Revision 23:33df42ff2541, committed 2014-01-02

Comitter:

bikeNomad

Date:

Thu Jan 02 10:30:25 2014 +0000

Parent:

22:abfed71656bd

Child:

24:feb1dae0403a

Commit message:

smoothed animation; added frames/sec count (now at 341 for rainbow)

Changed in this revision

--- a/WS2811.cpp	Thu Jan 02 02:31:24 2014 +0000
+++ b/WS2811.cpp	Thu Jan 02 10:30:25 2014 +0000
@@ -1,394 +1,399 @@
-// 800 KHz WS2811 driver driving potentially many LED strings.
-// Uses 3-phase DMA
-// 16K SRAM less stack, etc.
-//
-// Per LED: 3 bytes (malloc'd) for RGB data
-//
-// Per LED strip / per LED
-//          96 bytes (static) for bit data
-//        + 96 bytes (static) for ones data
-//        = 192 bytes
-//
-//        40 LEDs max per string = 7680 bytes static
-//
-//        40 LEDs: 7680 + 40*3 = 7800 bytes
-//        80 LEDs: 7680 + 80*3 = 7920 bytes
-
-#include "MKL25Z4.h"
-#include "LedStrip.h"
-#include "WS2811.h"
-
-//
-// Configuration
-//
-
-// Define MONITOR_TPM0_PWM as non-zero to monitor PWM timing on PTD0 and PTD1
-// PTD0 TPM0/CH0 PWM_1 J2/06
-// PTD1 TPM0/CH1 PWM_2 J2/12 (also LED_BLUE)
-#define MONITOR_TPM0_PWM 0
-
-// define DEBUG_PIN to identify a pin in PORTD used for debug output
-// #define DEBUG_PIN 3 /* PTD3 debugOut */
-
-#ifdef DEBUG_PIN
-#define DEBUG 1
-#endif
-
-#if DEBUG
-#define DEBUG_MASK (1<<DEBUG_PIN)
-#define RESET_DEBUG (IO_GPIO->PDOR &= ~DEBUG_MASK)
-#define SET_DEBUG (IO_GPIO->PDOR |= DEBUG_MASK)
-#else
-#define DEBUG_MASK 0
-#define RESET_DEBUG (void)0
-#define SET_DEBUG (void)0
-#endif
-
-static PORT_Type volatile * const IO_PORT = PORTD;
-static GPIO_Type volatile * const IO_GPIO = PTD;
-
-// 48 MHz clock, no prescaling.
-#define NSEC_TO_TICKS(nsec) ((nsec)*48/1000)
-static const uint32_t CLK_NSEC = 1250;
-static const uint32_t tpm_period    = NSEC_TO_TICKS(CLK_NSEC);
-static const uint32_t tpm_p0_period = NSEC_TO_TICKS(CLK_NSEC / 3);
-static const uint32_t tpm_p1_period = NSEC_TO_TICKS(CLK_NSEC * 2 / 3);
-
-enum DMA_MUX_SRC
-{
-    DMA_MUX_SRC_TPM0_CH_0     = 24,
-    DMA_MUX_SRC_TPM0_CH_1,
-    DMA_MUX_SRC_TPM0_Overflow = 54,
-};
-
-enum DMA_CHAN
-{
-    DMA_CHAN_START = 0,
-    DMA_CHAN_0_LOW = 1,
-    DMA_CHAN_1_LOW = 2,
-    N_DMA_CHANNELS
-};
-
-static volatile bool dma_done = true;
-
-// class static
-bool WS2811::initialized = false;
-
-// class static
-uint32_t WS2811::enabledPins = 0;
-
-#define WORD_ALIGNED __attribute__ ((aligned(4)))
-
-#define DMA_LEADING_ZEROS  2
-#define BITS_PER_RGB       24
-#define DMA_TRAILING_ZEROS 1
-
-static struct
-{
-    uint32_t start_t1_low[ DMA_LEADING_ZEROS ];
-    uint32_t dmaWords[ BITS_PER_RGB * MAX_LEDS_PER_STRIP ];
-    uint32_t trailing_zeros_1[ DMA_TRAILING_ZEROS ];
-
-    uint32_t start_t0_high[ DMA_LEADING_ZEROS - 1 ];
-    uint32_t allOnes[ BITS_PER_RGB * MAX_LEDS_PER_STRIP ];
-    uint32_t trailing_zeros_2[ DMA_TRAILING_ZEROS + 1 ];
-} dmaData WORD_ALIGNED;
-
-// class static 
-bool WS2811::is_dma_done()
-{
-    return dma_done;
-}
-
-// class static
-void WS2811::hw_init()
-{
-    if (initialized) return;
-
-    dma_data_init();
-    clock_init();
-    dma_init();
-    io_init();
-    tpm_init();
-
-    initialized = true;
-}
-
-// class static
-void WS2811::dma_data_init()
-{
-    memset(dmaData.allOnes, 0xFF, sizeof(dmaData.allOnes));
-
-#if DEBUG
-    for (unsigned i = 0; i < BITS_PER_RGB * MAX_LEDS_PER_STRIP; i++)
-        dmaData.dmaWords[i] = DEBUG_MASK;
-#endif
-}
-
-// class static
-
-/// Enable PORTD, DMA and TPM0 clocking
-void WS2811::clock_init()
-{
-    SIM->SCGC5 |= SIM_SCGC5_PORTD_MASK;
