intel/compiler: Make MAX_VGRF_SIZE macro depend on devinfo and update it for Xe2.

Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25020>

src/intel/compiler/brw_fs.cpp

@@ -2320,7 +2320,7 @@ fs_visitor::split_virtual_grfs()
          if (split_points[reg]) {
             has_splits = true;
             vgrf_has_split[i] = true;
-            assert(offset <= MAX_VGRF_SIZE);
+            assert(offset <= MAX_VGRF_SIZE(devinfo));
             unsigned grf = alloc.allocate(offset);
             for (unsigned k = reg - offset; k < reg; k++)
                new_virtual_grf[k] = grf;
@@ -2332,7 +2332,7 @@ fs_visitor::split_virtual_grfs()
       }
 
       /* The last one gets the original register number */
-      assert(offset <= MAX_VGRF_SIZE);
+      assert(offset <= MAX_VGRF_SIZE(devinfo));
       alloc.sizes[i] = offset;
       for (unsigned k = reg - offset; k < reg; k++)
          new_virtual_grf[k] = i;

src/intel/compiler/brw_fs_reg_allocate.cpp

@@ -116,7 +116,7 @@ brw_alloc_reg_set(struct brw_compiler *compiler, int dispatch_width)
     * texturing.
     */
    int class_sizes[REG_CLASS_COUNT];
-   assert(REG_CLASS_COUNT == MAX_VGRF_SIZE);
+   assert(REG_CLASS_COUNT == MAX_VGRF_SIZE(devinfo));
    for (unsigned i = 0; i < REG_CLASS_COUNT; i++)
       class_sizes[i] = i + 1;
 

src/intel/compiler/brw_fs_register_coalesce.cpp

@@ -196,10 +196,10 @@ fs_visitor::register_coalesce()
    int src_size = 0;
    int channels_remaining = 0;
    unsigned src_reg = ~0u, dst_reg = ~0u;
-   int dst_reg_offset[MAX_VGRF_SIZE];
+   int *dst_reg_offset = new int[MAX_VGRF_SIZE(devinfo)];
-   fs_inst *mov[MAX_VGRF_SIZE];
+   fs_inst **mov = new fs_inst *[MAX_VGRF_SIZE(devinfo)];
-   int dst_var[MAX_VGRF_SIZE];
+   int *dst_var = new int[MAX_VGRF_SIZE(devinfo)];
-   int src_var[MAX_VGRF_SIZE];
+   int *src_var = new int[MAX_VGRF_SIZE(devinfo)];
 
    foreach_block_and_inst(block, fs_inst, inst, cfg) {
       if (!is_coalesce_candidate(this, inst))
@@ -215,10 +215,10 @@ fs_visitor::register_coalesce()
          src_reg = inst->src[0].nr;
 
          src_size = alloc.sizes[inst->src[0].nr];
-         assert(src_size <= MAX_VGRF_SIZE);
+         assert(src_size <= MAX_VGRF_SIZE(devinfo));
 
          channels_remaining = src_size;
-         memset(mov, 0, sizeof(mov));
+         memset(mov, 0, sizeof(*mov) * MAX_VGRF_SIZE(devinfo));
 
          dst_reg = inst->dst.nr;
       }
@@ -340,5 +340,10 @@ fs_visitor::register_coalesce()
       invalidate_analysis(DEPENDENCY_INSTRUCTIONS);
    }
 
+   delete[] src_var;
+   delete[] dst_var;
+   delete[] mov;
+   delete[] dst_reg_offset;
+
    return progress;
 }

src/intel/compiler/brw_ir.h

@@ -35,7 +35,7 @@
  * SIMD32, each component takes up 4 GRFs, so we need to allow up to size-20
  * VGRFs to hold the result.
  */
-#define MAX_VGRF_SIZE 20
+#define MAX_VGRF_SIZE(devinfo) ((devinfo)->ver >= 20 ? 40 : 20)
 
 #ifdef __cplusplus
 struct backend_reg : private brw_reg

src/intel/compiler/brw_vec4_reg_allocate.cpp

@@ -102,7 +102,7 @@ brw_vec4_alloc_reg_set(struct brw_compiler *compiler)
     * SEND-from-GRF sources cannot be split, so we also need classes for each
     * potential message length.
     */
-   assert(REG_CLASS_COUNT == MAX_VGRF_SIZE);
+   assert(REG_CLASS_COUNT == MAX_VGRF_SIZE(compiler->devinfo));
    int class_sizes[REG_CLASS_COUNT];
 
    for (int i = 0; i < REG_CLASS_COUNT; i++)
@@ -178,7 +178,7 @@ vec4_visitor::reg_allocate()
 
    for (unsigned i = 0; i < alloc.count; i++) {
       int size = this->alloc.sizes[i];
-      assert(size >= 1 && size <= MAX_VGRF_SIZE);
+      assert(size >= 1 && size <= MAX_VGRF_SIZE(devinfo));
       ra_set_node_class(g, i, compiler->vec4_reg_set.classes[size - 1]);
 
       for (unsigned j = 0; j < i; j++) {