Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-05 Thread michal
Keith Whitwell wrote on 2010-01-04 18:46: > On Mon, 2010-01-04 at 09:39 -0800, Brian Paul wrote: > >> michal wrote: >> >>> Hi, >>> >>> I would like to merge gallium-integer-opcodes branch to master this >>> week. This feature branch adds support for integer operations in TGSI >>> that is

Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-04 Thread Keith Whitwell
On Mon, 2010-01-04 at 09:39 -0800, Brian Paul wrote: > michal wrote: > > Hi, > > > > I would like to merge gallium-integer-opcodes branch to master this > > week. This feature branch adds support for integer operations in TGSI > > that is required by GLSL 1.30. > > > > In summary: > > * add a b

Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-04 Thread Brian Paul
michal wrote: > Hi, > > I would like to merge gallium-integer-opcodes branch to master this > week. This feature branch adds support for integer operations in TGSI > that is required by GLSL 1.30. > > In summary: > * add a bunch of opcodes operating on signed and unsigned integers, > * add sign

Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-04 Thread Keith Whitwell
Given that we're going down the path of having typed operands, it would seem that new operands (like MOVDB) make sense. Keith On Mon, 2010-01-04 at 05:18 -0800, Igor Oliveira wrote: > Right, > > i was thinking tgsi supporting DOUBLE types. The first solution that i > was considering is use all o

Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-04 Thread Igor Oliveira
Right, i was thinking tgsi supporting DOUBLE types. The first solution that i was considering is use all operations like double value. Other way is create Double instructions like movdb ou something like that. what do you think? Igor On Mon, Jan 4, 2010 at 8:35 AM, michal wrote: > Igor Oliveir

Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-04 Thread michal
Igor Oliveira wrote on 2010-01-04 12:49: > Hi > > i was seeing the changes done by gallium-integer-opcodes the mov > operation using dst like float type in embedded systems can not be > slow? > > Igor, The MOV instruction always interprets the source operand as FLOAT, thus source operand modif

Re: [Mesa3d-dev] [RFC] gallium-integer-opcodes branch

2010-01-04 Thread Igor Oliveira
Hi i was seeing the changes done by gallium-integer-opcodes the mov operation using dst like float type in embedded systems can not be slow? Igor On Sun, Jan 3, 2010 at 4:14 PM, michal wrote: > Hi, > > I would like to merge gallium-integer-opcodes branch to master this > week. This feature bran