This adds code to loadstore1 to convert between single-precision and
double-precision formats, and implements the lfs* and stfs*
instructions. The conversion processes are described in Power ISA
v3.1 Book 1 sections 4.6.2 and 4.6.3.
These conversions take one cycle, so lfs* and stfs* are one cycle
slower than lfd* and stfd*.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This tests that floating-point unavailable exceptions occur as expected
on FP loads and stores, and that the simple FP loads and stores appear
to give reasonable results.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This extends the register file so it can hold FPR values, and
implements the FP loads and stores that do not require conversion
between single and double precision.
We now have the FP, FE0 and FE1 bits in MSR. FP loads and stores
cause a FP unavailable interrupt if MSR[FP] = 0.
The FPU facilities are optional and their presence is controlled by
the HAS_FPU generic passed down from the top-level board file. It
defaults to true for all except the A7-35 boards.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Trace interrupts occur when the MSR[TE] field is non-zero and an
instruction other than rfid has been successfully completed. A trace
interrupt occurs before the next instruction is executed or any
asynchronous interrupt is taken.
Since the trace interrupt is defined to set SRR1 bits depending on
whether the traced instruction is a load or an instruction treated as
a load, or a store or an instruction treated as a store, we need to
make sure the treated-as-a-load instructions (icbi, icbt, dcbt, dcbst,
dcbf) and the treated-as-a-store instructions (dcbtst, dcbz) have the
correct opcodes in decode1. Several of them were previously marked as
OP_NOP.
We don't yet implement the SIAR or SDAR registers, which should be set
by trace interrupts.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
In the cases where we need to override the values from the decode ROMs,
we now do that overriding after the clock edge (eating into decode2's
cycle) rather than before. This helps timing a little.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This checks that the instructions seem to update memory as expected,
and also that they generate alignment interrupts when necessary.
We don't check whether the memory update is atomic as we don't have
SMP yet.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Load-and-reserve and store-conditional instructions are required to
generate an alignment interrupt (0x600 vector) if their EA is not
aligned. Implement this.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
In 32-bit mode, effective addresses are truncated to 32 bits, both for
instruction fetches and data accesses, and CR0 is set for Rc=1 (record
form) instructions based on the lower 32 bits of the result rather
than all 64 bits.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Big-endian mode affects both instruction fetches and data accesses.
For instruction fetches, we byte-swap each word read from memory when
writing it into the icache data RAM, and use a tag bit to indicate
whether each cache line contains instructions in BE or LE form.
For data accesses, we simply need to invert the existing byte_reverse
signal in BE mode. The only thing to be careful of is to get the sign
bit from the correct place when doing a sign-extending load that
crosses two doublewords of memory.
For now, interrupts unconditionally set MSR[LE]. We will need some
sort of interrupt-little-endian bit somewhere, perhaps in LPCR.
This also fixes a debug report statement in fetch1.vhdl.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
The tests were using MSR values that did not have MSR_SF or MSR_LE
set. Fix this so that the test still works when 32-bit and BE modes
are implemented.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This is a NiteFury based PCIe M2 form-factor board originally
used for mining. It contains a speed grade 2 Artix 7 200T,
1GB of DDR3 and 32MB of flash.
The serial port is routed to pin 2 (RX) and 3 (TX) of the P2
connector (pin 1 is GND).
Note: Only 16MB of flash is currently usable until code is added
to configure the flash controller to use 4-bytes address commands
on that part.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To avoid adding too much logic, this moves the adder used by OP_ADD
out of the case statement in execute1.vhdl so that the result can
be used by OP_ADDG6S as well.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
These are no-ops that are reserved for future use as performance
hints, so we just need to treat them as no-ops.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
The addex instruction is like adde but uses the XER[OV] bit for the
carry in and out rather than XER[CA].
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This adds a true random number generator for the Xilinx FPGAs which
uses a set of chaotic ring oscillators to generate random bits and
then passes them through a Linear Hybrid Cellular Automaton (LHCA) to
remove bias, as described in "High Speed True Random Number Generators
in Xilinx FPGAs" by Catalin Baetoniu of Xilinx Inc., in:
https://pdfs.semanticscholar.org/83ac/9e9c1bb3dad5180654984604c8d5d8137412.pdf
This requires adding a .xdc file to tell vivado that the combinatorial
loops that form the ring oscillators are intentional. The same
code should work on other FPGAs as well if their tools can be told to
accept the combinatorial loops.
For simulation, the random.vhdl module gets compiled in, which uses
the pseudorand() function to generate random numbers.
Synthesis using yosys uses nonrandom.vhdl, which always signals an
error, causing darn to return 0xffff_ffff_ffff_ffff.
This adds an implementation of the darn instruction. Darn can return
either raw or conditioned random numbers. On Xilinx FPGAs, reading a
raw random number gives the output of the ring oscillators, and
reading a conditioned random number gives the output of the LHCA.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
These instructions use major opcode 4 and have a third GPR input
operand, so we need a decode table for major opcode 4 and some
plumbing to get the RC register operand read.
The multiply-add instructions use the same insn_type_t values as the
regular multiply instructions, and we distinguish in execute1 by
looking at the major opcode. This turns out to be convenient because
we don't have to add any cases in the code that handles the output of
the multiplier, and it frees up some insn_type_t values.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This also removes OP_MCRXR, as the mcrxr instruction was removed in
version 3.0B of the Power ISA, having been phased-out for the server
architecture since v2.02.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
We now expect the overflow signal from the multiplier to come along
one cycle later than the product.
This breaks up a long combinatorial path and improves timing.