-    SIM->SCGC6 |= SIM_SCGC6_DMAMUX_MASK | SIM_SCGC6_TPM0_MASK; // Enable clock to DMA mux and TPM0
-    SIM->SCGC7 |= SIM_SCGC7_DMA_MASK;  // Enable clock to DMA
-
-    SIM->SOPT2 |= SIM_SOPT2_TPMSRC(1); // Clock source: MCGFLLCLK or MCGPLLCLK
-}
-
-// class static
-
-/// Configure GPIO output pins
-void WS2811::io_init()
-{
-    uint32_t m = 1;
-    for (uint32_t i = 0; i < 32; i++)
-    {
-        // set up each pin
-        if (m & enabledPins)
-        {
-            IO_PORT->PCR[i] = PORT_PCR_MUX(1) // GPIO
-                              | PORT_PCR_DSE_MASK; // high drive strength
-        }
-        m <<= 1;
-    }
-
-    IO_GPIO->PDDR |= enabledPins;      // set as outputs
-
-#if MONITOR_TPM0_PWM
-    // PTD0 CH0 monitor: TPM0, high drive strength
-    IO_PORT->PCR[0] = PORT_PCR_MUX(4) | PORT_PCR_DSE_MASK;
-    // PTD1 CH1 monitor: TPM0, high drive strength
-    IO_PORT->PCR[1] = PORT_PCR_MUX(4) | PORT_PCR_DSE_MASK;
-    IO_GPIO->PDDR  |= 3;               // set as outputs
-    IO_GPIO->PDOR &= ~(enabledPins | 3);     // initially low
-#else
-    IO_GPIO->PDOR &= ~enabledPins;     // initially low
-#endif
-
-#if DEBUG
-    IO_PORT->PCR[DEBUG_PIN] = PORT_PCR_MUX(1) | PORT_PCR_DSE_MASK;
-    IO_GPIO->PDDR |= DEBUG_MASK;
-    IO_GPIO->PDOR &= ~DEBUG_MASK;
-#endif
-}
-
-// class static
-
-/// Configure DMA and DMAMUX
-void WS2811::dma_init()
-{
-    // reset DMAMUX
-    DMAMUX0->CHCFG[DMA_CHAN_START] = 0;
-    DMAMUX0->CHCFG[DMA_CHAN_0_LOW] = 0;
-    DMAMUX0->CHCFG[DMA_CHAN_1_LOW] = 0;
-
-    // wire our DMA event sources into the first three DMA channels
-    // t=0: all enabled outputs go high on TPM0 overflow
-    DMAMUX0->CHCFG[DMA_CHAN_START] = DMAMUX_CHCFG_ENBL_MASK | DMAMUX_CHCFG_SOURCE(DMA_MUX_SRC_TPM0_Overflow);
-    // t=tpm_p0_period: all of the 0 bits go low.
-    DMAMUX0->CHCFG[DMA_CHAN_0_LOW] = DMAMUX_CHCFG_ENBL_MASK | DMAMUX_CHCFG_SOURCE(DMA_MUX_SRC_TPM0_CH_0);
-    // t=tpm_p1_period: all outputs go low.
-    DMAMUX0->CHCFG[DMA_CHAN_1_LOW] = DMAMUX_CHCFG_ENBL_MASK | DMAMUX_CHCFG_SOURCE(DMA_MUX_SRC_TPM0_CH_1);
-
-    NVIC_EnableIRQ(DMA0_IRQn);
-}
-
-// class static
-
-/// Configure TPM0 to do two different PWM periods at 800kHz rate
-void WS2811::tpm_init()
-{
-    // set up TPM0 for proper period (800 kHz = 1.25 usec ±600nsec)
-    TPM_Type volatile *tpm = TPM0;
-    tpm->SC = TPM_SC_DMA_MASK          // enable DMA
-              | TPM_SC_CMOD(0)         // disable clocks
-              | TPM_SC_PS(0);          // 48MHz / 1 = 48MHz clock
-    tpm->MOD = tpm_period - 1;         // 48MHz / 800kHz
-
-    // No Interrupts; High True pulses on Edge Aligned PWM
-    tpm->CONTROLS[0].CnSC = TPM_CnSC_MSB_MASK | TPM_CnSC_ELSB_MASK | TPM_CnSC_DMA_MASK;
-    tpm->CONTROLS[1].CnSC = TPM_CnSC_MSB_MASK | TPM_CnSC_ELSB_MASK | TPM_CnSC_DMA_MASK;
-
-    // set TPM0 channel 0 for 0.35 usec (±150nsec) / 0.8 usec (±150nsec) (0 code)
-    // 1.25 usec * 1/3 = 417 nsec
-    tpm->CONTROLS[0].CnV = tpm_p0_period;
-
-    // set TPM0 channel 1 for 0.7 usec (±150nsec) / 0.6 usec (±150nsec) (1 code)
-    // 1.25 usec * 2/3 = 833 nsec
-    tpm->CONTROLS[1].CnV = tpm_p1_period;
-}
-
-WS2811::WS2811(unsigned n, unsigned pinNumber)
-    : LedStrip(n)
-    , pinMask(1U << pinNumber)
-{
-    enabledPins |= pinMask;
-    guardtime.start();
-}
-
-// class static
-void WS2811::startDMA()
-{
-    DMA_Type volatile * dma   = DMA0;
-    TPM_Type volatile *tpm   = TPM0;
-    uint32_t nBytes = sizeof(dmaData.start_t1_low)
-        + sizeof(dmaData.dmaWords)
-        + sizeof(dmaData.trailing_zeros_1);
-
-    tpm->SC &= ~TPM_SC_CMOD_MASK; // disable internal clocking
