Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2018-03-12 Thread Thomas Helland
2018-03-12 5:23 GMT+01:00 Dave Airlie : > Did anything ever comes of this series, trying some soft fp64 shaders, > and glsl copy opt is taking 2-3 seconds on the big ones. > > Nearly all spent in hash table insertions. > > Dave. I still have the patches around. I also have a new "pointer_map" in t

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2018-03-11 Thread Dave Airlie
Did anything ever comes of this series, trying some soft fp64 shaders, and glsl copy opt is taking 2-3 seconds on the big ones. Nearly all spent in hash table insertions. Dave. ___ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freed

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-15 Thread Tapani Pälli
On 01/13/2017 08:55 PM, Thomas Helland wrote: 2017-01-13 18:41 GMT+01:00 Vladislav Egorov : 13.01.2017 15:31, Tapani Pälli пишет: On 01/12/2017 09:23 PM, Thomas Helland wrote: Walking the whole hash table, inserting entries by hashing them first is just a really really bad idea. We can s

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-14 Thread Vladislav Egorov
14.01.2017 02:32, Connor Abbott пишет: On Fri, Jan 13, 2017 at 1:55 PM, Thomas Helland wrote: 2017-01-13 18:41 GMT+01:00 Vladislav Egorov : 13.01.2017 15:31, Tapani Pälli пишет: On 01/12/2017 09:23 PM, Thomas Helland wrote: Walking the whole hash table, inserting entries by hashing them fi

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-13 Thread Connor Abbott
On Fri, Jan 13, 2017 at 1:55 PM, Thomas Helland wrote: > 2017-01-13 18:41 GMT+01:00 Vladislav Egorov : >> 13.01.2017 15:31, Tapani Pälli пишет: >>> >>> >>> >>> On 01/12/2017 09:23 PM, Thomas Helland wrote: Walking the whole hash table, inserting entries by hashing them first is just

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-13 Thread Thomas Helland
2017-01-13 18:41 GMT+01:00 Vladislav Egorov : > 13.01.2017 15:31, Tapani Pälli пишет: >> >> >> >> On 01/12/2017 09:23 PM, Thomas Helland wrote: >>> >>> Walking the whole hash table, inserting entries by hashing them first >>> is just a really really bad idea. We can simply memcpy the whole thing. >

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-13 Thread Владислав Егоров
> Quick benchmark of Tom's patches on shader-db. Thomas' patch, sorry. It's hard to simultaneously compose messages, and play in Paw Patrol with 3 yo kid. 2017-01-13 20:41 GMT+03:00 Vladislav Egorov : > 13.01.2017 15:31, Tapani Pälli пишет: > >> >> >> On 01/12/2017 09:23 PM, Thomas Helland wrote

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-13 Thread Vladislav Egorov
13.01.2017 15:31, Tapani Pälli пишет: On 01/12/2017 09:23 PM, Thomas Helland wrote: Walking the whole hash table, inserting entries by hashing them first is just a really really bad idea. We can simply memcpy the whole thing. Maybe it is just 'really' not 'really really' since I don't spot a

Re: [Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-13 Thread Tapani Pälli
On 01/12/2017 09:23 PM, Thomas Helland wrote: Walking the whole hash table, inserting entries by hashing them first is just a really really bad idea. We can simply memcpy the whole thing. Maybe it is just 'really' not 'really really' since I don't spot any difference in time running the tort

[Mesa-dev] [PATCH 4/4] glsl: Use hash table cloning in copy propagation

2017-01-12 Thread Thomas Helland
Walking the whole hash table, inserting entries by hashing them first is just a really really bad idea. We can simply memcpy the whole thing. This eliminates hash_table_insert from perf's top 15 costly functions. --- src/compiler/glsl/opt_copy_propagation.cpp | 17 - .../glsl/o