This also changes some uses of v.<field> to r.<field> in the slow
op logic, which should help timing as well.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This makes the interface to the multiplier more general so an instance
of it can be used in the FPU. It now has a 128-bit addend that is
added on to the product. Instead of an input to negate the output,
it now has a "not_result" input to complement the output. Execute1
uses not_result=1 and addend=-1 to get the effect of negating the
output. The interface is defined this way because this is what can
be done easily with the Xilinx DSP slices in xilinx-mult.vhdl.
This also adds clock enable signals to the DSP slices, mostly for the
sake of reducing power consumption.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This rearranges the code used for store data formatting so that the
"for i in 0 to 7" loop indexes the output bytes rather than the
input bytes. The new expression is formally identical to the old
but is easier to synthesize. This reduces the number of LUTs by
about 250 on the Artix-7 and improves timing.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This reworks the way that the busy and done signals are generated in
loadstore in order to work around some problems where yosys/nextpnr
are reporting combinatorial loops (not in fact on the current code but
on minor variations needed for supporting the FPU). It seems that
yosys has problems with the case statement on v.state.
This also lifts the maddr and byte_sel generation out of the case
statement. The overall result is a slight reduction in resource usage
(~30 6-input LUTs on the A7-100).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This eliminates a path where the inputs to r1.wb.dat and r1.wb.sel
depend on req_op, which depends on the TLB and cache hit detection.
In fact they only need to depend on the nature of the request in
r0.req (i.e. DCBZ, store, cacheable load, or non-cacheable load).
This sets them at the beginning of the code for IDLE state rather
than inside the req_op case statement.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Commit d5c8c33bae ("decode1: Reformat to 4-space indentation") resulted
in some rows of major_decode_rom_array being misaligned. This fixes it.
No code change.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This computes the address sent to the MMU separately from that sent
to the dcache. This means that the address sent to the MMU doesn't
have the delay through the lsu_sum adder, making it available earlier.
The path through the lsu_sum adder and through the MMU to the MMU
done and err outputs showed up as a critical path on some builds.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This makes the calculation of busy as simple as possible and dependent
only on register outputs. The timing of busy is critical, as it gates
the valid signal for the next instruction, and therefore any delays
in dropping busy at the end of a load or store directly impact the
timing of a host of other paths.
This also separates the 'done without error' and 'done with error'
cases from the MMU into separate signals that are both driven directly
from registers.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This moves the incrementing or decrementing of r1.acks_pending
to the cycle after a strobe is output or an ack is seen on the
wishbone, and simplifies the logic that determines whether the
cycle is now complete. This means that the path from seeing
req_op equal to OP_STORE_HIT or OP_STORE_MISS to setting r1.state
and r1.cyc now just involves the stbs_done bit rather than a more
complex calculation involving the possibly incremented r1.acks_pending.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This makes d_out.valid and m_out.done come directly from registers in
order to improve timing. The inputs to the registers are set by the
same conditions that cause r1.hit_load_valid, r1.slow_valid,
r1.error_done and r1.stcx_fail to be set.
Note that the STORE_WAIT_ACK state doesn't test r1.mmu_req but assumes
that the request came from loadstore1. This is because we normally
have r1.full = 0 in this state, which means that r1.mmu_req can
change at any time.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This adds "if LOG_LENGTH > 0 generate" to the places in the core
where log output data is latched, so that when LOG_LENGTH = 0 we
don't create the logic to collect the data which won't be stored.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This uses an algorithm for count leading/trailing zeroes that is
faster on FPGAs, which makes timing easier. cntlz* and cnttz*
still take two cycles, though.
For count trailing zeroes, we compute x & -x, which for non-zero x
has a single 1 bit in the position of the least-significant 1 bit
in x. This one-hot representation can then be converted to a bit
number with six 32-input OR gates. For count leading zeroes, we
simply do a bit-reversal on x and then use the same algorithm.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This makes the l_out.done signal come from a clean latch, which
improves timing. The cost is that TLB load and invalidation
operations to the dcache now signal done back to loadstore1 one
cycle later than before, but that doesn't seem to affect overall
performance noticeably.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This improves timing by setting r1.wb.{adr,dat,sel} to the next
request when doing a write cycle on the wishbone before we know
whether the next request has a TLB and cache hit or not, i.e.
without depending on req_op. r1.wb.stb still depends on req_op.
This contains a workaround for what is probably a bug elsewhere,
in that changing r1.wb.sel unconditionally once we see stall=0
from the wishbone causes incorrect behaviour. Making it
conditional on there being a valid following request appears
to fix the problem.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This puts the inputs to the TLB PLRU through a register stage, so
the TLB PLRU update is done in the cycle after the TLB tag
matching rather than the same cycle. This improves timing.
The PLRU output is only used when writing the TLB in response to
a tlbwe request from the MMU, and that doesn't happen within one
cycle of a virtual-mode load or store, so the fact that the
tlb victim way information is delayed by one cycle doesn't
create any problems.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
The computation of two_dwords from r.second_bytes has shown up as
part of a critical path at times. Instead we add a 'last_dword'
flag to the reg_stage_t record which tells us more directly
whether a valid flag coming in from dcache means that the
instruction is done, thereby shortening the path to the busy output
back to execute1.
This also simplifies some of the trim_ctl logic. The two_dwords = 0
case could never have use_second(i) = 1 for any of the bytes being
transferred, so "not use_second(i)" is always 1.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This eliminates a dependency of r.f.redirect_nia on the carry out
from the main adder in the case of a conditional trap instruction.
We can set r.f.redirect_nia unconditionally, even if no interrupt
is generated.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Boris Shingarov