-    tpm->CNT = tpm_p0_period - 2 ;
-    tpm->STATUS = 0xFFFFFFFF;
-
-    dma->DMA[DMA_CHAN_START].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
-    dma->DMA[DMA_CHAN_0_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
-    dma->DMA[DMA_CHAN_1_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
-
-    // t=0: all outputs go high
-    // triggered by TPM0_Overflow
-    // source is one word of 0 then 24 x 0xffffffff, then another 0 word
-    dma->DMA[DMA_CHAN_START].SAR     = (uint32_t)(void*)dmaData.start_t0_high;
-    dma->DMA[DMA_CHAN_START].DSR_BCR = DMA_DSR_BCR_BCR_MASK & nBytes; // length of transfer in bytes
-
-    // t=tpm_p0_period: some outputs (the 0 bits) go low.
-    // Triggered by TPM0_CH0
-    // Start 2 words before the actual data to avoid garbage pulses.
-    dma->DMA[DMA_CHAN_0_LOW].SAR     = (uint32_t)(void*)dmaData.start_t1_low; // set source address
-    dma->DMA[DMA_CHAN_0_LOW].DSR_BCR = DMA_DSR_BCR_BCR_MASK & nBytes; // length of transfer in bytes
-
-    // t=tpm_p1_period: all outputs go low.
-    // Triggered by TPM0_CH1
-    // source is constant 0x00000000 (first word of dmaWords)
-    dma->DMA[DMA_CHAN_1_LOW].SAR     = (uint32_t)(void*)dmaData.start_t1_low; // set source address
-    dma->DMA[DMA_CHAN_1_LOW].DSR_BCR = DMA_DSR_BCR_BCR_MASK & nBytes; // length of transfer in bytes
-
-    dma->DMA[DMA_CHAN_0_LOW].DAR 
-        = dma->DMA[DMA_CHAN_1_LOW].DAR 
-        = dma->DMA[DMA_CHAN_START].DAR 
-        = (uint32_t)(void*)&IO_GPIO->PDOR;
-
-    // wait until done
-    while (!is_dma_done())
-    {
-        __WFI();
-    }
-
-    SET_DEBUG;
-
-    dma->DMA[DMA_CHAN_0_LOW].DCR     = DMA_DCR_EINT_MASK // enable interrupt on end of transfer
-                                       | DMA_DCR_ERQ_MASK
-                                       | DMA_DCR_D_REQ_MASK // clear ERQ on end of transfer
-                                       | DMA_DCR_SINC_MASK // increment source each transfer
-                                       | DMA_DCR_CS_MASK
-                                       | DMA_DCR_SSIZE(0) // 32-bit source transfers
-                                       | DMA_DCR_DSIZE(0); // 32-bit destination transfers
-
-    dma->DMA[DMA_CHAN_1_LOW].DCR     = DMA_DCR_EINT_MASK // enable interrupt on end of transfer
-                                       | DMA_DCR_ERQ_MASK
-                                       | DMA_DCR_D_REQ_MASK // clear ERQ on end of transfer
-                                       | DMA_DCR_CS_MASK
-                                       | DMA_DCR_SSIZE(0) // 32-bit source transfers
-                                       | DMA_DCR_DSIZE(0); // 32-bit destination transfers
-
-    dma->DMA[DMA_CHAN_START].DCR     = DMA_DCR_EINT_MASK // enable interrupt on end of transfer
-                                       | DMA_DCR_ERQ_MASK
-                                       | DMA_DCR_D_REQ_MASK // clear ERQ on end of transfer
-                                       | DMA_DCR_SINC_MASK // increment source each transfer
-                                       | DMA_DCR_CS_MASK
-                                       | DMA_DCR_SSIZE(0) // 32-bit source transfers
-                                       | DMA_DCR_DSIZE(0);
-
-
-    tpm->SC |= TPM_SC_CMOD(1);         // enable internal clocking
-}
-
-void WS2811::writePixel(unsigned n, uint8_t *p)
-{
-    uint32_t *dest = dmaData.dmaWords + n * BITS_PER_RGB;
-    writeByte(*p++, pinMask, dest + 0); // G
-    writeByte(*p++, pinMask, dest + 8); // R
-    writeByte(*p, pinMask, dest + 16); // B
