diff --git a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp index 0411c67013342..18076f8082d0f 100644 --- a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp +++ b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp @@ -3203,6 +3203,7 @@ Error AMDGPUKernelTy::launchImpl(GenericDeviceTy &GenericDevice, ImplArgs->GroupSizeY = 1; ImplArgs->GroupSizeZ = 1; ImplArgs->GridDims = 1; + ImplArgs->DynamicLdsSize = KernelArgs.DynCGroupMem; } // Push the kernel launch into the stream. diff --git a/openmp/libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h b/openmp/libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h index 2471590c27b37..58a3b5df00fac 100644 --- a/openmp/libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h +++ b/openmp/libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h @@ -45,7 +45,9 @@ struct AMDGPUImplicitArgsTy { uint16_t GroupSizeZ; uint8_t Unused0[46]; // 46 byte offset. uint16_t GridDims; - uint8_t Unused1[190]; // 190 byte offset. + uint8_t Unused1[54]; // 54 byte offset. + uint32_t DynamicLdsSize; + uint8_t Unused2[132]; // 132 byte offset. }; // Dummy struct for COV4 implicitargs.