[Openmp-commits] [openmp] [openmp][amdgpu] Add DynamicLdsSize to AMDGPUImplicitArgsTy (PR #65325)
via Openmp-commits
openmp-commits at lists.llvm.org
Mon Nov 13 22:05:45 PST 2023
https://github.com/skc7 updated https://github.com/llvm/llvm-project/pull/65325
>From eb41bbf8ad09395d72b2967ba5745d8c2957bef6 Mon Sep 17 00:00:00 2001
From: skc7 <Krishna.Sankisa at amd.com>
Date: Tue, 5 Sep 2023 14:46:05 +0530
Subject: [PATCH] [openmp][amdgpu] Add DynamicLdsSize to AMDGPUImplicitArgsTy
---
openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp | 1 +
.../libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h | 4 +++-
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
index 399a71390a65abe..877b7d0f88aa883 100644
--- a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -3092,6 +3092,7 @@ 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 b39545ab7d02ba2..34d179c2996fe28 100644
--- a/openmp/libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h
+++ b/openmp/libomptarget/plugins-nextgen/amdgpu/utils/UtilitiesRTL.h
@@ -43,7 +43,9 @@ 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.
More information about the Openmp-commits
mailing list