Commit Graph

15 Commits (047be5c0c3b2f12c9321412518e17b7267fe14ea)

Author SHA1 Message Date
Paul Mackerras 734e4c4a52 core: Add a short multiplier
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>
3 years ago
Paul Mackerras f1238299bd execute1: Take an extra cycle for OE=1 multiply instructions
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>
4 years ago
Paul Mackerras 535341961d multiplier: Generalize interface to the multiplier
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>
4 years ago
Paul Mackerras 9880fc7435 multiply: Move selection of result bits into execute1
This puts the logic that selects which bits of the multiplier result
get written into the destination GPR into execute1, moved out from
multiply.

The multiplier is now expected to do an unsigned multiplication of
64-bit operands, optionally negate the result, detect 32-bit
or 64-bit signed overflow of the result, and return a full 128-bit
result.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
4 years ago
Paul Mackerras c9a2076dd3 execute1: Remember dest GPR, RC, OE, XER for slow operations
For multiply and divide operations, execute1 now records the
destination GPR number, RC and OE from the instruction, and the
XER value.  This means that the multiply and divide units don't
need to record those values and then send them back to execute1.
This makes the interface to those units a bit simpler.  They
simply report an overflow signal along with the result value, and
execute1 takes care of updating XER if necessary.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
5 years ago
Paul Mackerras 2167186b5f Make multiplier hang off the side of execute1
With this, the multiplier isn't a separate pipe that decode2 issues
instructions to, but rather is a unit that execute1 sends operands
to and which sends the result back to execute1, which then sends it
to writeback.  Execute1 now sends a stall signal when it gets a
multiply instruction until it gets a valid signal back from the
multiplier.

This all means that we no longer need to mark the multiply
instructions as single-issue.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
5 years ago
Benjamin Herrenschmidt 501b6daf9b Add basic XER support
The carry is currently internal to execute1. We don't handle any of
the other XER fields.

This creates type called "xer_common_t" that contains the commonly
used XER bits (CA, CA32, SO, OV, OV32).

The value is stored in the CR file (though it could be a separate
module). The rest of the bits will be implemented as a separate
SPR and the two parts reconciled in mfspr/mtspr in latter commits.

We always read XER in decode2 (there is little point not to)
and send it down all pipeline branches as it will be needed in
writeback for all type of instructions when CR0:SO needs to be
updated (such forms exist for all pipeline branches even if we don't
yet implement them).

To avoid having to track XER hazards, we forward it back in EX1. This
assumes that other pipeline branches that can modify it (mult and div)
are running single issue for now.

One additional hazard to beware of is an XER:SO modifying instruction
in EX1 followed immediately by a store conditional. Due to our writeback
latency, the store will go down the LSU with the previous XER value,
thus the stcx. will set CR0:SO using an obsolete SO value.

I doubt there exist any code relying on this behaviour being correct
but we should account for it regardless, possibly by ensuring that
stcx. remain single issue initially, or later by adding some minimal
tracking or moving the LSU into the same pipeline as execute.

Missing some obscure XER affecting instructions like addex or mcrxrx.

[paulus@ozlabs.org - fix CA32 and OV32 for OP_ADD, fix order of
 arguments to set_ov]

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
5 years ago
Paul Mackerras 374f4c536d writeback: Do data formatting and condition recording in writeback
This adds code to writeback to format data and test the result
against zero for the purpose of setting CR0.  The data formatter
is able to shift and mask by bytes and do byte reversal and sign
extension.  It can also put together bytes from two input
doublewords to support unaligned loads (including unaligned
byte-reversed loads).

The data formatter starts with an 8:1 multiplexer that is able
to direct any byte of the input to any byte of the output.  This
lets us rotate the data and simultaneously byte-reverse it.
The rotated/reversed data goes to a register for the unaligned
cases that overlap two doublewords.  Then there is per-byte logic
that does trimming, sign extension, and splicing together bytes
from a previous input doubleword (stored in data_latched) and the
current doubleword.  Finally the 64-bit result is tested to set
CR0 if rc = 1.

This removes the RC logic from the execute2, multiply and divide
units, and the shift/mask/byte-reverse/sign-extend logic from
loadstore2.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
5 years ago
Benjamin Herrenschmidt 48e6e719d3 Multiply needs to be 16 stages to fix all timing issues
This seems dependent on the FPGA type/size, so we should probably
make it a toplevel generic, but for now this helps on the
Arty A7-35

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
5 years ago
Anton Blanchard 8dd97fbe7f Reformat multiply code
Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
5 years ago
Anton Blanchard 99dd4de54e Don't use VHDL 2008 condition operator in multiply
Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
5 years ago
Anton Blanchard 68533c4cfb Reduce multiply to 2 cycles
We want all non load/store ops to take 2 cycles to make
tracking write back easier.

Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
5 years ago
Anton Blanchard a22afbdb5b Quieten multiply warning
We no longer gate multiply with the valid signal, so it's complaining
a lot. Comment out the warning.

Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
5 years ago
Anton Blanchard 18b9b39a2c Simplify multiply
No need to gate everything with the valid bit.

Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
5 years ago
Anton Blanchard 5a29cb4699 Initial import of microwatt
Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
5 years ago