src/Cargo.lock

@@ -271,6 +271,7 @@ dependencies = [
  "libconfig",
  "libcortex_a9",
  "libregister",
+ "libsupport_zynq",
  "log",
  "log_buffer",
  "nb 1.0.0",

src/gateware/kasli_soc.py

@@ -16,7 +16,7 @@ from artiq.coredevice import jsondesc
 from artiq.gateware import rtio, eem_7series
 from artiq.gateware.rtio.xilinx_clocking import fix_serdes_timing_path
 from artiq.gateware.rtio.phy import ttl_simple
-from artiq.gateware.drtio.transceiver import gtx_7series
+from artiq.gateware.drtio.transceiver import gtx_7series, eem_serdes
 from artiq.gateware.drtio.siphaser import SiPhaser7Series
 from artiq.gateware.drtio.rx_synchronizer import XilinxRXSynchronizer
 from artiq.gateware.drtio import *
@@ -201,6 +201,7 @@ class GenericMaster(SoCCore):
     def __init__(self, description, acpki=False):
         clk_freq = description["rtio_frequency"]
 
+        has_drtio_over_eem = any(peripheral["type"] == "shuttler" for peripheral in description["peripherals"])
         self.acpki = acpki
 
         platform = kasli_soc.Platform()
@@ -246,6 +247,8 @@ class GenericMaster(SoCCore):
 
         self.rtio_channels = []
         has_grabber = any(peripheral["type"] == "grabber" for peripheral in description["peripherals"])
+        if has_drtio_over_eem:
+            self.eem_drtio_channels = []
         if has_grabber:
             self.grabber_csr_group = []
         eem_7series.add_peripherals(self, description["peripherals"], iostandard=eem_iostandard)
@@ -260,17 +263,17 @@ class GenericMaster(SoCCore):
 
         self.submodules.rtio_tsc = rtio.TSC(glbl_fine_ts_width=3)
 
-        drtio_csr_group = []
-        drtioaux_csr_group = []
-        drtioaux_memory_group = []
+        self.drtio_csr_group = []
+        self.drtioaux_csr_group = []
+        self.drtioaux_memory_group = []
         self.drtio_cri = []
         for i in range(len(self.gt_drtio.channels)):
             core_name = "drtio" + str(i)
             coreaux_name = "drtioaux" + str(i)
             memory_name = "drtioaux" + str(i) + "_mem"
-            drtio_csr_group.append(core_name)
-            drtioaux_csr_group.append(coreaux_name)
-            drtioaux_memory_group.append(memory_name)
+            self.drtio_csr_group.append(core_name)
+            self.drtioaux_csr_group.append(coreaux_name)
+            self.drtioaux_memory_group.append(memory_name)
 
             cdr = ClockDomainsRenamer({"rtio_rx": "rtio_rx" + str(i)})
 
@@ -289,9 +292,10 @@ class GenericMaster(SoCCore):
             self.add_memory_region(memory_name, self.mem_map["csr"] + memory_address, size * 2)
         self.config["HAS_DRTIO"] = None
         self.config["HAS_DRTIO_ROUTING"] = None
-        self.add_csr_group("drtio", drtio_csr_group)
-        self.add_csr_group("drtioaux", drtioaux_csr_group)
-        self.add_memory_group("drtioaux_mem", drtioaux_memory_group)
+
+        if has_drtio_over_eem:
+            self.add_eem_drtio(self.eem_drtio_channels)
+        self.add_drtio_cpuif_groups()
 
         self.submodules.rtio_core = rtio.Core(
             self.rtio_tsc, self.rtio_channels, lane_count=description["sed_lanes"]
@@ -340,6 +344,42 @@ class GenericMaster(SoCCore):
         self.comb += [self.virtual_leds.get(i).eq(channel.rx_ready)
                 for i, channel in enumerate(self.gt_drtio.channels)]
 
