OpenCores
URL https://opencores.org/ocsvn/raytrac/raytrac/trunk

Subversion Repositories raytrac

[/] [raytrac/] [branches/] [fp/] [fadd32long.vhd] - Rev 255

Rev

Go to most recent revision | Details | Compare with Previous | Blame

Filtering Options

Clear current filter

Rev Log message Author Age Path
227 Fixed a BUG where big differences betweeen exponents difference suffered from miss-signedness because of the width of the result was 1 bit narrower, and still its highest significant bit was taken as the sign, in result big differences in where taken as negative results... leading to situations like A+0=0 cause the exponent chosen as the big one was the zero's (-127) leading to an unexpected 0 in the result. The bug was fixed by correcting the signedness of the operation and making the result less narrower in one bit. jguarin2002 4327d 23h /raytrac/branches/fp/fadd32long.vhd
169 Long Stupid, version of a 32 bit floating point I3E754 Adder jguarin2002 4442d 13h /raytrac/branches/fp/fadd32long.vhd
166 A strong revision on the decodification of the places to shift must be done..... I mean s5factor is EATING memory (Altera Synthesis), perhaps thats a better way jguarin2002 4445d 13h /raytrac/branches/fp/fadd32.vhd
165 Fix on the decodification of factor to add or sub to the final exponent after mantissa normalization (Stage 5, s5factor) jguarin2002 4445d 22h /raytrac/branches/fp/fadd32.vhd
164 reverting the not(s0delta(7)) change on revision 163 to s0delta(7) again jguarin2002 4447d 00h /raytrac/branches/fp/fadd32.vhd
163 dpc: Signals to eval in functional simulatio. Fix on the codification of the sign applied into the arithmetic block depending on the UCA code of the instruction being excuted. Also a correction was done on the decodification of the result queues write signals. A correction applied on the decodification of the interruptions generated due to full queues. RayTrac: A signal to decode the sign that goes into the addition operations was made as long with its combinatorial operation to calculate it. Fadd32: Signals to eval in functional simulation. An important bug was fixed when decoding the shift to normalize the mantissa of the float number with the minor exponent, that was causing a misscalculation of the normalized mantissa. Arithpack: Formatting of the instruction at function ap_format_instruction fixed due to a change in the opcodes of the unary instructions. jguarin2002 4447d 02h /raytrac/branches/fp/fadd32.vhd
160 Corrections derived from simulation debugging jguarin2002 4453d 09h /raytrac/branches/fp/fadd32.vhd
158 Changing std_logic_vector types to my custom far more convinients xfloat32\! jguarin2002 4454d 23h /raytrac/branches/fp/fadd32.vhd
157 For the first time the whole Raytrac RTL code compiled along with its testbench code in ModelSim jguarin2002 4455d 11h /raytrac/branches/fp/fadd32.vhd
155 Changes applied prior to testbenching using the script tb_compiler.py jguarin2002 4459d 00h /raytrac/branches/fp/fadd32.vhd
153 last modifications for tb_compiler.py compliance jguarin2002 4461d 15h /raytrac/branches/fp/fadd32.vhd
152 Test bench oriented modifications jguarin2002 4465d 17h /raytrac/branches/fp/fadd32.vhd
150 First Beta of RayTrac for a total size of 3874 lcells. Great Result\! jguarin2002 4538d 10h /raytrac/branches/fp/fadd32.vhd
139 Sync jguarin2002 4649d 01h /raytrac/branches/fp/fadd32.vhd
137 Syncing with enables and eleminated all the register outputs since none block should carry on a register output jguarin2002 4659d 17h /raytrac/branches/fp/fadd32.vhd
121 taking out std_logic_arith from sight.... no conversions allowed jguarin2002 4705d 04h /raytrac/branches/fp/fadd32.vhd
120 Beta 0 Adder LCELLS 373 jguarin2002 4711d 03h /raytrac/branches/fp/fadd32.vhd
119 382 LEs Adder, RTL viewer Check Ok jguarin2002 4711d 09h /raytrac/branches/fp/fadd32.vhd
118 fp beta version reached a 17,5% logic cell starting at 450 LEs and finishing in 371 LEs for fadd32 jguarin2002 4711d 16h /raytrac/branches/fp/fadd32.vhd

powered by: WebSVN 2.1.0

© copyright 1999-2024 OpenCores.org, equivalent to Oliscience, all rights reserved. OpenCores®, registered trademark.