-}
-
-// class static
-void WS2811::writeByte(uint8_t byte, uint32_t mask, uint32_t *dest)
-{
-    for (uint8_t bm = 0x80; bm; bm >>= 1)
-    {
-        // MSBit first
-        if (byte & bm)
-            *dest |= mask;
-        else
-            *dest &= ~mask;
-        dest++;
-    }
-}
-
-void WS2811::begin()
-{
-    blank();
-    show();
-}
-
-void WS2811::blank()
-{
-    memset(pixels, 0x00, numPixelBytes());
-
-#if DEBUG
-    for (unsigned i = DMA_LEADING_ZEROS; i < DMA_LEADING_ZEROS + BITS_PER_RGB; i++)
-            dmaData.dmaWords[i] = DEBUG_MASK;
-#else
-    memset(dmaData.dmaWords, 0x00, sizeof(dmaData.dmaWords));
-#endif
-}
-
-void WS2811::show()
-{
-    hw_init();
-
-    uint16_t i, n = numPixels(); // 3 bytes per LED
-    uint8_t *p = pixels;
-    while (guardtime.read_us() < 50)
-    {
-        __NOP();
-    }
-
-    for (i=0; i<n; i++ )
-    {
-        writePixel(i, p);
-        p += 3;
-    }
-
-    startDMA();
-
-    guardtime.reset();
-}
-
-extern "C" void DMA0_IRQHandler()
-{
-    DMA_Type volatile * dma = DMA0;
-    TPM_Type volatile *tpm   = TPM0;
-
-    uint32_t db = dma->DMA[DMA_CHAN_START].DSR_BCR;
-    if (db & DMA_DSR_BCR_DONE_MASK)
-    {
-        dma->DMA[DMA_CHAN_START].DSR_BCR = DMA_DSR_BCR_DONE_MASK;  // clear/reset DMA status
-    }
-
-    db = dma->DMA[DMA_CHAN_0_LOW].DSR_BCR;
-    if (db & DMA_DSR_BCR_DONE_MASK)
-    {
-        dma->DMA[DMA_CHAN_0_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK;  // clear/reset DMA status
-    }
-
-    db = dma->DMA[DMA_CHAN_1_LOW].DSR_BCR;
-    if (db & DMA_DSR_BCR_DONE_MASK)
-    {
-        dma->DMA[DMA_CHAN_1_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
-        dma_done                         = true;
-        tpm->SC &= ~TPM_SC_CMOD_MASK; // disable internal clocking
-        RESET_DEBUG;
-    }
-}
+// 800 KHz WS2811 driver driving potentially many LED strings.
+// Uses 3-phase DMA
+// 16K SRAM less stack, etc.
+//
+// Per LED: 3 bytes (malloc'd) for RGB data
+//
+// Per LED strip / per LED
+//          96 bytes (static) for bit data
+//        + 96 bytes (static) for ones data
+//        = 192 bytes
+//
+//        40 LEDs max per string = 7680 bytes static
+//
+//        40 LEDs: 7680 + 40*3 = 7800 bytes
+//        80 LEDs: 7680 + 80*3 = 7920 bytes
+
+#include "MKL25Z4.h"
+#include "LedStrip.h"
+#include "WS2811.h"
+
+//
+// Configuration
+//
+
+// Define MONITOR_TPM0_PWM as non-zero to monitor PWM timing on PTD0 and PTD1
+// PTD0 TPM0/CH0 PWM_1 J2/06
+// PTD1 TPM0/CH1 PWM_2 J2/12 (also LED_BLUE)
+#define MONITOR_TPM0_PWM 0
+
+// define DEBUG_PIN to identify a pin in PORTD used for debug output
+// #define DEBUG_PIN 3 /* PTD3 debugOut */
+
+#ifdef DEBUG_PIN
+#define DEBUG 1
+#endif
+
+#if DEBUG
+#define DEBUG_MASK (1<<DEBUG_PIN)
+#define RESET_DEBUG (IO_GPIO->PDOR &= ~DEBUG_MASK)
+#define SET_DEBUG (IO_GPIO->PDOR |= DEBUG_MASK)
+#else
+#define DEBUG_MASK 0
+#define RESET_DEBUG (void)0
+#define SET_DEBUG (void)0
+#endif
+
+static PORT_Type volatile * const IO_PORT = PORTD;
+static GPIO_Type volatile * const IO_GPIO = PTD;
+
+// 48 MHz clock, no prescaling.
+#define NSEC_TO_TICKS(nsec) ((nsec)*48/1000)
+static const uint32_t CLK_NSEC = 1250;
+static const uint32_t tpm_period    = NSEC_TO_TICKS(CLK_NSEC);
+static const uint32_t tpm_p0_period = NSEC_TO_TICKS(CLK_NSEC / 3);
+static const uint32_t tpm_p1_period = NSEC_TO_TICKS(CLK_NSEC * 2 / 3);
+
+enum DMA_MUX_SRC
+{
+    DMA_MUX_SRC_TPM0_CH_0     = 24,
+    DMA_MUX_SRC_TPM0_CH_1,
+    DMA_MUX_SRC_TPM0_Overflow = 54,
+};
+
+enum DMA_CHAN
+{