+    def add_eem_drtio(self, eem_drtio_channels):
+        # Must be called before invoking add_rtio() to construct the CRI
+        # interconnect properly
+        self.submodules.eem_transceiver = eem_serdes.EEMSerdes(self.platform, eem_drtio_channels)
+        self.csr_devices.append("eem_transceiver")
+        self.config["HAS_DRTIO_EEM"] = None
+        self.config["EEM_DRTIO_COUNT"] = len(eem_drtio_channels)
+
+        cdr = ClockDomainsRenamer({"rtio_rx": "sys"})
+        for i in range(len(self.eem_transceiver.channels)):
+            channel = i + len(self.gt_drtio.channels)
+            core_name = "drtio" + str(channel)
+            coreaux_name = "drtioaux" + str(channel)
+            memory_name = "drtioaux" + str(channel) + "_mem"
+            self.drtio_csr_group.append(core_name)
+            self.drtioaux_csr_group.append(coreaux_name)
+            self.drtioaux_memory_group.append(memory_name)
+
+            core = cdr(DRTIOMaster(self.rtio_tsc, self.eem_transceiver.channels[i]))
+            setattr(self.submodules, core_name, core)
+            self.drtio_cri.append(core.cri)
+            self.csr_devices.append(core_name)
+
+            coreaux = cdr(drtio_aux_controller.DRTIOAuxControllerBare(core.link_layer))
+            setattr(self.submodules, coreaux_name, coreaux)
+            self.csr_devices.append(coreaux_name)
+
+            size = coreaux.get_mem_size()
+            memory_address = self.axi2csr.register_port(coreaux.get_tx_port(), size)
+            self.axi2csr.register_port(coreaux.get_rx_port(), size)
+            self.add_memory_region(memory_name, self.mem_map["csr"] + memory_address, size * 2)
+
+    def add_drtio_cpuif_groups(self):
+        self.add_csr_group("drtio", self.drtio_csr_group)
+        self.add_csr_group("drtioaux", self.drtioaux_csr_group)
+        self.add_memory_group("drtioaux_mem", self.drtioaux_memory_group)
 
 
 class GenericSatellite(SoCCore):

src/gateware/zynq_clocking.py

@@ -69,6 +69,8 @@ class SYSCRG(Module, AutoCSR):
         # assumes bootstrap clock is same freq as main and sys output
         self.clock_domains.cd_sys = ClockDomain()
         self.clock_domains.cd_sys4x = ClockDomain(reset_less=True)
+        self.clock_domains.cd_sys5x = ClockDomain(reset_less=True)
+        self.clock_domains.cd_clk200 = ClockDomain()
 
         self.current_clock = CSRStatus()
 
@@ -78,11 +80,6 @@ class SYSCRG(Module, AutoCSR):
 
         period = 1e9/freq
 
-        pll_locked = Signal()
-        pll_sys = Signal()
-        pll_sys4x = Signal()
-        fb_clk = Signal()
-
         self.submodules.clk_sw_fsm = ClockSwitchFSM()
 
         if clk_sw is None:
@@ -91,32 +88,55 @@ class SYSCRG(Module, AutoCSR):
         else:
             self.comb += self.clk_sw_fsm.i_clk_sw.eq(clk_sw)
 
+        mmcm_locked = Signal()
+        mmcm_sys = Signal()
+        mmcm_sys4x = Signal()
+        mmcm_sys5x = Signal()
+        mmcm_clk208 = Signal()
+        mmcm_fb_clk = Signal()
         self.specials += [
-            Instance("PLLE2_ADV",
-                     p_STARTUP_WAIT="FALSE", o_LOCKED=pll_locked,
-                     p_BANDWIDTH="HIGH",
-                     p_REF_JITTER1=0.001,
-                     p_CLKIN1_PERIOD=period, i_CLKIN1=main_clk,
-                     p_CLKIN2_PERIOD=period, i_CLKIN2=bootstrap_clk,
-                     i_CLKINSEL=self.clk_sw_fsm.o_clk_sw,
+            Instance("MMCME2_ADV",
+                p_STARTUP_WAIT="FALSE", o_LOCKED=mmcm_locked,
+                p_BANDWIDTH="HIGH",
+                p_REF_JITTER1=0.001,
+                p_CLKIN1_PERIOD=period, i_CLKIN1=main_clk,
+                p_CLKIN2_PERIOD=period, i_CLKIN2=bootstrap_clk,
+                i_CLKINSEL=self.clk_sw_fsm.o_clk_sw,
 
-                     # VCO @ 1.5GHz when using 125MHz input
-                     # 1.2GHz for 100MHz (zc706)
-                     p_CLKFBOUT_MULT=12, p_DIVCLK_DIVIDE=1,
-                     i_CLKFBIN=fb_clk,
-                     i_RST=self.clk_sw_fsm.o_reset,
+                # VCO @ 1.25GHz
+                p_CLKFBOUT_MULT_F=10, p_DIVCLK_DIVIDE=1,
+                i_CLKFBIN=mmcm_fb_clk,
+                i_RST=self.clk_sw_fsm.o_reset,
 
