- 15 Apr, 2016 3 commits
-
-
Wesley W. Terpstra authored
-
Dietrich Beck authored
-
Dietrich Beck authored
-
- 14 Apr, 2016 3 commits
-
-
Dietrich Beck authored
-
Dietrich Beck authored
-
Wesley W. Terpstra authored
-
- 13 Apr, 2016 10 commits
-
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
- 15 Dec, 2015 1 commit
-
-
Wesley W. Terpstra authored
-
- 11 Dec, 2015 2 commits
-
-
Mathias Kreider authored
ebm: Complete rework of EBM. Replaced out error prone flow control logic. High time I got round to this
-
Mathias Kreider authored
-
- 09 Dec, 2015 1 commit
-
-
Wesley W. Terpstra authored
-
- 08 Dec, 2015 2 commits
-
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
- 07 Dec, 2015 3 commits
-
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
- 31 Aug, 2015 1 commit
-
-
Wesley W. Terpstra authored
... this is actually not really a bug, but I can see why valgrind complains, so let's keep it happy.
-
- 29 Jun, 2015 2 commits
-
-
Wesley W. Terpstra authored
-
Wesley W. Terpstra authored
-
- 03 Jun, 2015 1 commit
-
-
Mathias Kreider authored
-
- 19 May, 2015 2 commits
-
-
Wesley W. Terpstra authored
-
Mathias Kreider authored
-
- 10 Apr, 2015 1 commit
-
-
Mathias Kreider authored
-
- 09 Apr, 2015 1 commit
-
-
Wesley W. Terpstra authored
It is indeed possible for the pass FIFO to have more than the tag FIFO. If the TX mux is blocked after popping the tag, but before popping the pass FIFO, the pass FIFO can have one more element. Thus, if you have all of the pending tags landing in the same FIFO (pass, wbm, cfg), you can end up with the situation where the tag FIFO is indeed less full and thus you refill the tag FIFO while overflowing the other FIFOs. The result of this bug is that when writing to slow slaves, a very homogeneous access pattern can end up with a corrupted word if you are unlucky. The worst part of this bug is that when I wrote that code, I was uncertain if this was safe and marked it to be reviewed. It never got reviewed. Doh.
-
- 04 Mar, 2015 2 commits
-
-
Wesley W. Terpstra authored
This reverts commit 8d5e5f78. It caused pcie to resend the header on each request!
-
Wesley W. Terpstra authored
-
- 03 Mar, 2015 1 commit
-
-
Wesley W. Terpstra authored
-
- 06 Feb, 2015 1 commit
-
-
Wesley W. Terpstra authored
-
- 13 Jan, 2015 2 commits
-
-
Mathias Kreider authored
-
Mathias Kreider authored
-
- 15 Sep, 2014 1 commit
-
-
Wesley W. Terpstra authored
-