This moves the calculation of the result for popcnt* into the
countbits unit, renamed from countzero, so that we can take two cycles
to get the result. The motivation for this is that the popcnt*
calculation was showing up as a critical path.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This adds an optional 16 bit x 16 bit signed multiplier and uses it
for multiply instructions that return the low 64 bits of the product
(mull[dw][o] and mulli, but not maddld) when the operands are both in
the range -2^15 .. 2^15 - 1. The "short" 16-bit multiplier produces
its result combinatorially, so a multiply that uses it executes in one
cycle. This improves the coremark result by about 4%, since coremark
does quite a lot of multiplies and they almost all have operands that
fit into 16 bits.
The presence of the short multiplier is controlled by a generic at the
execute1, SOC, core and top levels. For now, it defaults to off for
all platforms, and can be enabled using the --has_short_mult flag to
fusesoc.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
- mcrxrx put the bits in the wrong order
- addpcis was setting CR0 if the instruction bit 0 = 1, which it
shouldn't
- bpermd was producing 0 always and additionally had the wrong bit
numbering
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This implements most of the architected PMU events. The ones missing
are mostly the ones that depend on which level of the cache hierarchy
data is fetched from. The events implemented here, and their raw
event codes, are:
Floating-point operation completed (100f4)
Load completed (100fc)
Store completed (200f0)
Icache miss (200fc)
ITLB miss (100f6)
ITLB miss resolved (400fc)
Dcache load miss (400f0)
Dcache load miss resolved (300f8)
Dcache store miss (300f0)
DTLB miss (300fc)
DTLB miss resolved (200f6)
No instruction available and none being executed (100f8)
Instruction dispatched (200f2, 300f2, 400f2)
Taken branch instruction completed (200fa)
Branch mispredicted (400f6)
External interrupt taken (200f8)
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This is the start of an implementation of a PMU according to PowerISA
v3.0B. Things not implemented yet include most architected events,
the BHRB, event-based branches, thresholding, MMCR0[TBCC] field, etc.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
At present the logic prevents any interrupts from being handled while
there is a load/store instruction (one that has unit=LDST) being
executed. However, load/store instructions can still get sent to
loadstore1. Thus an instruction which should generate an interrupt
such as a floating-point unavailable interrupt will instead get
executed.
To fix this, when we detect that an interrupt should be generated but
loadstore1 is still executing a previous instruction, we don't execute
any new instructions, and set a new r.intr_pending flag. That results
in busy_out being asserted (meaning that no further instructions will
come in from decode2). When loadstore1 has finished the instructions
it has, the interrupt gets sent to writeback. If one of the
instructions in loadstore1 generates an interrupt in the meantime, the
l_in.interrupt signal gets asserted and that clears r.intr_pending, so
the interrupt we detected gets discarded.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
The idea here is that we can have multiple instructions in progress at
the same time as long as they all go to the same unit, because that
unit will keep them in order. If we get an instruction for a
different unit, we wait for all the previous instructions to finish
before executing it. Since the loadstore unit is the only one that is
currently pipelined, this boils down to saying that loadstore
instructions can go ahead while l_in.in_progress = 1 but other
instructions have to wait until it is 0.
This gives a 2% increase on coremark performance on the Arty A7-100
(from ~190 to ~194).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This moves the logic for redirecting fetching and writing SRR0 and
SRR1 to writeback. The aim is that ultimately units other than
execute1 can send their interrupts to writeback along with their
instruction completions, so that there can be multiple instructions
in flight without needing execute1 to keep track of the address
of each outstanding instruction.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This changes the bypass path. Previously it went from after
execute1's output to after decode2's output. Now it goes from before
execute1's output register to before decode2's output register. The
reason is that the new path will be simpler to manage when there are
possibly multiple instructions in flight. This means that the
bypassing can be managed inside decode2 and control.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This changes the way GPR hazards are detected and tracked. Instead of
having a model of the pipeline in gpr_hazard.vhdl, which has to mirror
the behaviour of the real pipeline exactly, we now assign a 2-bit tag
to each instruction and record which GSPR the instruction writes.
Subsequent instructions that need to use the GSPR get the tag number
and stall until the value with that tag is being written back to the
register file.
For now, the forwarding paths are disabled. That gives about a 8%
reduction in coremark performance.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This uses the instruction doubling machinery to convert conditional
branch instructions that update both CTR and LR (e.g., bdnzl, bdnzlrl)
into two instructions, of which the first updates CTR and determines
whether the branch is taken, and the second updates LR and does the
redirect if necessary.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This uses the instruction-doubling machinery to send load with update
instructions down to loadstore1 as two separate ops, rather than
one op with two destinations. This will help to simplify the value
tracking mechanisms.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
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>
Using the main adder for comparisons has the disadvantage of creating
a long path from the CA/OV bit forwarding to v.busy via the carry
input of the adder, the comparison result, and determining whether a
trap instruction would trap. Instead we now have dedicated
comparators for the high and low words of a_in vs. b_in, and combine
their results to get the signed and unsigned comparison results.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This breaks up the enormous if .. elsif .. case .. elsif statement in
execute1 in order to try to make it simpler and more understandable.
