Use global Buffer for HUB75

platformio.ini

@@ -1087,8 +1087,11 @@ custom_usermods = *   ; Expands to all usermods in usermods folder
 
 ;; Core HUB75 flags - common to every HUB75 build
 build_flags =
-  -D WLED_ENABLE_HUB75MATRIX -D NO_GFX
+  -D WLED_ENABLE_HUB75MATRIX
+  -D NO_GFX ; disable GFX library usage, we do not need it
+  -D NO_FAST_FUNCTIONS ; no fast line drawing functions (used by GFX, saves 1k of flash)
   -D NO_CIE1931 ;; disable driver-internal gamma correction
+  ; -D WLED_HUB75_EXTRA_BUFFER ; enable extra drawing buffer (use in case you see image tearing on large setups >8000 LEDs)
   -D WLED_DEBUG_BUS
   -D LED_TYPES=TYPE_HUB75MATRIX_HS
   ; -D WLED_DEBUG

wled00/FX_fcn.cpp

@@ -148,11 +148,9 @@ bool Segment::allocateData(size_t len) {
   if (len == 0) return false;    // nothing to do
   if (data && _dataLen >= len) { // already allocated enough (reduce fragmentation)
     if (call == 0) {
-      if (_dataLen < FAIR_DATA_PER_SEG) { // segment data is small
         //DEBUG_PRINTF_P(PSTR("--   Clearing data (%d): %p\n"), len, this);
         memset(data, 0, len);  // erase buffer if called during effect initialisation
         return true; // no need to reallocate
-      }
     }
     else
       return true;
@@ -196,7 +194,7 @@ void Segment::deallocateData() {
     DEBUG_PRINTF_P(PSTR("---- Released data (%p): inconsistent UsedSegmentData (%d/%d), cowardly refusing to free nothing.\n"), this, _dataLen, Segment::getUsedSegmentData());
   }
   data = nullptr;
-  Segment::addUsedSegmentData(_dataLen <= Segment::getUsedSegmentData() ? -_dataLen : -Segment::getUsedSegmentData());
+  Segment::addUsedSegmentData(-_dataLen); // addUsedSegmentData guards agains negative and sets zero if underrun so this is safe
   _dataLen = 0;
 }
 

wled00/bus_manager.cpp

@@ -1067,8 +1067,9 @@ BusHub75Matrix::BusHub75Matrix(const BusConfig &bc) : Bus(bc.type, bc.start, bc.
     _valid = true;
     display->clearScreen();   // initially clear the screen buffer
     DEBUGBUS_PRINTLN("MatrixPanel_I2S_DMA clear ok");
-
+    #ifdef WLED_HUB75_EXTRA_BUFFER
     if (_ledBuffer) d_free(_ledBuffer);                 // should not happen
+    #endif
     if (_ledsDirty) d_free(_ledsDirty);                 // should not happen
     DEBUGBUS_PRINTLN("MatrixPanel_I2S_DMA allocate memory");
     _ledsDirty = (byte*) d_malloc(getBitArrayBytes(_len));  // create LEDs dirty bits
@@ -1083,9 +1084,10 @@ BusHub75Matrix::BusHub75Matrix(const BusConfig &bc) : Bus(bc.type, bc.start, bc.
       return;  //  fail is we cannot get memory for the buffer
     }
     setBitArray(_ledsDirty, _len, false);             // reset dirty bits
-
+    #ifdef WLED_HUB75_EXTRA_BUFFER
     // create LEDs buffer (initialized to BLACK), prefer DRAM if enough heap is available (faster in case global _pixels buffer is in PSRAM as not both will fit the cache)
     _ledBuffer = static_cast<CRGB*>(allocate_buffer(_len * sizeof(CRGB), BFRALLOC_PREFER_DRAM | BFRALLOC_CLEAR));
+    #endif
   }
 
   PANEL_CHAIN_TYPE chainType = CHAIN_NONE; // default for quarter-scan panels that do not use chaining
@@ -1132,27 +1134,34 @@ BusHub75Matrix::BusHub75Matrix(const BusConfig &bc) : Bus(bc.type, bc.start, bc.
 
   DEBUGBUS_PRINT(F("MatrixPanel_I2S_DMA "));
   DEBUGBUS_PRINTF_P(PSTR("%sstarted, width=%u, %u pixels.\n"), _valid? "":"not ", _panelWidth, _len);
-
-  if (_ledBuffer != nullptr) DEBUGBUS_PRINTLN(F("MatrixPanel_I2S_DMA LEDS buffer enabled."));
-  if (_ledsDirty != nullptr) DEBUGBUS_PRINTLN(F("MatrixPanel_I2S_DMA LEDS dirty bit optimization enabled."));
-  if ((_ledBuffer != nullptr) || (_ledsDirty != nullptr)) {
-    DEBUGBUS_PRINT(F("MatrixPanel_I2S_DMA LEDS buffer uses "));
-    DEBUGBUS_PRINT((_ledBuffer? _len*sizeof(CRGB) :0) + (_ledsDirty? getBitArrayBytes(_len) :0));
-    DEBUGBUS_PRINTLN(F(" bytes."));
+  #ifdef WLED_HUB75_EXTRA_BUFFER
+  if (_ledBuffer != nullptr) {
+    DEBUGBUS_PRINTLN(F("MatrixPanel_I2S_DMA extra buffer enabled."));
+    DEBUGBUS_PRINT(F("Extra buffer uses "));
+    DEBUGBUS_PRINT(_len*sizeof(CRGB));
+  }
+  #endif
+  if (_ledsDirty != nullptr) {
+    DEBUGBUS_PRINTLN(F("MatrixPanel_I2S_DMA LEDS dirty bit optimization enabled."));
+    DEBUGBUS_PRINT(F("Dirty buffer uses "));
+    DEBUGBUS_PRINT((getBitArrayBytes(_len)));
   }
 }
 
