From e436c6b7c71fa46d5fefab2e8506f70f8566bf44 Mon Sep 17 00:00:00 2001
From: Joe McLaren <236280545+parallelArchitect@users.noreply.github.com>
Date: Wed, 15 Apr 2026 06:50:48 -0400
Subject: [PATCH] Fix NVML memory reporting regression on coherent UMA
 platforms (Fixes #449)

On GB10 / DGX Spark, nvmlDeviceGetMemoryInfo returns NVML_SUCCESS with
total == system MemTotal (~121GB). This prevents has_unified_memory from
being set, causing incorrect VRAM reporting and broken memory graph since 3.3.1.

Fix: detect UMA by comparing NVML total against /proc/meminfo MemTotal.
If total >= 90% of system RAM, classify as unified memory and use
MemAvailable instead of MemTotal for display.

Note: requires validation on GB10 / DGX Spark hardware. Author does not
have access to a coherent UMA system.
---
 src/extract_gpuinfo_nvidia.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/src/extract_gpuinfo_nvidia.c b/src/extract_gpuinfo_nvidia.c
index 5ba298cc..7c637058 100644
--- a/src/extract_gpuinfo_nvidia.c
+++ b/src/extract_gpuinfo_nvidia.c
@@ -655,9 +655,24 @@ static void gpuinfo_nvidia_refresh_dynamic_info(struct gpu_info *_gpu_info) {
     memory_info.version = 2;
     last_nvml_return_status = nvmlDeviceGetMemoryInfo_v2(device, &memory_info);
     if (last_nvml_return_status == NVML_SUCCESS) {
-      // Check if this is a unified memory GPU (total == 0 indicates unified memory)
       got_meminfo = true;
-      if (memory_info.total == 0) {
+      // Detect coherent UMA platforms (e.g. GB10 Grace Blackwell):
+      // NVML returns NVML_SUCCESS but total == full system MemTotal.
+      // This is not usable VRAM — treat as unified memory and use MemAvailable.
+      unsigned long long sys_mem_total = 0;
+      FILE *mf = fopen("/proc/meminfo", "r");
+      if (mf) {
+        char ml[256];
+        while (fgets(ml, sizeof(ml), mf)) {
+          if (sscanf(ml, "MemTotal: %llu kB", &sys_mem_total) == 1) {
+            sys_mem_total *= 1024;
+            break;
+          }
+        }
+        fclose(mf);
+      }
+      if (memory_info.total == 0 ||
+          (sys_mem_total > 0 && memory_info.total >= sys_mem_total * 9 / 10)) {
         has_unified_memory = true;
       } else {
         SET_GPUINFO_DYNAMIC(dynamic_info, total_memory, memory_info.total);