We now have decode2 deciding whether the instruction has a value to be
written back to a register (GPR, GSPR, FPR, etc.) rather than
individual cases in execute1 setting result_en. The computation of
the data to be written back is now independent of detection of various
exception conditions. We now have an if block determining if any
exception condition exists which prevents the next instruction from
being executed, then the case statement which performs actions such as
setting carry/overflow bits, determining if a trap exception exists,
doing branches, etc., then an if statement for all the r.busy = 1
cases (continuing execution of an instruction which was started in a
previous cycle, or writing SRR1 for an interrupt).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This adds an explicit multiplexer feeding v.e.write_data in execute1,
with the select lines determined in the previous cycle based on the
insn_type. Similarly, for multiply and divide instructions, there is
now an explicit multiplexer.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This does the addition of the instruction NIA and the branch offset
after the register at the output of execute1 rather than before.
The propagation through the adder was showing up as a critical path
on the A7-100. Performance is unaffected and now it makes timing.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This makes it simpler to work out when to deliver a FPU unavailable
interrupt. This also means we can get rid of the OP_FPLOAD and
OP_FPSTORE insn_type values.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This implements the lq, stq, lqarx and stqcx. instructions.
These instructions all access two consecutive GPRs; for example the
"lq %r6,0(%r3)" instruction will load the doubleword at the address
in R3 into R7 and the doubleword at address R3 + 8 into R6. To cope
with having two GPR sources or destinations, the instruction gets
repeated at the decode2 stage, that is, for each lq/stq/lqarx/stqcx.
coming in from decode1, two instructions get sent out to execute1.
For these instructions, the RS or RT register gets modified on one
of the iterations by setting the LSB of the register number. In LE
mode, the first iteration uses RS|1 or RT|1 and the second iteration
uses RS or RT. In BE mode, this is done the other way around. In
order for decode2 to know what endianness is currently in use, we
pass the big_endian flag down from icache through decode1 to decode2.
This is always in sync with what execute1 is using because only rfid
or an interrupt can change MSR[LE], and those operations all cause
a flush and redirect.
There is now an extra column in the decode tables in decode1 to
indicate whether the instruction needs to be repeated. Decode1 also
enforces the rule that lq with RT = RT and lqarx with RA = RT or
RB = RT are illegal.
Decode2 now passes a 'repeat' flag and a 'second' flag to execute1,
and execute1 passes them on to loadstore1. The 'repeat' flag is set
for both iterations of a repeated instruction, and 'second' is set
on the second iteration. Execute1 does not take asynchronous or
trace interrupts on the second iteration of a repeated instruction.
Loadstore1 uses 'next_addr' for the second iteration of a repeated
load/store so that we access the second doubleword of the memory
operand. Thus loadstore1 accesses the doublewords in increasing
memory order. For 16-byte loads this means that the first iteration
writes GPR RT|1. It is possible that RA = RT|1 (this is a legal
but non-preferred form), meaning that if the memory operand was
misaligned, the first iteration would overwrite RA but then the
second iteration might take a page fault, leading to corrupted state.
To avoid that possibility, 16-byte loads in LE mode take an
alignment interrupt if the operand is not 16-byte aligned. (This
is the case anyway for lqarx, and we enforce it for lq as well.)
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This deletes some commentary that is now out of date and replaces it
with a simple statement about the XER common bits being forwarded from
the output of execute1 to the input.
The comment being deleted talked about a hazard if an instruction that
modifies XER[SO] is immediately followed by a store conditional. That
is no longer a problem because the operands for loadstore1 are sent
from execute1 (and therefore have the forwarded value) rather than
decode2. This was in fact fixed in 5422007f83 ("Plumb loadstore1
input from execute1 not decode2", 2020-01-14).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
We don't care what the values of TB and DECR are after reset, but we
don't want the X state to propagate to other parts of the chip.
Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
Random execution testcases showed that a bdnzl which doesn't branch,
followed immediately by a bdnz, uses the wrong value for CTR for the
bdnz. Decode2 detects the read-after-write hazard on CTR and tells
execute1 to use the bypass path. However, the bdnzl takes two cycles
because it has to write back both CTR and LR, meaning that by the time
the bdnz starts to execute, r.e.write_data no longer contains the CTR
value, but instead contains zero.
To fix this, we make execute1 maintain the written-back value of CTR
in r.e.write_data across the cycle where LR is written back (this is
possible because the LR writeback uses the exc_write_data path).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Branch instructions which do a redirect and write both CTR and LR were
not doing the write to LR due to a logic error. This fixes it.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
If an instruction fetch results in an instruction TLB miss, an
OP_FETCH_FAILED instruction is sent down the pipe. If the MSR[TE]
field is set for instruction tracing, the core currently considers
that executing the OP_FETCH_FAILED counts as having executed one
instruction and so generates a trace interrupt on the next valid
instruction, meaning that the trace interrupt happens before the
desired instruction rather than after it.
Fix this by not tracing OP_FETCH_FAILED instructions.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
This adds the skeleton of a floating-point unit and implements the
mffs and mtfsf instructions.
Execute1 sends FP instructions to the FPU and receives busy,
exception, FP interrupt and illegal interrupt signals from it.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
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 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>
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>
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>
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 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>
Anton Blanchard