 void IRAM_ATTR BusHub75Matrix::setPixelColor(unsigned pix, uint32_t c) {
   if (!_valid) return; // note: no need to check pix >= _len as that is checked in containsPixel()
   // if (_cct >= 1900) c = colorBalanceFromKelvin(_cct, c); //color correction from CCT
-
+  #ifdef WLED_HUB75_EXTRA_BUFFER
   if (_ledBuffer) {
     CRGB fastled_col = CRGB(c);
     if (_ledBuffer[pix] != fastled_col) {
       _ledBuffer[pix] = fastled_col;
       setBitInArray(_ledsDirty, pix, true);  // flag pixel as "dirty"
     }
   }
+  #else
+  if (false) {} // placeholder
+  #endif
   else {
     if ((c == IS_BLACK) && (getBitFromArray(_ledsDirty, pix) == false)) return; // ignore black if pixel is already black
     setBitInArray(_ledsDirty, pix, c != IS_BLACK);                              // dirty = true means "color is not BLACK"
@@ -1175,10 +1184,14 @@ void IRAM_ATTR BusHub75Matrix::setPixelColor(unsigned pix, uint32_t c) {
 
 uint32_t BusHub75Matrix::getPixelColor(unsigned pix) const {
   if (!_valid) return IS_BLACK; // note: no need to check pix >= _len as that is checked in containsPixel()
+  #ifdef WLED_HUB75_EXTRA_BUFFER
   if (_ledBuffer)
     return uint32_t(_ledBuffer[pix]);  // fastled-slim already returns RGB, no need to mask out the upper byte
   else
     return getBitFromArray(_ledsDirty, pix) ? IS_DARKGREY: IS_BLACK;   // just a hack - we only know if the pixel is black or not
+  #else
+  return getBitFromArray(_ledsDirty, pix) ? IS_DARKGREY: IS_BLACK;   // just a hack - we only know if the pixel is black or not
+  #endif
 }
 
 void BusHub75Matrix::setBrightness(uint8_t b) {
@@ -1188,6 +1201,7 @@ void BusHub75Matrix::setBrightness(uint8_t b) {
 }
 
 void BusHub75Matrix::show(void) {
+  #ifdef WLED_HUB75_EXTRA_BUFFER
   if (!_valid) return;
   if (_ledBuffer) {
     // write out buffered LEDs
@@ -1207,6 +1221,9 @@ void BusHub75Matrix::show(void) {
     }
     setBitArray(_ledsDirty, _len, false);  // buffer shown - reset all dirty bits
   }
+  #endif
+  // show() is a no-op if WLED_HUB75_EXTRA_BUFFER is not defined: pixels were already written directly in setPixelColor(),
+  // the DMA driver handles continuous refresh asynchronously
 }
 
 void BusHub75Matrix::cleanup() {
@@ -1224,7 +1241,9 @@ void BusHub75Matrix::cleanup() {
   #else  // runtime reconfiguration is not working on -S3, request reboot from user instead
     errorFlag = ERR_REBOOT_NEEDED;
   #endif
+  #ifdef WLED_HUB75_EXTRA_BUFFER
   if (_ledBuffer != nullptr) d_free(_ledBuffer); _ledBuffer = nullptr;
+  #endif
   if (_ledsDirty != nullptr) d_free(_ledsDirty); _ledsDirty = nullptr;
 }
 

wled00/const.h

@@ -572,7 +572,7 @@ static_assert(WLED_MAX_BUSSES <= 32, "WLED_MAX_BUSSES exceeds hard limit");
   #elif defined(CONFIG_IDF_TARGET_ESP32C3) || defined(CONFIG_IDF_TARGET_ESP32C5) || defined(CONFIG_IDF_TARGET_ESP32C6) || defined(CONFIG_IDF_TARGET_ESP32C61)
     #define MAX_LEDS 4096
   #else
-    #define MAX_LEDS 16384 // classic esp32, S3 and P4 can take more
+    #define MAX_LEDS 16384 // note: P4/S3 can take more, 24576 is already unstable on S3 using HUB75 (DMA buffers)
   #endif
 #endif
 

wled00/util.cpp

@@ -927,8 +927,8 @@ void *allocate_buffer(size_t size, uint32_t type) {
   buffer = d_malloc(size);
   #else
   if (type & BFRALLOC_PREFER_DRAM) {
-    if (getContiguousFreeHeap() < 3*(MIN_HEAP_SIZE/2) + size && size > PSRAM_THRESHOLD)
-      buffer = p_malloc(size); // prefer PSRAM for large allocations & when DRAM is low
+    if ((getContiguousFreeHeap() < 3*(MIN_HEAP_SIZE/2) + size && size > PSRAM_THRESHOLD) || size > 2*PSRAM_THRESHOLD)
+      buffer = p_malloc(size); // prefer PSRAM for large allocations & when DRAM is low or when buffer is huge
     else
       buffer = d_malloc(size); // allocate in DRAM if enough free heap is available, PSRAM as fallback
   }