gpu-compute: Store accum_offset from code object in WF

The accumulation offset is needed for some instructions. In order to
access this value we need to place it somewhere instruction definitions
can access. The most logical place is in the wavefront.

This commit simply copies the value from the HSA task to the wavefront
object.

Change-Id: I44ef62ef32d2421953f096c431dd758e882245b4

src/gpu-compute/gpu_command_processor.cc

@@ -723,7 +723,6 @@ GPUCommandProcessor::sanityCheckAKC(AMDKernelCode *akc)
     warn_if(akc->kernarg_preload_spec_length ||
             akc->kernarg_preload_spec_offset,
             "Kernarg preload not implemented\n");
-    warn_if(akc->accum_offset, "ACC offset not implemented\n");
     warn_if(akc->tg_split, "TG split not implemented\n");
 }
 

src/gpu-compute/hsa_queue_entry.hh

@@ -122,6 +122,11 @@ class HSAQueueEntry
         }
 
         parseKernelCode(akc);
+
+        // Offset of a first AccVGPR in the unified register file.
+        // Granularity 4. Value 0-63. 0 - accum-offset = 4,
+        // 1 - accum-offset = 8, ..., 63 - accum-offset = 256.
+        _accumOffset = (akc->accum_offset + 1) * 4;
     }
 
     const GfxVersion&
@@ -394,6 +399,12 @@ class HSAQueueEntry
         assert(_outstandingWbs >= 0);
     }
 
+    unsigned
+    accumOffset() const
+    {
+        return _accumOffset;
+    }
+
   private:
     void
     parseKernelCode(AMDKernelCode *akc)
@@ -489,6 +500,8 @@ class HSAQueueEntry
 
     std::bitset<NumVectorInitFields> initialVgprState;
     std::bitset<NumScalarInitFields> initialSgprState;
+
+    unsigned _accumOffset;
 };
 
 } // namespace gem5

src/gpu-compute/wavefront.cc

@@ -430,6 +430,9 @@ Wavefront::initRegState(HSAQueueEntry *task, int wgSizeInWorkItems)
         }
     }
 
+    // Save the offset to the first accumulation VGPR number from HSA task.
+    accumOffset = task->accumOffset();
+
     regInitIdx = 0;
 
     // VGPRs are initialized to the work item IDs for a given thread. There

src/gpu-compute/wavefront.hh

@@ -131,6 +131,8 @@ class Wavefront : public SimObject
     uint32_t maxVgprs;
     // number of SGPRs required by WF
     uint32_t maxSgprs;
+    // first accumulation vgpr number
+    uint32_t accumOffset;
     void freeResources();
     GPUDynInstPtr nextInstr();
     void setStatus(status_e newStatus);