README.md

@@ -103,8 +103,14 @@ sudo dnf install fusesoc
 
 ```
 fusesoc init
-fusesoc fetch uart16550
+```
-fusesoc library add microwatt /path/to/microwatt
+
+- Create a working directory and point FuseSoC at microwatt:
+
+```
+mkdir microwatt-fusesoc
+cd microwatt-fusesoc
+fusesoc library add microwatt /path/to/microwatt/
 ```
 
 - Build using FuseSoC. For hello world (Replace nexys_video with your FPGA board such as --target=arty_a7-100):
@@ -122,68 +128,6 @@ You should then be able to see output via the serial port of the board (/dev/tty
 fusesoc run --target=nexys_video microwatt
 ```
 
-## Linux on Microwatt
-
-Mainline Linux supports Microwatt as of v5.14. The Arty A7 is the best tested
-platform, but it's also been tested on the OrangeCrab and ButterStick.
-
-1. Use buildroot to create a userspace
-
-   A small change is required to glibc in order to support the VMX/AltiVec-less
-   Microwatt, as float128 support is mandiatory and for this in GCC requires
-   VSX/AltiVec. This change is included in Joel's buildroot fork, along with a
-   defconfig:
-   ```
-   git clone -b microwatt https://github.com/shenki/buildroot
-   cd buildroot
-   make ppc64le_microwatt_defconfig
-   make
-   ```
-
-   The output is `output/images/rootfs.cpio`.
-
-2. Build the Linux kernel
-   ```
-   git clone https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-   cd linux
-   make ARCH=powerpc microwatt_defconfig
-   make ARCH=powerpc CROSS_COMPILE=powerpc64le-linux-gnu- \
-     CONFIG_INITRAMFS_SOURCE=/buildroot/output/images/rootfs.cpio -j`nproc`
-   ```
-
-   The output is `arch/powerpc/boot/dtbImage.microwatt.elf`.
-
-3. Build gateware using FuseSoC
-
-   First configure FuseSoC as above.
-   ```
-   fusesoc run --build --target=arty_a7-100 microwatt --no_bram --memory_size=0
-   ```
-
-   The output is `build/microwatt_0/arty_a7-100-vivado/microwatt_0.bit`.
-
-4. Program the flash
-
-   This operation will overwrite the contents of your flash.
-
-   For the Arty A7 A100, set `FLASH_ADDRESS` to `0x400000` and pass `-f a100`.
-
-   For the Arty A7 A35, set `FLASH_ADDRESS` to `0x300000` and pass `-f a35`.
-   ```
-   microwatt/openocd/flash-arty -f a100 build/microwatt_0/arty_a7-100-vivado/microwatt_0.bit
-   microwatt/openocd/flash-arty -f a100 dtbImage.microwatt.elf -t bin -a $FLASH_ADDRESS
-   ```
-
-5. Connect to the second USB TTY device exposed by the FPGA
-
-   ```
-   minicom -D /dev/ttyUSB1
-   ```
-
-   The gateware has firmware that will look at `FLASH_ADDRESS` and attempt to
-   parse an ELF there, loading it to the address specified in the ELF header
-   and jumping to it.
-
 ## Testing
 
 - A simple test suite containing random execution test cases and a couple of

core.vhdl

@@ -117,6 +117,7 @@ architecture behave of core is
     signal complete: instr_tag_t;
     signal terminate: std_ulogic;
     signal core_rst: std_ulogic;
+    signal icache_inv: std_ulogic;
     signal do_interrupt: std_ulogic;
 
     -- Delayed/Latched resets and alt_reset

dcache.vhdl

@@ -1121,6 +1121,7 @@ begin
     rams: for i in 0 to NUM_WAYS-1 generate
 	signal do_read  : std_ulogic;
 	signal rd_addr  : std_ulogic_vector(ROW_BITS-1 downto 0);
+	signal do_write : std_ulogic;
 	signal wr_addr  : std_ulogic_vector(ROW_BITS-1 downto 0);
 	signal wr_data  : std_ulogic_vector(wishbone_data_bits-1 downto 0);
 	signal wr_sel   : std_ulogic_vector(ROW_SIZE-1 downto 0);

divider.vhdl

@@ -42,8 +42,6 @@ begin
                 quot <= (others => '0');
                 running <= '0';
                 count <= "0000000";
-                is_32bit <= '0';
-                overflow <= '0';
             elsif d_in.valid = '1' then
                 if d_in.is_extended = '1'  then
                     dend <= '0' & d_in.dividend & x"0000000000000000";

execute1.vhdl

@@ -113,6 +113,8 @@ architecture behaviour of execute1 is
     signal misc_result: std_ulogic_vector(63 downto 0);
     signal muldiv_result: std_ulogic_vector(63 downto 0);
     signal spr_result: std_ulogic_vector(63 downto 0);
+    signal result_mux_sel: std_ulogic_vector(2 downto 0);
+    signal sub_mux_sel: std_ulogic_vector(2 downto 0);
     signal next_nia : std_ulogic_vector(63 downto 0);
     signal current: Decode2ToExecute1Type;
 

icache.vhdl

@@ -555,11 +555,7 @@ begin
 	--       I prefer not to do just yet as it would force fetch2 to know about
 	--       some of the cache geometry information.
 	--
-	if r.hit_valid = '1' then
         i_out.insn <= read_insn_word(r.hit_nia, cache_out(r.hit_way));
-	else
-            i_out.insn <= (others => '0');
-	end if;
 	i_out.valid <= r.hit_valid;
 	i_out.nia <= r.hit_nia;
 	i_out.stop_mark <= r.hit_smark;
@@ -824,7 +820,4 @@ begin
         end process;
         log_out <= log_data;
     end generate;
-
-    events <= ev;
-
 end;

icache_tb.vhdl

@@ -74,9 +74,6 @@ begin
         i_out.req <= '0';
         i_out.nia <= (others => '0');
         i_out.stop_mark <= '0';
-        i_out.priv_mode <= '1';
-        i_out.virt_mode <= '0';
-        i_out.big_endian <= '0';
 
         m_out.tlbld <= '0';
         m_out.tlbie <= '0';

loadstore1.vhdl

@@ -275,27 +275,10 @@ begin
         if rising_edge(clk) then
             if rst = '1' then
                 r1.req.valid <= '0';
-                r1.req.tlbie <= '0';
-                r1.req.is_slbia <= '0';
-                r1.req.instr_fault <= '0';
-                r1.req.load <= '0';
-                r1.req.priv_mode <= '0';
-                r1.req.sprn <= (others => '0');
-                r1.req.xerc <= xerc_init;
-
                 r2.req.valid <= '0';
-                r2.req.tlbie <= '0';
-                r2.req.is_slbia <= '0';
-                r2.req.instr_fault <= '0';
-                r2.req.load <= '0';
-                r2.req.priv_mode <= '0';
-                r2.req.sprn <= (others => '0');
-                r2.req.xerc <= xerc_init;
-
                 r2.wait_dc <= '0';
                 r2.wait_mmu <= '0';
                 r2.one_cycle <= '0';
-
                 r3.dar <= (others => '0');
                 r3.dsisr <= (others => '0');
                 r3.state <= IDLE;