Remove option for "short" 16x16 bit multiplier
authorPaul Mackerras <paulus@ozlabs.org>
Tue, 19 Jul 2022 02:29:47 +0000 (12:29 +1000)
committerPaul Mackerras <paulus@ozlabs.org>
Wed, 10 Aug 2022 01:27:45 +0000 (11:27 +1000)
commitd1e8e62feee3e2d2d01a69f1486e8099e8438b31
tree4a4d8330dbe065f05644368c9c38a3fd451d7833
parente02d8060edaa0300f14a695895f4a0b622e0351a
Remove option for "short" 16x16 bit multiplier

Now that we have a 33 bit x 33 bit signed multiplier in execute1,
there is really no need for the 16 bit multiplier.  The coremark
results are just as good without it as with it.  This removes the
option for the sake of simplicity.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
core.vhdl
execute1.vhdl
fpga/top-arty.vhdl
fpga/top-generic.vhdl
fpga/top-nexys-video.vhdl
fpga/top-orangecrab0.2.vhdl
fpga/top-wukong-v2.vhdl
microwatt.core
soc.vhdl