gpu-compute,arch-vega: Overhaul HWRegs, setreg, getreg

These instructions are supposed to be read/writing special shader
hardware registers. Currently they are getting/setting to an SGPR. This
results in getting incorrect registers at best and clobbering an SGPR
being used by an application at worst. Furthermore, some registers need
to be set in the shader and the application will never (can never) set
them.

This patch overhauls the getreg/setreg instructions to use different
storage in the shader. The values will be updated either via setreg from
an application (e.g., mode register) or set by a PM4 MAP_PROCESS.

Change-Id: Ie5e5d552bd04dc47f5b35b5ee40a569ae345abac
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/61655
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>

src/gpu-compute/shader.hh

@@ -88,6 +88,9 @@ class Shader : public ClockedObject
     ApertureRegister _scratchApe;
     Addr shHiddenPrivateBaseVmid;
 
+    // Hardware regs accessed by getreg/setreg instructions, set by queues
+    std::unordered_map<int, uint32_t> hwRegs;
+
     // Number of active Cus attached to this shader
     int _activeCus;
 
@@ -109,6 +112,18 @@ class Shader : public ClockedObject
     ThreadContext *gpuTc;
     BaseCPU *cpuPointer;
 
+    void
+    setHwReg(int regIdx, uint32_t val)
+    {
+        hwRegs[regIdx] = val;
+    }
+
+    uint32_t
+    getHwReg(int regIdx)
+    {
+        return hwRegs[regIdx];
+    }
+
     const ApertureRegister&
     gpuVmApe() const
     {