+    DMA_CHAN_START = 0,
+    DMA_CHAN_0_LOW = 1,
+    DMA_CHAN_1_LOW = 2,
+    N_DMA_CHANNELS
+};
+
+static volatile bool dma_done = true;
+
+// class static
+bool WS2811::initialized = false;
+
+// class static
+Timer WS2811::guardtime;
+
+// class static
+uint32_t WS2811::enabledPins = 0;
+
+#define WORD_ALIGNED __attribute__ ((aligned(4)))
+
+#define DMA_LEADING_ZEROS  2
+#define BITS_PER_RGB       24
+#define DMA_TRAILING_ZEROS 1
+
+static struct
+{
+    uint32_t start_t1_low[ DMA_LEADING_ZEROS ];
+    uint32_t dmaWords[ BITS_PER_RGB * MAX_LEDS_PER_STRIP ];
+    uint32_t trailing_zeros_1[ DMA_TRAILING_ZEROS ];
+
+    uint32_t start_t0_high[ DMA_LEADING_ZEROS - 1 ];
+    uint32_t allOnes[ BITS_PER_RGB * MAX_LEDS_PER_STRIP ];
+    uint32_t trailing_zeros_2[ DMA_TRAILING_ZEROS + 1 ];
+} dmaData WORD_ALIGNED;
+
+// class static 
+bool WS2811::is_dma_done()
+{
+    return dma_done;
+}
+
+// class static
+void WS2811::hw_init()
+{
+    if (initialized) return;
+
+    guardtime.start();
+
+    dma_data_init();
+    clock_init();
+    dma_init();
+    io_init();
+    tpm_init();
+
+    initialized = true;
+}
+
+// class static
+void WS2811::dma_data_init()
+{
+    memset(dmaData.allOnes, 0xFF, sizeof(dmaData.allOnes));
+
+#if DEBUG
+    for (unsigned i = 0; i < BITS_PER_RGB * MAX_LEDS_PER_STRIP; i++)
+        dmaData.dmaWords[i] = DEBUG_MASK;
+#endif
+}
+
+// class static
+
+/// Enable PORTD, DMA and TPM0 clocking
+void WS2811::clock_init()
+{
+    SIM->SCGC5 |= SIM_SCGC5_PORTD_MASK;
+    SIM->SCGC6 |= SIM_SCGC6_DMAMUX_MASK | SIM_SCGC6_TPM0_MASK; // Enable clock to DMA mux and TPM0
+    SIM->SCGC7 |= SIM_SCGC7_DMA_MASK;  // Enable clock to DMA
+
+    SIM->SOPT2 |= SIM_SOPT2_TPMSRC(1); // Clock source: MCGFLLCLK or MCGPLLCLK
+}
+
+// class static
+
+/// Configure GPIO output pins
+void WS2811::io_init()
+{
+    uint32_t m = 1;
+    for (uint32_t i = 0; i < 32; i++)
+    {
+        // set up each pin
+        if (m & enabledPins)
+        {
+            IO_PORT->PCR[i] = PORT_PCR_MUX(1) // GPIO
+                              | PORT_PCR_DSE_MASK; // high drive strength
+        }
+        m <<= 1;
+    }
+
+    IO_GPIO->PDDR |= enabledPins;      // set as outputs
+
+#if MONITOR_TPM0_PWM
+    // PTD0 CH0 monitor: TPM0, high drive strength
+    IO_PORT->PCR[0] = PORT_PCR_MUX(4) | PORT_PCR_DSE_MASK;
+    // PTD1 CH1 monitor: TPM0, high drive strength
+    IO_PORT->PCR[1] = PORT_PCR_MUX(4) | PORT_PCR_DSE_MASK;
+    IO_GPIO->PDDR  |= 3;               // set as outputs
+    IO_GPIO->PDOR &= ~(enabledPins | 3);     // initially low
+#else
+    IO_GPIO->PDOR &= ~enabledPins;     // initially low
+#endif
+
+#if DEBUG
+    IO_PORT->PCR[DEBUG_PIN] = PORT_PCR_MUX(1) | PORT_PCR_DSE_MASK;
+    IO_GPIO->PDDR |= DEBUG_MASK;
+    IO_GPIO->PDOR &= ~DEBUG_MASK;
+#endif
+}
+
+// class static
+
+/// Configure DMA and DMAMUX
+void WS2811::dma_init()
+{
+    // reset DMAMUX
+    DMAMUX0->CHCFG[DMA_CHAN_START] = 0;
+    DMAMUX0->CHCFG[DMA_CHAN_0_LOW] = 0;
+    DMAMUX0->CHCFG[DMA_CHAN_1_LOW] = 0;
+
+    // wire our DMA event sources into the first three DMA channels
+    // t=0: all enabled outputs go high on TPM0 overflow
+    DMAMUX0->CHCFG[DMA_CHAN_START] = DMAMUX_CHCFG_ENBL_MASK | DMAMUX_CHCFG_SOURCE(DMA_MUX_SRC_TPM0_Overflow);
+    // t=tpm_p0_period: all of the 0 bits go low.
+    DMAMUX0->CHCFG[DMA_CHAN_0_LOW] = DMAMUX_CHCFG_ENBL_MASK | DMAMUX_CHCFG_SOURCE(DMA_MUX_SRC_TPM0_CH_0);
+    // t=tpm_p1_period: all outputs go low.
+    DMAMUX0->CHCFG[DMA_CHAN_1_LOW] = DMAMUX_CHCFG_ENBL_MASK | DMAMUX_CHCFG_SOURCE(DMA_MUX_SRC_TPM0_CH_1);
 
