radv: Remove radv_bvh_aabb_node::aabb

It was only read by RRA which can infer it from the parenbt internal
node.

Change in average build time (Control):
84.69471 ms -> 84.25319 ms

Reviewed-by: Friedrich Vock <friedrich.vock@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22400>

src/amd/vulkan/bvh/bvh.h

@@ -181,11 +181,10 @@ struct radv_bvh_triangle_node {
 };
 
 struct radv_bvh_aabb_node {
-   radv_aabb aabb;
    uint32_t primitive_id;
    /* flags in upper 4 bits */
    uint32_t geometry_id_and_flags;
-   uint32_t reserved[8];
+   uint32_t reserved[14];
 };
 
 struct radv_bvh_instance_node {

src/amd/vulkan/bvh/encode.comp

@@ -84,7 +84,6 @@ encode_leaf_node(uint32_t type, uint64_t src_node, uint64_t dst_node)
       radv_ir_aabb_node src = DEREF(REF(radv_ir_aabb_node)(src_node));
       REF(radv_bvh_aabb_node) dst = REF(radv_bvh_aabb_node)(dst_node);
 
-      DEREF(dst).aabb = src.base.aabb;
       DEREF(dst).primitive_id = src.primitive_id;
       DEREF(dst).geometry_id_and_flags = src.geometry_id_and_flags;
       break;

src/amd/vulkan/radv_rra.c

@@ -22,6 +22,7 @@
  */
 
 #include "bvh/bvh.h"
+#include "util/half_float.h"
 #include "amd_family.h"
 #include "radv_private.h"
 #include "vk_acceleration_structure.h"
@@ -540,17 +541,18 @@ rra_transcode_triangle_node(struct rra_transcoding_context *ctx,
 }
 
 static void
-rra_transcode_aabb_node(struct rra_transcoding_context *ctx, const struct radv_bvh_aabb_node *src)
+rra_transcode_aabb_node(struct rra_transcoding_context *ctx, const struct radv_bvh_aabb_node *src,
+                        radv_aabb bounds)
 {
    struct rra_aabb_node *dst = (struct rra_aabb_node *)(ctx->dst + ctx->dst_leaf_offset);
    ctx->dst_leaf_offset += sizeof(struct rra_aabb_node);
 
-   dst->aabb[0][0] = src->aabb.min.x;
+   dst->aabb[0][0] = bounds.min.x;
-   dst->aabb[0][1] = src->aabb.min.y;
+   dst->aabb[0][1] = bounds.min.y;
-   dst->aabb[0][2] = src->aabb.min.z;
+   dst->aabb[0][2] = bounds.min.z;
-   dst->aabb[1][0] = src->aabb.max.x;
+   dst->aabb[1][0] = bounds.max.x;
-   dst->aabb[1][1] = src->aabb.max.y;
+   dst->aabb[1][1] = bounds.max.y;
-   dst->aabb[1][2] = src->aabb.max.z;
+   dst->aabb[1][2] = bounds.max.z;
 
    dst->geometry_id = src->geometry_id_and_flags & 0xfffffff;
    dst->flags = src->geometry_id_and_flags >> 28;
@@ -579,7 +581,7 @@ rra_transcode_instance_node(struct rra_transcoding_context *ctx,
 }
 
 static uint32_t rra_transcode_node(struct rra_transcoding_context *ctx, uint32_t parent_id,
-                                   uint32_t src_id);
+                                   uint32_t src_id, radv_aabb bounds);
 
 static void
 rra_transcode_box16_node(struct rra_transcoding_context *ctx, const struct radv_bvh_box16_node *src)
@@ -596,8 +598,23 @@ rra_transcode_box16_node(struct rra_transcoding_context *ctx, const struct radv_
          continue;
       }
 
+      radv_aabb bounds = {
+         .min =
+            {
+               _mesa_half_to_float(src->coords[i][0][0]),
+               _mesa_half_to_float(src->coords[i][0][1]),
+               _mesa_half_to_float(src->coords[i][0][2]),
+            },
+         .max =
+            {
+               _mesa_half_to_float(src->coords[i][1][0]),
+               _mesa_half_to_float(src->coords[i][1][1]),
+               _mesa_half_to_float(src->coords[i][1][2]),
+            },
+      };
+
       dst->children[i] =
-         rra_transcode_node(ctx, radv_bvh_node_box16 | (dst_offset >> 3), src->children[i]);
+         rra_transcode_node(ctx, radv_bvh_node_box16 | (dst_offset >> 3), src->children[i], bounds);
    }
 }
 
@@ -616,8 +633,8 @@ rra_transcode_box32_node(struct rra_transcoding_context *ctx, const struct radv_
          continue;
       }
 
-      dst->children[i] =
+      dst->children[i] = rra_transcode_node(ctx, radv_bvh_node_box32 | (dst_offset >> 3),
-         rra_transcode_node(ctx, radv_bvh_node_box32 | (dst_offset >> 3), src->children[i]);
+                                            src->children[i], src->coords[i]);
    }
 }
 
@@ -638,7 +655,8 @@ get_geometry_id(const void *node, uint32_t node_type)
 }
 
 static uint32_t
-rra_transcode_node(struct rra_transcoding_context *ctx, uint32_t parent_id, uint32_t src_id)
+rra_transcode_node(struct rra_transcoding_context *ctx, uint32_t parent_id, uint32_t src_id,
+                   radv_aabb bounds)
 {
    uint32_t node_type = src_id & 7;
    uint32_t src_offset = (src_id & (~7u)) << 3;
@@ -658,7 +676,7 @@ rra_transcode_node(struct rra_transcoding_context *ctx, uint32_t parent_id, uint
       if (node_type == radv_bvh_node_triangle)
          rra_transcode_triangle_node(ctx, src_child_node);
       else if (node_type == radv_bvh_node_aabb)
-         rra_transcode_aabb_node(ctx, src_child_node);
+         rra_transcode_aabb_node(ctx, src_child_node, bounds);
       else if (node_type == radv_bvh_node_instance)
          rra_transcode_instance_node(ctx, src_child_node);
    }
@@ -811,7 +829,7 @@ rra_dump_acceleration_structure(struct radv_rra_accel_struct_data *accel_struct,
       .leaf_indices = leaf_indices,
    };
 
-   rra_transcode_node(&ctx, 0xFFFFFFFF, RADV_BVH_ROOT_NODE);
+   rra_transcode_node(&ctx, 0xFFFFFFFF, RADV_BVH_ROOT_NODE, header->aabb);
 
    struct rra_accel_struct_chunk_header chunk_header = {
       .metadata_offset = 0,

src/amd/vulkan/radv_rt_common.c

@@ -502,8 +502,9 @@ insert_traversal_aabb_case(struct radv_device *device, nir_builder *b,
 
    struct radv_leaf_intersection intersection;
    intersection.node_addr = build_node_to_addr(device, b, bvh_node, false);
-   nir_ssa_def *triangle_info =
+   nir_ssa_def *triangle_info = nir_build_load_global(
-      nir_build_load_global(b, 2, 32, nir_iadd_imm(b, intersection.node_addr, 24));
+      b, 2, 32,
+      nir_iadd_imm(b, intersection.node_addr, offsetof(struct radv_bvh_aabb_node, primitive_id)));
    intersection.primitive_id = nir_channel(b, triangle_info, 0);
    intersection.geometry_id_and_flags = nir_channel(b, triangle_info, 1);
    intersection.opaque = hit_is_opaque(b, nir_load_deref(b, args->vars.sbt_offset_and_flags),