid for a single thread Acc: "
+                        + getAccName<AccCpuSerial<TDim, TIdx>>() + ". Threads per block should be 1!");
+                }
+
                 return TaskKernelCpuSerial<TDim, TIdx, TKernelFnObj, TArgs...>(
                     workDiv,
                     kernelFnObj,
diff --git a/include/alpaka/acc/AccCpuTbbBlocks.hpp b/include/alpaka/acc/AccCpuTbbBlocks.hpp
index 1d2c7aec5a58..d283523e7a5a 100644
--- a/include/alpaka/acc/AccCpuTbbBlocks.hpp
+++ b/include/alpaka/acc/AccCpuTbbBlocks.hpp
@@ -183,6 +183,13 @@ namespace alpaka
                 TKernelFnObj const& kernelFnObj,
                 TArgs&&... args)
             {
+                if(workDiv.m_blockThreadExtent.prod() != static_cast<TIdx>(1u))
+                {
+                    throw std::runtime_error(
+                        "The given work division is not valid for a single thread Acc: "
+                        + getAccName<AccCpuTbbBlocks<TDim, TIdx>>() + ". Threads per block should be 1!");
+                }
+
                 return TaskKernelCpuTbbBlocks<TDim, TIdx, TKernelFnObj, TArgs...>(
                     workDiv,
                     kernelFnObj,

From 70aca453c16f9d6bf686d0b3d0e126dda0571339 Mon Sep 17 00:00:00 2001
From: Tapish <narwal83@hzdr.de>
Date: Mon, 23 Sep 2024 15:07:59 +0200
Subject: [PATCH 2/2] Remove old exception throw

---
 include/alpaka/kernel/TaskKernelCpuOmp2Blocks.hpp | 4 ----
 include/alpaka/kernel/TaskKernelCpuSerial.hpp     | 5 -----
 include/alpaka/kernel/TaskKernelCpuTbbBlocks.hpp  | 5 -----
 3 files changed, 14 deletions(-)

diff --git a/include/alpaka/kernel/TaskKernelCpuOmp2Blocks.hpp b/include/alpaka/kernel/TaskKernelCpuOmp2Blocks.hpp
index d1e5f4b0574b..d3e1d396ddd6 100644
--- a/include/alpaka/kernel/TaskKernelCpuOmp2Blocks.hpp
+++ b/include/alpaka/kernel/TaskKernelCpuOmp2Blocks.hpp
@@ -826,10 +826,6 @@ namespace alpaka
 
             // The number of blocks in the grid.
             TIdx const numBlocksInGrid(gridBlockExtent.prod());
-            if(blockThreadExtent.prod() != static_cast<TIdx>(1u))
-            {
-                throw std::runtime_error("Only one thread per block allowed in the OpenMP 2.0 block accelerator!");
-            }
 
             // Get the OpenMP schedule information for the given kernel and parameter types
             auto const schedule = std::apply(
diff --git a/include/alpaka/kernel/TaskKernelCpuSerial.hpp b/include/alpaka/kernel/TaskKernelCpuSerial.hpp
index 2889ac3d2a19..a9a370d1cbba 100644
--- a/include/alpaka/kernel/TaskKernelCpuSerial.hpp
+++ b/include/alpaka/kernel/TaskKernelCpuSerial.hpp
@@ -79,11 +79,6 @@ namespace alpaka
                 *static_cast<WorkDivMembers<TDim, TIdx> const*>(this),
                 blockSharedMemDynSizeBytes);
 
-            if(blockThreadExtent.prod() != static_cast<TIdx>(1u))
-            {
-                throw std::runtime_error("A block for the serial accelerator can only ever have one single thread!");
-            }
-
             // Execute the blocks serially.
             meta::ndLoopIncIdx(
                 gridBlockExtent,
diff --git a/include/alpaka/kernel/TaskKernelCpuTbbBlocks.hpp b/include/alpaka/kernel/TaskKernelCpuTbbBlocks.hpp
index 0bc578ccc5a1..4ca90dd5d3f4 100644
--- a/include/alpaka/kernel/TaskKernelCpuTbbBlocks.hpp
+++ b/include/alpaka/kernel/TaskKernelCpuTbbBlocks.hpp
@@ -83,11 +83,6 @@ namespace alpaka
             // The number of blocks in the grid.
             TIdx const numBlocksInGrid = gridBlockExtent.prod();
 
-            if(blockThreadExtent.prod() != static_cast<TIdx>(1u))
-            {
-                throw std::runtime_error("A block for the TBB accelerator can only ever have one single thread!");
-            }
-
             tbb::this_task_arena::isolate(
                 [&]
                 {