engine/rr: native Ray Reconstruction stages with capture/replay and shim integration

- engine/rr: d4r's own shaders for the denoiser frame (exposure, six encoders,
  five decoders, hkpn output stage) at NGX layouts, plus PTX->GLSL/HIP packing
  scripts, reference implementations and weight extraction
- runtime.h/runtime_rr.inc, game_rr.{h,cpp}: GameDenoiser wired into the engine
  build (d4r-rr replay binary) and the D3D12 shim's feature-13 path
- shim: answer GetFeatureRequirements from d4r's own state only (the old
  cross-binary CUDA handoff crashed OptiScaler's scan); drop the core's
  CUDA GetFeatureRequirements import
- shim/harness: exact guide capture/replay of a frame's RR inputs
- kernels/rr: expanded enc0/engine prototypes; kernels/tools: ptxsim rewrite
  plus rrsim and an engine test; vulkan: ptx2glsl FP8/cooperative-matrix
  support, kvk inout buffers and KVK_DISABLE_OPTIMIZATION
- bridge: report the surface array in cuSurfObjectCreate traces
- packaging: RR settings and the ICU launch overrides in D4R_README

engine/runtime.cpp

@@ -2,8 +2,11 @@
 #include "vk_dispatch.h"
 #include <algorithm>
 #include <cmath>
+#include <cstdlib>
 #include <cstring>
 #include <fstream>
+#include <map>
+#include <sstream>
 #include <stdexcept>
 #include <vector>
 
@@ -139,7 +142,7 @@ struct Pipeline {
         if (descriptors) vkDestroyDescriptorSetLayout(device, descriptors, nullptr);
     }
     void create(VkDevice dev, const std::string& file, const std::vector<VkDescriptorType>& types,
-                uint32_t subgroup, VkPipelineCache cache) {
+                uint32_t subgroup, VkPipelineCache cache, VkPipelineCreateFlags flags = 0) {
         device = dev;
         std::vector<VkDescriptorSetLayoutBinding> bindings;
         for (uint32_t i = 0; i < types.size(); ++i)
@@ -161,7 +164,7 @@ struct Pipeline {
         VkPipelineShaderStageRequiredSubgroupSizeCreateInfo required{VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_REQUIRED_SUBGROUP_SIZE_CREATE_INFO};
         required.requiredSubgroupSize = subgroup;
         VkComputePipelineCreateInfo ci{VK_STRUCTURE_TYPE_COMPUTE_PIPELINE_CREATE_INFO};
-        ci.layout = layout;
+        ci.layout = layout; ci.flags = flags;
         ci.stage = {VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO, &required,
                     VK_PIPELINE_SHADER_STAGE_CREATE_REQUIRE_FULL_SUBGROUPS_BIT, VK_SHADER_STAGE_COMPUTE_BIT, shader, "main", nullptr};
         VkResult result = vkCreateComputePipelines(dev, cache, 1, &ci, nullptr, &handle);
@@ -779,4 +782,5 @@ VkDeviceSize Engine::networkHeadBytes(uint32_t outputWidth, uint32_t outputHeigh
 }
 VkDeviceSize Engine::activationBytes() const { return impl->activations; }
 #include "runtime_m.inc"
+#include "runtime_rr.inc"
 } // namespace d4r