|
|
|
library ieee;
|
|
|
|
use ieee.std_logic_1164.all;
|
|
|
|
|
|
|
|
library work;
|
|
|
|
use work.wishbone_types.all;
|
|
|
|
|
|
|
|
entity toplevel is
|
|
|
|
generic (
|
|
|
|
MEMORY_SIZE : positive := (384*1024);
|
|
|
|
RAM_INIT_FILE : string := "firmware.hex";
|
|
|
|
RESET_LOW : boolean := true;
|
|
|
|
CLK_INPUT : positive := 100000000;
|
|
|
|
CLK_FREQUENCY : positive := 100000000;
|
|
|
|
HAS_FPU : boolean := true;
|
fetch1: Implement a simple branch target cache
This implements a cache in fetch1, where each entry stores the address
of a simple branch instruction (b or bc) and the target of the branch.
When fetching sequentially, if the address being fetched matches the
cache entry, then fetching will be redirected to the branch target.
The cache has 1024 entries and is direct-mapped, i.e. indexed by bits
11..2 of the NIA.
The bus from execute1 now carries information about taken and
not-taken simple branches, which fetch1 uses to update the cache.
The cache entry is updated for both taken and not-taken branches, with
the valid bit being set if the branch was taken and cleared if the
branch was not taken.
If fetching is redirected to the branch target then that goes down the
pipe as a predicted-taken branch, and decode1 does not do any static
branch prediction. If fetching is not redirected, then the next
instruction goes down the pipe as normal and decode1 does its static
branch prediction.
In order to make timing, the lookup of the cache is pipelined, so on
each cycle the cache entry for the current NIA + 8 is read. This
means that after a redirect (from decode1 or execute1), only the third
and subsequent sequentially-fetched instructions will be able to be
predicted.
This improves the coremark value on the Arty A7-100 from about 180 to
about 190 (more than 5%).
The BTC is optional. Builds for the Artix 7 35-T part have it off by
default because the extra ~1420 LUTs it takes mean that the design
doesn't fit on the Arty A7-35 board.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
4 years ago
|
|
|
HAS_BTC : boolean := false;
|
|
|
|
LOG_LENGTH : natural := 512;
|
|
|
|
DISABLE_FLATTEN_CORE : boolean := false;
|
|
|
|
UART_IS_16550 : boolean := true
|
|
|
|
);
|
|
|
|
port(
|
|
|
|
ext_clk : in std_ulogic;
|
|
|
|
ext_rst : in std_ulogic;
|
|
|
|
|
|
|
|
-- UART0 signals:
|
|
|
|
uart0_txd : out std_ulogic;
|
|
|
|
uart0_rxd : in std_ulogic
|
|
|
|
);
|
|
|
|
end entity toplevel;
|
|
|
|
|
|
|
|
architecture behaviour of toplevel is
|
|
|
|
|
|
|
|
-- Reset signals:
|
|
|
|
signal soc_rst : std_ulogic;
|
|
|
|
signal pll_rst : std_ulogic;
|
|
|
|
|
|
|
|
-- Internal clock signals:
|
|
|
|
signal system_clk : std_ulogic;
|
|
|
|
signal system_clk_locked : std_ulogic;
|
|
|
|
|
|
|
|
begin
|
|
|
|
|
|
|
|
reset_controller: entity work.soc_reset
|
|
|
|
generic map(
|
|
|
|
RESET_LOW => RESET_LOW
|
|
|
|
)
|
|
|
|
port map(
|
|
|
|
ext_clk => ext_clk,
|
|
|
|
pll_clk => system_clk,
|
|
|
|
pll_locked_in => system_clk_locked,
|
|
|
|
ext_rst_in => ext_rst,
|
|
|
|
pll_rst_out => pll_rst,
|
|
|
|
rst_out => soc_rst
|
|
|
|
);
|
|
|
|
|
|
|
|
clkgen: entity work.clock_generator
|
|
|
|
generic map(
|
|
|
|
CLK_INPUT_HZ => CLK_INPUT,
|
|
|
|
CLK_OUTPUT_HZ => CLK_FREQUENCY
|
|
|
|
)
|
|
|
|
port map(
|
|
|
|
ext_clk => ext_clk,
|
|
|
|
pll_rst_in => pll_rst,
|
|
|
|
pll_clk_out => system_clk,
|
|
|
|
pll_locked_out => system_clk_locked
|
|
|
|
);
|
|
|
|
|
|
|
|
-- Main SoC
|
|
|
|
soc0: entity work.soc
|
|
|
|
generic map(
|
|
|
|
MEMORY_SIZE => MEMORY_SIZE,
|
|
|
|
RAM_INIT_FILE => RAM_INIT_FILE,
|
|
|
|
SIM => false,
|
|
|
|
CLK_FREQ => CLK_FREQUENCY,
|
|
|
|
HAS_FPU => HAS_FPU,
|
fetch1: Implement a simple branch target cache
This implements a cache in fetch1, where each entry stores the address
of a simple branch instruction (b or bc) and the target of the branch.
When fetching sequentially, if the address being fetched matches the
cache entry, then fetching will be redirected to the branch target.
The cache has 1024 entries and is direct-mapped, i.e. indexed by bits
11..2 of the NIA.
The bus from execute1 now carries information about taken and
not-taken simple branches, which fetch1 uses to update the cache.
The cache entry is updated for both taken and not-taken branches, with
the valid bit being set if the branch was taken and cleared if the
branch was not taken.
If fetching is redirected to the branch target then that goes down the
pipe as a predicted-taken branch, and decode1 does not do any static
branch prediction. If fetching is not redirected, then the next
instruction goes down the pipe as normal and decode1 does its static
branch prediction.
In order to make timing, the lookup of the cache is pipelined, so on
each cycle the cache entry for the current NIA + 8 is read. This
means that after a redirect (from decode1 or execute1), only the third
and subsequent sequentially-fetched instructions will be able to be
predicted.
This improves the coremark value on the Arty A7-100 from about 180 to
about 190 (more than 5%).
The BTC is optional. Builds for the Artix 7 35-T part have it off by
default because the extra ~1420 LUTs it takes mean that the design
doesn't fit on the Arty A7-35 board.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
4 years ago
|
|
|
HAS_BTC => HAS_BTC,
|
|
|
|
LOG_LENGTH => LOG_LENGTH,
|
|
|
|
DISABLE_FLATTEN_CORE => DISABLE_FLATTEN_CORE,
|
|
|
|
UART0_IS_16550 => UART_IS_16550
|
|
|
|
)
|
|
|
|
port map (
|
|
|
|
system_clk => system_clk,
|
|
|
|
rst => soc_rst,
|
|
|
|
uart0_txd => uart0_txd,
|
|
|
|
uart0_rxd => uart0_rxd
|
|
|
|
);
|
|
|
|
|
|
|
|
end architecture behaviour;
|