-                     o_CLKFBOUT=fb_clk,
+                o_CLKFBOUT=mmcm_fb_clk,
 
-                     p_CLKOUT0_DIVIDE=3, p_CLKOUT0_PHASE=0.0,
-                     o_CLKOUT0=pll_sys4x,
+                p_CLKOUT0_DIVIDE_F=2.5, p_CLKOUT0_PHASE=0.0, o_CLKOUT0=mmcm_sys4x,
 
-                     p_CLKOUT1_DIVIDE=12, p_CLKOUT1_PHASE=0.0,
-                     o_CLKOUT1=pll_sys),
-            Instance("BUFG", i_I=pll_sys, o_O=self.cd_sys.clk),
-            Instance("BUFG", i_I=pll_sys4x, o_O=self.cd_sys4x.clk),
+                # 125MHz
+                p_CLKOUT1_DIVIDE=10, p_CLKOUT1_PHASE=0.0, o_CLKOUT1=mmcm_sys,
 
-            AsyncResetSynchronizer(self.cd_sys, ~pll_locked),
+                # 625MHz
+                p_CLKOUT2_DIVIDE=2, p_CLKOUT2_PHASE=0.0, o_CLKOUT2=mmcm_sys5x,
+
+                # 208MHz
+                p_CLKOUT3_DIVIDE=6, p_CLKOUT3_PHASE=0.0, o_CLKOUT3=mmcm_clk208,
+            ),
+            Instance("BUFG", i_I=mmcm_sys5x, o_O=self.cd_sys5x.clk),
+            Instance("BUFG", i_I=mmcm_sys, o_O=self.cd_sys.clk),
+            Instance("BUFG", i_I=mmcm_sys4x, o_O=self.cd_sys4x.clk),
+            Instance("BUFG", i_I=mmcm_clk208, o_O=self.cd_clk200.clk),
+            AsyncResetSynchronizer(self.cd_sys, ~mmcm_locked),
+            AsyncResetSynchronizer(self.cd_clk200, ~mmcm_locked),
         ]
 
+        reset_counter = Signal(4, reset=15)
+        ic_reset = Signal(reset=1)
+        self.sync.clk200 += \
+            If(reset_counter != 0,
+                reset_counter.eq(reset_counter - 1)
+            ).Else(
+                ic_reset.eq(0)
+            )
+        self.specials += Instance("IDELAYCTRL", i_REFCLK=ClockSignal("clk200"), i_RST=ic_reset)
+
         self.comb += self.current_clock.status.eq(self.clk_sw_fsm.o_clk_sw)

src/libboard_artiq/Cargo.toml.tpl

@@ -25,6 +25,7 @@ void = { version = "1", default-features = false }
 
 io = { path = "../libio", features = ["byteorder"] }
 libboard_zynq = { path = "@@ZYNQ_RS@@/libboard_zynq" }
+libsupport_zynq = { path = "@@ZYNQ_RS@@/libsupport_zynq", default-features = false, features = ["alloc_core"] }
 libregister = { path = "@@ZYNQ_RS@@/libregister" }
 libconfig = { path = "@@ZYNQ_RS@@/libconfig", features = ["fat_lfn"] }
 libcortex_a9 = { path = "@@ZYNQ_RS@@/libcortex_a9" }

