arch-gcn3,arch-vega: Select proper data on misaligned access

req1->getSize() returns the size in bytes, but because we're using it in an array index, we need to scale it by the size of the data type. This ensures we give the second request the proper data. Change-Id: I578665406762d5d0c95f2ea8297c362e1cc0620b Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/54503 Reviewed-by: Matt Sinclair <[email protected]> Maintainer: Matt Sinclair <[email protected]> Tested-by: kokoro <[email protected]> Reviewed-by: Matthew Poremba <[email protected]>
darchr · Dec 20, 2021 · f9deeea · f9deeea
1 parent c70403e
commit f9deeea
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/src/arch/amdgpu/gcn3/gpu_mem_helpers.hh b/src/arch/amdgpu/gcn3/gpu_mem_helpers.hh
@@ -107,7 +107,8 @@ initMemReqHelper(GPUDynInstPtr gpuDynInst, MemCmd mem_req_type,
                 pkt1->dataStatic(&(reinterpret_cast<T*>(
                     gpuDynInst->d_data))[lane * N]);
                 pkt2->dataStatic(&(reinterpret_cast<T*>(
-                    gpuDynInst->d_data))[lane * N + req1->getSize()]);
+                    gpuDynInst->d_data))[lane * N +
+                                         req1->getSize()/sizeof(T)]);
                 DPRINTF(GPUMem, "CU%d: WF[%d][%d]: index: %d unaligned memory "
                         "request for %#x\n", gpuDynInst->cu_id,
                         gpuDynInst->simdId, gpuDynInst->wfSlotId, lane,

diff --git a/src/arch/amdgpu/vega/gpu_mem_helpers.hh b/src/arch/amdgpu/vega/gpu_mem_helpers.hh
@@ -107,7 +107,8 @@ initMemReqHelper(GPUDynInstPtr gpuDynInst, MemCmd mem_req_type,
                 pkt1->dataStatic(&(reinterpret_cast<T*>(
                     gpuDynInst->d_data))[lane * N]);
                 pkt2->dataStatic(&(reinterpret_cast<T*>(
-                    gpuDynInst->d_data))[lane * N + req1->getSize()]);
+                    gpuDynInst->d_data))[lane * N +
+                                         req1->getSize()/sizeof(T)]);
                 DPRINTF(GPUMem, "CU%d: WF[%d][%d]: index: %d unaligned memory "
                         "request for %#x\n", gpuDynInst->cu_id,
                         gpuDynInst->simdId, gpuDynInst->wfSlotId, lane,