From 9fa32bdad0735798cb5401666baccb55b1da4a7b Mon Sep 17 00:00:00 2001
From: Swung0x48 <swung0x48@outlook.com>
Date: Thu, 30 Jul 2026 02:45:39 -0400
Subject: [PATCH] [Fix] (DirectVulkan): declare only the used colour attachment
 span per subpass

- every render pass declared colorAttachmentCount=8 (the full GL draw-buffer
  slot span) with trailing VK_ATTACHMENT_UNUSED references, and Adreno
  configures its per-pixel render-backend/export path from the DECLARED
  count - so every fragment of every pass paid an 8-render-target export
  cost; this was the bulk of the 1.5x per-pixel gap against
  MobileGlues+ANGLE on the same Qualcomm driver (their subpasses declare
  exactly the used span)
- measured on Adreno 650 / MC 26.2 / 1440x3044: total GPU frame time
  11.9 -> 7.5 ms (-37%, now below ANGLE's 7.87 ms), the single-quad
  swapchain blit pass alone 1.26 -> 0.40 ms, steady in-world FPS 82.8 -> 123
  under the standard cooled-start protocol, matching the
  MobileGlues+ANGLE+system-Vulkan benchmark of 123.8
- trailing UNUSED references are popped before the subpass is built (the
  entry's colorAttachmentCount and every pipeline's colour-blend span follow
  it); interior GL_NONE holes keep their slots so fragment-output locations
  still line up
- the pipeline-side fragmentOutputMask check downgrades from assert to a
  debug log: an output at a location past the trimmed span is discarded,
  which is GL's defined behaviour for a draw buffer set to GL_NONE
---
 .../Renderer/VkRenderPassManager.cpp             | 16 ++++++++++++++++
 .../DirectVulkan/Renderer/VulkanRenderer.cpp     | 15 +++++++++------
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp b/MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp
index 99c0671a..40985d90 100644
--- a/MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp
+++ b/MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp
@@ -1187,6 +1187,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         const Bool hasDepthStencilAttachment = depthAttachmentRef.attachment != VK_ATTACHMENT_UNUSED;
 
+        // Declare only the used colour-reference span. The GL draw-buffer array
+        // always spans 8 slots, so passes used to declare colorAttachmentCount=8
+        // with trailing VK_ATTACHMENT_UNUSED holes - and Adreno configures its
+        // per-pixel render-backend/export path from the DECLARED count, so every
+        // fragment of every pass paid the 8-target export cost (measured on
+        // Adreno 650 / MC 26.2: 11.9 -> 7.5 ms of GPU time per frame, with the
+        // single-quad swapchain blit pass alone dropping 1.26 -> 0.40 ms).
+        // Interior GL_NONE holes keep their slots so fragment-output locations
+        // still line up; a fragment output at a location past the trimmed count
+        // is discarded, which is exactly GL's semantic for writing to a draw
+        // buffer set to GL_NONE.
+        while (!colorAttachmentRefs.empty() &&
+               colorAttachmentRefs.back().attachment == VK_ATTACHMENT_UNUSED) {
+            colorAttachmentRefs.pop_back();
+        }
+
         // Subpass
         VkSubpassDescription subpassDesc;
         subpassDesc.flags = 0;
diff --git a/MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp b/MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp
index 8b653a6c..6bb989f5 100644
--- a/MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp
+++ b/MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp
@@ -4041,12 +4041,15 @@ void main() {
             payload.backStencilCompareOp = VK_COMPARE_OP_ALWAYS;
         }
         const Uint32 fragmentOutputMask = programObj.activeFragmentOutputLocationMask;
-        MOBILEGL_ASSERT(
-            (fragmentOutputMask >> payload.colorAttachmentCount) == 0,
-            "GetOrCreatePipeline: fragmentOutputMask=0x%x exceeds colorAttachmentCount=%u for program=%u",
-            fragmentOutputMask,
-            payload.colorAttachmentCount,
-            program.GetExternalIndex());
+        // Outputs at locations past the render pass's trimmed colour span are
+        // simply discarded - GL's semantic for a fragment output whose draw
+        // buffer is GL_NONE (the trailing UNUSED slots no longer occupy
+        // references, see GetOrCreateRenderPass).
+        if ((fragmentOutputMask >> payload.colorAttachmentCount) != 0) {
+            MGLOG_D("GetOrCreatePipeline: fragmentOutputMask=0x%x exceeds colorAttachmentCount=%u for program=%u; "
+                    "outputs past the span are discarded",
+                    fragmentOutputMask, payload.colorAttachmentCount, program.GetExternalIndex());
+        }
         MOBILEGL_ASSERT(payload.colorAttachmentCount <= PipelineFactory::PipelineCreatePayload::kMaxColorAttachments,
                         "GetOrCreatePipeline: colorAttachmentCount=%u exceeds payload capacity",
                         payload.colorAttachmentCount);