[Openmp-commits] [openmp] [libomptarget][nextgen-plugin] Use SCRELEASE/SCACQUIRE in packet headers (PR #85678)

[Gheorghe-Teodor Bercea via Openmp-commits]

https://github.com/doru1004 created https://github.com/llvm/llvm-project/pull/85678

This patch updates the construction of packet headers to replace the usage of ACQUIRE/RELEASE with SCACQUIRE/SCRELEASE which is now recommended.
The patch also fixes a potential source of problems by ensuring the atomic store operation refers to the header field directly and doesn't rely on it being the first field in the packet struct. 

>From e2a0e035854a3db1837cc1b43a20b4a173d3ada9 Mon Sep 17 00:00:00 2001
From: Doru Bercea <doru.bercea at amd.com>
Date: Mon, 18 Mar 2024 13:52:32 -0400
Subject: [PATCH] Use SCRELEASE/SCACQUIRE in packet header

---
 .../plugins-nextgen/amdgpu/src/rtl.cpp        | 21 +++++++++----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
index fce7454bf2800d..886d8732d088fc 100644
--- a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -826,15 +826,14 @@ struct AMDGPUQueueTy {
   /// Assumes the queue lock is acquired.
   void publishKernelPacket(uint64_t PacketId, uint16_t Setup,
                            hsa_kernel_dispatch_packet_t *Packet) {
-    uint32_t *PacketPtr = reinterpret_cast<uint32_t *>(Packet);
-
-    uint16_t Header = HSA_PACKET_TYPE_KERNEL_DISPATCH << HSA_PACKET_HEADER_TYPE;
-    Header |= HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_ACQUIRE_FENCE_SCOPE;
-    Header |= HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_RELEASE_FENCE_SCOPE;
+    uint16_t Header =
+        (HSA_PACKET_TYPE_KERNEL_DISPATCH << HSA_PACKET_HEADER_TYPE) |
+        (HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_SCACQUIRE_FENCE_SCOPE) |
+        (HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_SCRELEASE_FENCE_SCOPE);
 
     // Publish the packet. Do not modify the package after this point.
     uint32_t HeaderWord = Header | (Setup << 16u);
-    __atomic_store_n(PacketPtr, HeaderWord, __ATOMIC_RELEASE);
+    __atomic_store_n((uint32_t *)&Packet->header, HeaderWord, __ATOMIC_RELEASE);
 
     // Signal the doorbell about the published packet.
     hsa_signal_store_relaxed(Queue->doorbell_signal, PacketId);
@@ -845,15 +844,15 @@ struct AMDGPUQueueTy {
   /// barrier dependencies (signals) are satisfied. Assumes the queue is locked
   void publishBarrierPacket(uint64_t PacketId,
                             hsa_barrier_and_packet_t *Packet) {
-    uint32_t *PacketPtr = reinterpret_cast<uint32_t *>(Packet);
     uint16_t Setup = 0;
-    uint16_t Header = HSA_PACKET_TYPE_BARRIER_AND << HSA_PACKET_HEADER_TYPE;
-    Header |= HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_ACQUIRE_FENCE_SCOPE;
-    Header |= HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_RELEASE_FENCE_SCOPE;
+    uint16_t Header =
+        (HSA_PACKET_TYPE_BARRIER_AND << HSA_PACKET_HEADER_TYPE) |
+        (HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_SCACQUIRE_FENCE_SCOPE) |
+        (HSA_FENCE_SCOPE_SYSTEM << HSA_PACKET_HEADER_SCRELEASE_FENCE_SCOPE);
 
     // Publish the packet. Do not modify the package after this point.
     uint32_t HeaderWord = Header | (Setup << 16u);
-    __atomic_store_n(PacketPtr, HeaderWord, __ATOMIC_RELEASE);
+    __atomic_store_n((uint32_t *)&Packet->header, HeaderWord, __ATOMIC_RELEASE);
 
     // Signal the doorbell about the published packet.
     hsa_signal_store_relaxed(Queue->doorbell_signal, PacketId);