================
@@ -515,8 +524,60 @@ Error GenericKernelTy::launch(GenericDeviceTy
&GenericDevice, void **ArgPtrs,
llvm::SmallVector<void *, 16> Args;
llvm::SmallVector<void *, 16> Ptrs;
+ uint32_t NumThreads[3] = {KernelArgs.ThreadLimit[0],
+ KernelArgs.ThreadLimit[1],
+ KernelArgs.ThreadLimit[2]};
+ uint32_t NumBlocks[3] = {KernelArgs.NumTeams[0], KernelArgs.NumTeams[1],
+ KernelArgs.NumTeams[2]};
+ if (!isBareMode()) {
+ NumThreads[0] = getNumThreads(GenericDevice, NumThreads);
+ NumBlocks[0] = getNumBlocks(GenericDevice, NumBlocks, KernelArgs.Tripcount,
+ NumThreads[0], KernelArgs.ThreadLimit[0] > 0);
+ }
+
+ uint32_t MaxBlockMemSize = GenericDevice.getMaxBlockSharedMemSize();
+ uint32_t DynBlockMemSize = KernelArgs.DynCGroupMem;
+ uint32_t TotalBlockMemSize = StaticBlockMemSize + DynBlockMemSize;
+ if (StaticBlockMemSize > MaxBlockMemSize)
+ return Plugin::error(ErrorCode::INVALID_ARGUMENT,
+ "Static block memory size exceeds maximum");
+ else if (static_cast<DynCGroupMemFallbackType>(
+ KernelArgs.Flags.DynCGroupMemFallback) ==
+ DynCGroupMemFallbackType::Abort &&
+ TotalBlockMemSize > MaxBlockMemSize)
+ return Plugin::error(
+ ErrorCode::INVALID_ARGUMENT,
+ "Static and dynamic block memory size exceeds maximum");
+
+ void *DynBlockMemFbPtr = nullptr;
+ uint32_t DynBlockMemLaunchSize = DynBlockMemSize;
+
+ DynCGroupMemFallbackType DynBlockMemFb = DynCGroupMemFallbackType::None;
+ if (DynBlockMemSize && (!GenericDevice.hasNativeBlockSharedMem() ||
----------------
kevinsala wrote:
For case a), the developers of such a feature should account for that amount of
dynamic shared memory (effectively reducing the amount available for the OpenMP
user).
https://github.com/llvm/llvm-project/pull/152831
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