src/libboard_artiq/src/drtio_eem.rs

@@ -0,0 +1,233 @@
+use crate::pl;
+use embedded_hal::prelude::_embedded_hal_blocking_delay_DelayUs;
+use libboard_zynq::timer::GlobalTimer;
+use libconfig::Config;
+use libsupport_zynq::alloc::format;
+use log::{debug, error, info};
+
+struct SerdesConfig {
+    pub delay: [u8; 4],
+}
+
+impl SerdesConfig {
+    pub fn as_bytes(&self) -> &[u8] {
+        unsafe {
+            core::slice::from_raw_parts(
+                (self as *const SerdesConfig) as *const u8,
+                core::mem::size_of::<SerdesConfig>(),
+            )
+        }
+    }
+}
+
+fn select_lane(lane_no: u8) {
+    unsafe {
+        pl::csr::eem_transceiver::lane_sel_write(lane_no);
+    }
+}
+
+fn apply_delay(tap: u8, timer: &mut GlobalTimer) {
+    unsafe {
+        pl::csr::eem_transceiver::dly_cnt_in_write(tap);
+        pl::csr::eem_transceiver::dly_ld_write(1);
+        timer.delay_us(1);
+        assert!(tap as u8 == pl::csr::eem_transceiver::dly_cnt_out_read());
+    }
+}
+
+fn apply_config(config: &SerdesConfig, timer: &mut GlobalTimer) {
+    for lane_no in 0..4 {
+        select_lane(lane_no as u8);
+        apply_delay(config.delay[lane_no], timer);
+    }
+}
+
+unsafe fn assign_delay(timer: &mut GlobalTimer) -> SerdesConfig {
+    // Select an appropriate delay for lane 0
+    select_lane(0);
+
+    //
+
+    let mut best_dly = None;
+
+    loop {
+        let mut prev = None;
+        for curr_dly in 0..32 {
+            //let read_align = read_align_fn(curr_dly, timer);
+            let curr_low_rate = read_align(curr_dly, timer);
+
+            if let Some(prev_low_rate) = prev {
+                // This is potentially a crossover position
+                if prev_low_rate <= curr_low_rate && curr_low_rate >= 0.5 {
+                    let prev_dev = 0.5 - prev_low_rate;
+                    let curr_dev = curr_low_rate - 0.5;
+                    let selected_idx = if prev_dev < curr_dev {
+                        curr_dly - 1
+                    } else {
+                        curr_dly
+                    };
+
+                    // The setup setup/hold calibration timing (even with
+                    // tolerance) might be invalid in other lanes due to skew.
+                    // 5 taps is very conservative, generally it is 1 or 2
+                    if selected_idx < 5 {
+                        prev = None;
+                        continue;
+                    } else {
+                        best_dly = Some(selected_idx);
+                        break;
+                    }
+                }
+            }
+
+            // Only rising slope from <= 0.5 can result in a rising low rate
+            // crossover at 50%.
+            if curr_low_rate <= 0.5 {
+                prev = Some(curr_low_rate);
+            }
+        }
+
+        if best_dly.is_none() {
+            error!("setup/hold timing calibration failed, retry in 1s...");
+            timer.delay_us(1_000_000);
+        } else {
+            break;
+        }
+    }
+
+    let best_dly = best_dly.unwrap();
+
+    apply_delay(best_dly, timer);
+    let mut delay_list = [best_dly; 4];
+
+    // Assign delay for other lanes
+    for lane_no in 1..=3 {
+        select_lane(lane_no as u8);
+
+        let mut min_deviation = 0.5;
+        let mut min_idx = 0;
+        for dly_delta in -3..=3 {
+            let index = (best_dly as isize + dly_delta) as u8;
+            let low_rate = read_align(index, timer);
+            // abs() from f32 is not available in core library
+            let deviation = if low_rate < 0.5 {
+                0.5 - low_rate
+            } else {
+                low_rate - 0.5
+            };
+
+            if deviation < min_deviation {
+                min_deviation = deviation;
+                min_idx = index;
+            }
+        }
+
+        apply_delay(min_idx, timer);
+        delay_list[lane_no] = min_idx;
+    }
+
+    debug!("setup/hold timing calibration: {:?}", delay_list);
+
+    SerdesConfig {
+        delay: delay_list,
+    }
+}
+
+fn read_align(dly: u8, timer: &mut GlobalTimer) -> f32 {
+    unsafe {
+        apply_delay(dly, timer);
+        pl::csr::eem_transceiver::counter_reset_write(1);
+
+        pl::csr::eem_transceiver::counter_enable_write(1);
+        timer.delay_us(2000);
+        pl::csr::eem_transceiver::counter_enable_write(0);
+
+        let (high, low) = (
+            pl::csr::eem_transceiver::counter_high_count_read(),
+            pl::csr::eem_transceiver::counter_low_count_read(),
+        );
+        if pl::csr::eem_transceiver::counter_overflow_read() == 1 {
+            panic!("Unexpected phase detector counter overflow");
+        }
+
+        low as f32 / (low + high) as f32
+    }
+}
+
+unsafe fn align_comma(timer: &mut GlobalTimer) {
+    loop {
+        for slip in 1..=10 {
+            // The soft transceiver has 2 8b10b decoders, which receives lane
+            // 0/1 and lane 2/3 respectively. The decoder are time-multiplexed
+            // to decode exactly 1 lane each sysclk cycle.
+            //
+            // The decoder decodes lane 0/2 data on odd sysclk cycles, buffer
+            // on even cycles, and vice versa for lane 1/3. Data/Clock latency
+            // could change timing. The extend bit flips the decoding timing,
+            // so lane 0/2 data are decoded on even cycles, and lane 1/3 data
+            // are decoded on odd cycles.
+            //
+            // This is needed because transmitting/receiving a 8b10b character
+            // takes 2 sysclk cycles. Adjusting bitslip only via ISERDES
+            // limits the range to 1 cycle. The wordslip bit extends the range
+            // to 2 sysclk cycles.
+            pl::csr::eem_transceiver::wordslip_write((slip > 5) as u8);
+
+            // Apply a double bitslip since the ISERDES is 2x oversampled.
+            // Bitslip is used for comma alignment purposes once setup/hold
+            // timing is met.
+            pl::csr::eem_transceiver::bitslip_write(1);
+            pl::csr::eem_transceiver::bitslip_write(1);
+            timer.delay_us(1);
+
+            pl::csr::eem_transceiver::comma_align_reset_write(1);
+            timer.delay_us(100);
+
+            if pl::csr::eem_transceiver::comma_read() == 1 {
+                debug!("comma alignment completed after {} bitslips", slip);
+                return;
+            }
+        }
+
+        error!("comma alignment failed, retrying in 1s...");
+        timer.delay_us(1_000_000);
+    }
+}
+
+pub fn init(timer: &mut GlobalTimer, cfg: &Config) {
+    for trx_no in 0..pl::csr::CONFIG_EEM_DRTIO_COUNT {
+        unsafe {
+            pl::csr::eem_transceiver::transceiver_sel_write(trx_no as u8);
+        }
+
+        let key = format!("eem_drtio_delay{}", trx_no);
+
+        let cfg_read = cfg.read(&key);
+        match cfg_read {
+            Ok(record) => {
+                info!("loading calibrated timing values from sd card");
+                unsafe {
+                    apply_config(&*(record.as_ptr() as *const SerdesConfig), timer);
+                }
+            }
+            Err(_) => {
+                info!("calibrating...");
+                let config = unsafe { assign_delay(timer) };
+
+                match cfg.write(&key, config.as_bytes().to_vec()) {
+                    Ok(()) => {
+                        info!("storing calibration timing values into sd card");
+                    }
+                    Err(e) => {
+                        error!("calibration successful but calibration timing values cannot be stored into sd card. Error:{}", e);
+                    }
+                };
+            }
+        }
+
+        unsafe {
+            align_comma(timer);
+            pl::csr::eem_transceiver::rx_ready_write(1);
+        }
+    }
+}