+    NVIC_EnableIRQ(DMA0_IRQn);
+}
+
+// class static
+
+/// Configure TPM0 to do two different PWM periods at 800kHz rate
+void WS2811::tpm_init()
+{
+    // set up TPM0 for proper period (800 kHz = 1.25 usec ±600nsec)
+    TPM_Type volatile *tpm = TPM0;
+    tpm->SC = TPM_SC_DMA_MASK          // enable DMA
+              | TPM_SC_CMOD(0)         // disable clocks
+              | TPM_SC_PS(0);          // 48MHz / 1 = 48MHz clock
+    tpm->MOD = tpm_period - 1;         // 48MHz / 800kHz
+
+    // No Interrupts; High True pulses on Edge Aligned PWM
+    tpm->CONTROLS[0].CnSC = TPM_CnSC_MSB_MASK | TPM_CnSC_ELSB_MASK | TPM_CnSC_DMA_MASK;
+    tpm->CONTROLS[1].CnSC = TPM_CnSC_MSB_MASK | TPM_CnSC_ELSB_MASK | TPM_CnSC_DMA_MASK;
+
+    // set TPM0 channel 0 for 0.35 usec (±150nsec) / 0.8 usec (±150nsec) (0 code)
+    // 1.25 usec * 1/3 = 417 nsec
+    tpm->CONTROLS[0].CnV = tpm_p0_period;
+
+    // set TPM0 channel 1 for 0.7 usec (±150nsec) / 0.6 usec (±150nsec) (1 code)
+    // 1.25 usec * 2/3 = 833 nsec
+    tpm->CONTROLS[1].CnV = tpm_p1_period;
+}
+
+WS2811::WS2811(unsigned n, unsigned pinNumber)
+    : LedStrip(n)
+    , pinMask(1U << pinNumber)
+{
+    enabledPins |= pinMask;
+}
+
+// class static
+void WS2811::startDMA()
+{
+    DMA_Type volatile * dma   = DMA0;
+    TPM_Type volatile *tpm   = TPM0;
+    uint32_t nBytes = sizeof(dmaData.start_t1_low)
+        + sizeof(dmaData.dmaWords)
+        + sizeof(dmaData.trailing_zeros_1);
+
+    tpm->SC &= ~TPM_SC_CMOD_MASK; // disable internal clocking
+    tpm->CNT = tpm_p0_period - 2 ;
+    tpm->STATUS = 0xFFFFFFFF;
+
+    dma->DMA[DMA_CHAN_START].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
+    dma->DMA[DMA_CHAN_0_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
+    dma->DMA[DMA_CHAN_1_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
+
+    // t=0: all outputs go high
+    // triggered by TPM0_Overflow
+    // source is one word of 0 then 24 x 0xffffffff, then another 0 word
+    dma->DMA[DMA_CHAN_START].SAR     = (uint32_t)(void*)dmaData.start_t0_high;
+    dma->DMA[DMA_CHAN_START].DSR_BCR = DMA_DSR_BCR_BCR_MASK & nBytes; // length of transfer in bytes
+
+    // t=tpm_p0_period: some outputs (the 0 bits) go low.
+    // Triggered by TPM0_CH0
+    // Start 2 words before the actual data to avoid garbage pulses.
+    dma->DMA[DMA_CHAN_0_LOW].SAR     = (uint32_t)(void*)dmaData.start_t1_low; // set source address
+    dma->DMA[DMA_CHAN_0_LOW].DSR_BCR = DMA_DSR_BCR_BCR_MASK & nBytes; // length of transfer in bytes
+
+    // t=tpm_p1_period: all outputs go low.
+    // Triggered by TPM0_CH1
+    // source is constant 0x00000000 (first word of dmaWords)
+    dma->DMA[DMA_CHAN_1_LOW].SAR     = (uint32_t)(void*)dmaData.start_t1_low; // set source address
+    dma->DMA[DMA_CHAN_1_LOW].DSR_BCR = DMA_DSR_BCR_BCR_MASK & nBytes; // length of transfer in bytes
+
+    dma->DMA[DMA_CHAN_0_LOW].DAR 
+        = dma->DMA[DMA_CHAN_1_LOW].DAR 
+        = dma->DMA[DMA_CHAN_START].DAR 
+        = (uint32_t)(void*)&IO_GPIO->PDOR;
+
+    // wait until done
+    while (!is_dma_done())
+    {
+        __WFI();
+    }
+    
+    // ensure sufficient guard time
+    while (guardtime.read_us() < 50)
+    {
+        __NOP();
+    }
+
+    SET_DEBUG;
+
+    dma->DMA[DMA_CHAN_0_LOW].DCR     = DMA_DCR_EINT_MASK // enable interrupt on end of transfer
+                                       | DMA_DCR_ERQ_MASK
+                                       | DMA_DCR_D_REQ_MASK // clear ERQ on end of transfer
