Rev |
Log message |
Author |
Age |
Path |
249 |
Using a register as a 66.5 MHZ timer counter |
jguarin2002 |
4296d 06h |
/raytrac/branches/fp_sgdma/ |
248 |
Corrected an error on the normal |
jguarin2002 |
4304d 12h |
/raytrac/branches/fp_sgdma/ |
246 |
framework for conditional and accumulative operations DESCRIBED NOT IMPLEMENTED |
jguarin2002 |
4311d 15h |
/raytrac/branches/fp_sgdma/ |
244 |
Changed the directory structure a little bit, there is now wide arith (which encapsulates in a single RTL 3 adders or 3 adders |
jguarin2002 |
4327d 09h |
/raytrac/branches/fp_sgdma/ |
243 |
The Registers BASE+1, BASE+2, BASE+3 are used now for debugging purposes |
jguarin2002 |
4327d 09h |
/raytrac/branches/fp_sgdma/ |
242 |
AS1 produced an unnoticed delay, the compiler geenerated an extra stage..... so a delay constant was added to sync this extra stage with the operation via ssync_chain |
jguarin2002 |
4327d 09h |
/raytrac/branches/fp_sgdma/ |
241 |
fmul32 x 6 multipliers wide |
jguarin2002 |
4328d 05h |
/raytrac/branches/fp_sgdma/ |
240 |
last minute correction |
jguarin2002 |
4328d 09h |
/raytrac/branches/fp_sgdma/ |
239 |
wide multiplicator added to avoid optimization |
jguarin2002 |
4328d 09h |
/raytrac/branches/fp_sgdma/ |
238 |
wide multiplicator added to avoid optimization |
jguarin2002 |
4328d 09h |
/raytrac/branches/fp_sgdma/ |
237 |
corrected errors in raytrac.vhd |
jguarin2002 |
4328d 11h |
/raytrac/branches/fp_sgdma/ |
236 |
Tunnning delay added to q0 queue |
jguarin2002 |
4328d 14h |
/raytrac/branches/fp_sgdma/ |
235 |
Tunnning delay added to q0 queue |
jguarin2002 |
4328d 14h |
/raytrac/branches/fp_sgdma/ |
234 |
raytrac update nothing major |
jguarin2002 |
4329d 14h |
/raytrac/branches/fp_sgdma/ |
233 |
raytrac sopc component updated |
jguarin2002 |
4329d 14h |
/raytrac/branches/fp_sgdma/ |
232 |
raytrac sopc component updated |
jguarin2002 |
4329d 14h |
/raytrac/branches/fp_sgdma/ |
231 |
nfetch address counter implemented in a whole register for convinience |
jguarin2002 |
4329d 15h |
/raytrac/branches/fp_sgdma/ |
230 |
RC 1.0 Previous rev(228), is functional and even more than this one, but is bigger and is for debugging |
jguarin2002 |
4334d 17h |
/raytrac/branches/fp_sgdma/ |
229 |
Total RtEngine Hardware, BUT, problems with interconnection... perhaps theres a problem with long path on ssumando5 |
jguarin2002 |
4335d 17h |
/raytrac/branches/fp_sgdma/ |
228 |
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 |
4337d 10h |
/raytrac/branches/fp_sgdma/ |
221 |
The change in sqrt and inv is about the path of the files with the data memory. dpc has been changed by ap_n_dpc and there was an error on RayTrac related to the load sync chain: the loading of Dot product Operation was being carried out as if it was an unary operation rather than a two operands operation |
jguarin2002 |
4347d 01h |
/raytrac/branches/fp_sgdma/ |
220 |
ap_n_dpc.vhd es el RTL que integra DataPathControl y ArithPipeLine |
jguarin2002 |
4347d 02h |
/raytrac/branches/fp_sgdma/ |
219 |
RayTrac: Non tested and witouh TSE |
jguarin2002 |
4347d 03h |
/raytrac/branches/fp_sgdma/ |
218 |
Raytrac : NS_JULI_DSF_ASM_DMA_120812_18081 : SOPC Library TCL scrip, load it into the Altera Project |
jguarin2002 |
4347d 07h |
/raytrac/branches/fp_sgdma/ |
217 |
Raytrac : NS_JULI_DSF_ASM_DMA_120812_18081 : \n+ NIOS 2 Standard\n+ JTAG UART | UART | LCD | I2C TOUCH SCREEN\n+ DDR SDRAM | SSRAM | FLASH \n+ Avalon Memory Mapped Master Interface | Avalon Memory Mapped Slave Interface \n+ Direct Memory Access Support \n+ 18081 logic elements out of 24624 (73%) used |
jguarin2002 |
4347d 07h |
/raytrac/branches/fp_sgdma/ |
216 |
At the moment memblock.vhd described 3 things: an input params queue (discarded, input control is made with master_readdatavalid signal and load_sync_chain) a load sync_chain(implemented in raytrac.vhd) and 4 result queues, which were implemented as a single result queue in raytrac.vhd).\n\n\ncustom_counter and Raytrac_control, are no longer needed |
jguarin2002 |
4347d 22h |
/raytrac/branches/fp_sgdma/ |
215 |
At the moment memblock.vhd described 3 things: an input params queue (discarded, input control is made with master_readdatavalid signal and load_sync_chain) a load sync_chain(implemented in raytrac.vhd) and 4 result queues, which were implemented as a single result queue in raytrac.vhd).\n\n\ncustom_counter and Raytrac_control, are no longer needed |
jguarin2002 |
4347d 22h |
/raytrac/branches/fp_sgdma/ |
214 |
At the moment memblock.vhd described 3 things: an input params queue (discarded, input control is made with master_readdatavalid signal and load_sync_chain) a load sync_chain(implemented in raytrac.vhd) and 4 result queues, which were implemented as a single result queue in raytrac.vhd).\n\n\ncustom_counter and Raytrac_control, are no longer needed |
jguarin2002 |
4347d 22h |
/raytrac/branches/fp_sgdma/ |
213 |
Arithpack: changes to suppport the Beta Raytrac RTL description (with almost DMA caps) |
jguarin2002 |
4347d 22h |
/raytrac/branches/fp_sgdma/ |
212 |
DPC changes\n\n\t+ established the DCS system rather than the UCA definitively\n\t+ Rather than usign 4 result queues now theres just a single one, of course 4 times wider, this was made to gain simplicity when writing and reading the RTL description that adapts this 4/3/1 word wide result buffer output into a 1 word wide result buffer input\n\t+ Added the Q1 queue to syncrhonize magnitude and normalization ops, managing them to enter at the sime tame rather than different times, formerly it was implemented by setting the normalization and magnitude results into the results buffers at 25th beat and 20th beat respectively, now both results enter into THE SINGLE RESULT QUEUE at 25th beat. This change also forces that Dot product operation to use the Q1 hardware and entering also at beath 25th into the result queue, it could be done in an earlier beatt (in fact in the 19th) but multiplexation logic would have to be added. |
jguarin2002 |
4347d 23h |
/raytrac/branches/fp_sgdma/ |