src/libboard_artiq/src/lib.rs

@@ -31,6 +31,8 @@ pub mod mem;
 pub mod pl;
 #[cfg(has_si5324)]
 pub mod si5324;
+#[cfg(has_drtio_eem)]
+pub mod drtio_eem;
 
 use core::{cmp, str};
 

src/runtime/src/main.rs

@@ -16,6 +16,8 @@ use libasync::task;
 #[cfg(feature = "target_kasli_soc")]
 use libboard_artiq::io_expander;
 use libboard_artiq::{identifier_read, logger, pl};
+#[cfg(has_drtio_eem)]
+use libboard_artiq::drtio_eem;
 use libboard_zynq::{gic, mpcore, timer::GlobalTimer};
 use libconfig::Config;
 use libcortex_a9::l2c::enable_l2_cache;
@@ -109,6 +111,9 @@ pub fn main_core0() {
 
     rtio_clocking::init(&mut timer, &cfg);
 
+    #[cfg(has_drtio_eem)]
+    drtio_eem::init(&mut timer, &cfg);
+
     task::spawn(ksupport::report_async_rtio_errors());
 
     #[cfg(feature = "target_kasli_soc")]

src/runtime/src/rtio_clocking.rs

@@ -104,6 +104,9 @@ fn init_drtio(timer: &mut GlobalTimer) {
     unsafe {
         pl::csr::rtio_core::reset_phy_write(1);
         pl::csr::gt_drtio::txenable_write(0xffffffffu32 as _);
+
+        #[cfg(has_drtio_eem)]
+        pl::csr::eem_transceiver::txenable_write(0xffffffffu32 as _);
     }
 }