Rev |
Log message |
Author |
Age |
Path |
255 |
Documento Final con primeros resultados de desempeño |
jguarin2002 |
4275d 21h |
/raytrac/branches/fp/ |
254 |
... |
jguarin2002 |
4278d 16h |
/raytrac/branches/fp/ |
253 |
.... |
jguarin2002 |
4278d 16h |
/raytrac/branches/fp/ |
252 |
Performance Results on the Raytrac |
jguarin2002 |
4279d 20h |
/raytrac/branches/fp/ |
251 |
Es claro.... |
jguarin2002 |
4279d 20h |
/raytrac/branches/fp/ |
250 |
Design changed..... doubts about OS using |
jguarin2002 |
4279d 20h |
/raytrac/branches/fp/ |
247 |
Advance in application... but some normalization problems had popped up |
jguarin2002 |
4291d 08h |
/raytrac/branches/fp/ |
245 |
Avances pequenos en los documentos |
jguarin2002 |
4310d 15h |
/raytrac/branches/fp/ |
231 |
nfetch address counter implemented in a whole register for convinience |
jguarin2002 |
4315d 20h |
/raytrac/branches/fp/ |
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 |
4323d 19h |
/raytrac/branches/fp/ |
226 |
Documento 90%, falta el glosario de siglas, el anexo de referencia de RTLs, el capitulo 9 (trazador de rayos) y la bibiliografia |
jguarin2002 |
4323d 20h |
/raytrac/branches/fp/ |
225 |
Documento 90%, falta el glosario de siglas, el anexo de referencia de RTLs, el capitulo 9 (trazador de rayos) y la bibiliografia |
jguarin2002 |
4323d 21h |
/raytrac/branches/fp/ |
224 |
Documento 90%, falta el glosario de siglas, el anexo de referencia de RTLs, el capitulo 9 (trazador de rayos) y la bibiliografia |
jguarin2002 |
4323d 21h |
/raytrac/branches/fp/ |
223 |
Reportes para NS_JULI_SDF_ASM_AP_DMA_130812_21028 |
jguarin2002 |
4330d 20h |
/raytrac/branches/fp/ |
222 |
documento en un 55\% |
jguarin2002 |
4330d 20h |
/raytrac/branches/fp/ |
210 |
Document advance..... towards dma oriented raytrac |
jguarin2002 |
4345d 16h |
/raytrac/branches/fp/ |
199 |
Check out in the design document for changes made on Load logic, a load chain has been added to Memblock I/O and several memory blocks were removed, under construction, this version WONT in any means work |
jguarin2002 |
4361d 23h |
/raytrac/branches/fp/ |
197 |
Chnages on interconnectivity: Check out the SGDMA Sheets |
jguarin2002 |
4372d 00h |
/raytrac/branches/fp/ |
196 |
raytrac+sg_dma+raytrac. Step One, the DPC is transformed. Now there are five instructions (check the design document), theres no full queue sync event, there are only four result queues and only 3 add fp 32 b adders rather than 4. Even it seems like a reduction has taken place, decodification efforts take place when decoding multiplexation from arithmetic blocks towards the resulting queues |
jguarin2002 |
4375d 11h |
/raytrac/branches/fp/ |
195 |
Document advance and changes in the design |
jguarin2002 |
4378d 08h |
/raytrac/branches/fp/ |
194 |
Work In Progress |
jguarin2002 |
4393d 14h |
/raytrac/branches/fp/ |
193 |
WIP: Main Document |
jguarin2002 |
4394d 11h |
/raytrac/branches/fp/ |
192 |
Some change I dont realize what is it in the design document (xls) |
jguarin2002 |
4394d 22h |
/raytrac/branches/fp/ |
191 |
Reduced the implementation of Instruction Queue to 16 instructions rather than 32 and using registers in logic cells rather than M9Ks memory blocks.... finally the design fits. |
jguarin2002 |
4394d 22h |
/raytrac/branches/fp/ |
190 |
M9K Block reduction. And Altera Compiler Directive was added to adder code to prevent unnecesary M9K block inferring... |
jguarin2002 |
4399d 07h |
/raytrac/branches/fp/ |
189 |
Limiting Block size on the operands register to a maximum of 256 |
jguarin2002 |
4399d 13h |
/raytrac/branches/fp/ |
188 |
Fitting Report |
jguarin2002 |
4400d 20h |
/raytrac/branches/fp/ |
187 |
Sopc claims that int is a name that conflicts with verilog or vhdl standards, so a change on the int port was made by renaming it to irq |
jguarin2002 |
4400d 20h |
/raytrac/branches/fp/ |
186 |
Sopc claims that int is a name that conflicts with verilog or vhdl standards, so a change on the int port was made by renaming it to irq |
jguarin2002 |
4400d 20h |
/raytrac/branches/fp/ |
185 |
Well mulblock was a void inside file.... |
jguarin2002 |
4401d 10h |
/raytrac/branches/fp/ |