+                                       | DMA_DCR_SINC_MASK // increment source each transfer
+                                       | DMA_DCR_CS_MASK
+                                       | DMA_DCR_SSIZE(0) // 32-bit source transfers
+                                       | DMA_DCR_DSIZE(0); // 32-bit destination transfers
+
+    dma->DMA[DMA_CHAN_1_LOW].DCR     = DMA_DCR_EINT_MASK // enable interrupt on end of transfer
+                                       | DMA_DCR_ERQ_MASK
+                                       | DMA_DCR_D_REQ_MASK // clear ERQ on end of transfer
+                                       | DMA_DCR_CS_MASK
+                                       | DMA_DCR_SSIZE(0) // 32-bit source transfers
+                                       | DMA_DCR_DSIZE(0); // 32-bit destination transfers
+
+    dma->DMA[DMA_CHAN_START].DCR     = DMA_DCR_EINT_MASK // enable interrupt on end of transfer
+                                       | DMA_DCR_ERQ_MASK
+                                       | DMA_DCR_D_REQ_MASK // clear ERQ on end of transfer
+                                       | DMA_DCR_SINC_MASK // increment source each transfer
+                                       | DMA_DCR_CS_MASK
+                                       | DMA_DCR_SSIZE(0) // 32-bit source transfers
+                                       | DMA_DCR_DSIZE(0);
+
+
+    tpm->SC |= TPM_SC_CMOD(1);         // enable internal clocking
+}
+
+void WS2811::writePixel(unsigned n, uint8_t *p)
+{
+    uint32_t *dest = dmaData.dmaWords + n * BITS_PER_RGB;
+    writeByte(*p++, pinMask, dest + 0); // G
+    writeByte(*p++, pinMask, dest + 8); // R
+    writeByte(*p, pinMask, dest + 16); // B
+}
+
+// class static
+void WS2811::writeByte(uint8_t byte, uint32_t mask, uint32_t *dest)
+{
+    for (uint8_t bm = 0x80; bm; bm >>= 1)
+    {
+        // MSBit first
+        if (byte & bm)
+            *dest |= mask;
+        else
+            *dest &= ~mask;
+        dest++;
+    }
+}
+
+void WS2811::begin()
+{
+    blank();
+    show();
+}
+
+void WS2811::blank()
+{
+    memset(pixels, 0x00, numPixelBytes());
+
+#if DEBUG
+    for (unsigned i = DMA_LEADING_ZEROS; i < DMA_LEADING_ZEROS + BITS_PER_RGB; i++)
+            dmaData.dmaWords[i] = DEBUG_MASK;
+#else
+    memset(dmaData.dmaWords, 0x00, sizeof(dmaData.dmaWords));
+#endif
+}
+
+void WS2811::show()
+{
+    hw_init();
+
+    uint16_t i, n = numPixels(); // 3 bytes per LED
+    uint8_t *p = pixels;
+
+    for (i=0; i<n; i++ )
+    {
+        writePixel(i, p);
+        p += 3;
+    }
+
+    startDMA();
+}
+
+extern "C" void DMA0_IRQHandler()
+{
+    DMA_Type volatile * dma = DMA0;
+    TPM_Type volatile *tpm   = TPM0;
+
+    uint32_t db = dma->DMA[DMA_CHAN_START].DSR_BCR;
+    if (db & DMA_DSR_BCR_DONE_MASK)
+    {
+        dma->DMA[DMA_CHAN_START].DSR_BCR = DMA_DSR_BCR_DONE_MASK;  // clear/reset DMA status
+    }
+
+    db = dma->DMA[DMA_CHAN_0_LOW].DSR_BCR;
+    if (db & DMA_DSR_BCR_DONE_MASK)
+    {
+        dma->DMA[DMA_CHAN_0_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK;  // clear/reset DMA status
+    }
+
+    db = dma->DMA[DMA_CHAN_1_LOW].DSR_BCR;
+    if (db & DMA_DSR_BCR_DONE_MASK)
+    {
+        dma->DMA[DMA_CHAN_1_LOW].DSR_BCR = DMA_DSR_BCR_DONE_MASK; // clear/reset DMA status
+        dma_done                         = true;
+        tpm->SC &= ~TPM_SC_CMOD_MASK; // disable internal clocking
+        RESET_DEBUG;
+        WS2811::guardtime.reset();
+    }
+}
+

--- a/WS2811.h	Thu Jan 02 02:31:24 2014 +0000
+++ b/WS2811.h	Thu Jan 02 10:30:25 2014 +0000
@@ -21,6 +21,8 @@
 
 #define MAX_LEDS_PER_STRIP 60
 
+extern "C" void DMA0_IRQHandler();
+
 class WS2811 : public LedStrip
 {
 public:
@@ -30,8 +32,10 @@
     virtual void show();
     virtual void blank();
 
+    static void startDMA();
+    static bool is_dma_done();
+
 private:
-    Timer guardtime;
     uint32_t pinMask;
 
     void writePixel(unsigned n, uint8_t *p);
@@ -40,11 +44,9 @@
 
     static bool initialized;
     static uint32_t enabledPins;
+    static Timer guardtime;
 
     static void writeByte(uint8_t byte, uint32_t mask, uint32_t *dest);
-    static void startDMA();
-
-    static bool is_dma_done();
 
     static void hw_init();
         static void io_init();
@@ -52,6 +54,8 @@
         static void dma_init();
         static void tpm_init();
         static void dma_data_init();
+        
+    friend void DMA0_IRQHandler();
 };
 
 #endif

--- a/main.cpp	Thu Jan 02 02:31:24 2014 +0000
+++ b/main.cpp	Thu Jan 02 10:30:25 2014 +0000
@@ -2,8 +2,8 @@
 #include "WS2811.h"
 #include "Colors.h"
 
-// per LED: 3x 20 mA = 60mA
-// 4x full brightness = 0.33A at 5V.
+// per LED: 3 * 20 mA = 60mA max
+// 60 LEDs: 60 * 60mA = 3600 mA max
 unsigned const nLEDs = MAX_LEDS_PER_STRIP;
 
 // I/O pin usage
@@ -33,42 +33,31 @@
     strip.show();
 }
 
-static void showTestPattern(WS2811 &strip)
-{
-    unsigned nLEDs = strip.numPixels();
-    for (unsigned i = 0; i < nLEDs; i++)
-    {
-        strip.setPixelColor(i, LedStrip::Color(0xff,0,0xAA));
-    }
-    strip.show();
-}
-
 int main(void)
 {
     pc.baud(115200);
-    pc.printf("\r\nLEDs: %d\r\n", nLEDs);
-
     WS2811 lightStrip(nLEDs, DATA_OUT_PIN);
 
     lightStrip.begin();
 
-    float sat = 1.0;    // color saturation, 0.0 to 1.0
-    float brite = 0.1;  // 1.0 is full brightness, which is VERY bright!
-    float hueShift = 0.0;
-    float hueShiftIncrement = 1.0 / (360.0 / nLEDs);
+    float brite = 0.2;  // 1.0 is full brightness, which is VERY bright!
+    float rainbowPeriod = 1 * 1.0e6; // usec
+    float sat = 1.0;
 
-    Timer advance;
-    advance.start();
+    Timer timeRunning;
+    timeRunning.start();
+    bool printed = false;
+    unsigned frames = 0;
 
     for (;;) {
-        advance.reset();
-
-        // showTestPattern(lightStrip);
+        unsigned running = timeRunning.read_us();
+        float hueShift = running / rainbowPeriod;
+        if (!printed && running >= 10000000U) {
+            pc.printf("%u frames in %u usec = %u frames / sec\r\n", frames, running, frames * 1000000 / running);
+            printed = true;
+        }
         showRainbow(lightStrip, sat, brite, hueShift);
-        hueShift += hueShiftIncrement;
-
-        while (advance.read_ms() < 100)
-            __NOP();
-   }
+        frames ++;
+    }
 }