|
»
»
[PATCH] gallium: Add a PREDICATE register file.
|
View:
New views
13 Messages
—
Rating Filter:
Alert me
|
 |
[PATCH] gallium: Add a PREDICATE register file.
by michal-9
::
Rate this Message:
gallium: Add a PREDICATE register file.
There's already a shader token that allows composition of predicated instructions (tgsi_instruction_ext_predicate). However, there is no way one can write to thos predicate registers in the first place. --- src/gallium/include/pipe/p_shader_tokens.h | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h index de338c4..6aa8b27 100644 --- a/src/gallium/include/pipe/p_shader_tokens.h +++ b/src/gallium/include/pipe/p_shader_tokens.h @@ -79,6 +79,7 @@ enum tgsi_file_type { TGSI_FILE_ADDRESS =6, TGSI_FILE_IMMEDIATE =7, TGSI_FILE_LOOP =8, + TGSI_FILE_PREDICATE =9, TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ }; -- 1.6.4.msysgit.0 ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Keith Whitwell-3
::
Rate this Message:
On Fri, 2009-10-30 at 03:43 -0700, michal wrote:
> gallium: Add a PREDICATE register file. > > There's already a shader token that allows composition of predicated > instructions (tgsi_instruction_ext_predicate). However, there is no way > one can write to thos predicate registers in the first place. > --- > src/gallium/include/pipe/p_shader_tokens.h | 1 + > 1 files changed, 1 insertions(+), 0 deletions(-) > > diff --git a/src/gallium/include/pipe/p_shader_tokens.h > b/src/gallium/include/pipe/p_shader_tokens.h > index de338c4..6aa8b27 100644 > --- a/src/gallium/include/pipe/p_shader_tokens.h > +++ b/src/gallium/include/pipe/p_shader_tokens.h > @@ -79,6 +79,7 @@ enum tgsi_file_type { > TGSI_FILE_ADDRESS =6, > TGSI_FILE_IMMEDIATE =7, > TGSI_FILE_LOOP =8, > + TGSI_FILE_PREDICATE =9, > TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ > }; Michal, Is your expectation that all drivers become able to understand instructions with predicates? That seems unreasonable. What is the expected way of setting a predicate register? What functionality will use this? It seems there are three ways to do conditional execution in TGSI currently -- predicates, condition codes and IF/THEN/ELSE instructions. I'd really prefer to have at most two, and in fact preferably just one. Can you take a look at the three alternatives and figure out if one can be amputated? Ketih ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by michal-9
::
Rate this Message:
Keith Whitwell pisze:
> On Fri, 2009-10-30 at 03:43 -0700, michal wrote: > >> gallium: Add a PREDICATE register file. >> >> There's already a shader token that allows composition of predicated >> instructions (tgsi_instruction_ext_predicate). However, there is no way >> one can write to thos predicate registers in the first place. >> --- >> src/gallium/include/pipe/p_shader_tokens.h | 1 + >> 1 files changed, 1 insertions(+), 0 deletions(-) >> >> diff --git a/src/gallium/include/pipe/p_shader_tokens.h >> b/src/gallium/include/pipe/p_shader_tokens.h >> index de338c4..6aa8b27 100644 >> --- a/src/gallium/include/pipe/p_shader_tokens.h >> +++ b/src/gallium/include/pipe/p_shader_tokens.h >> @@ -79,6 +79,7 @@ enum tgsi_file_type { >> TGSI_FILE_ADDRESS =6, >> TGSI_FILE_IMMEDIATE =7, >> TGSI_FILE_LOOP =8, >> + TGSI_FILE_PREDICATE =9, >> TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ >> }; >> > > Michal, > > Is your expectation that all drivers become able to understand > instructions with predicates? That seems unreasonable. > > What is the expected way of setting a predicate register? What > functionality will use this? > > DECL IN[0..1] DECL OUT[0] DECL PRED[0] 1: MOV OUT[0], IN[0] 2: SGT PRED[0], IN[0], IN[1] 3: (PRED[0]) MOV OUT[0], IN[1] In (2) we set each component of PRED[0] to 1.0 if the corresponding components of IN[0] are greater than IN[1], and to 0.0 otherwise. In (3) we write IN[1] to only those components of OUT[0], for which the respective components of PRED[0] are non-zero. > It seems there are three ways to do conditional execution in TGSI > currently -- predicates, condition codes and IF/THEN/ELSE instructions. > > I'd really prefer to have at most two, and in fact preferably just one. > Can you take a look at the three alternatives and figure out if one can > be amputated? > > We could kill off the condition codes -- no driver uses that, and it's easier for us to emulate them with predicates than the other way round. ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Keith Whitwell-3
::
Rate this Message:
On Fri, 2009-10-30 at 04:36 -0700, michal wrote:
> Keith Whitwell pisze: > > On Fri, 2009-10-30 at 03:43 -0700, michal wrote: > > > >> gallium: Add a PREDICATE register file. > >> > >> There's already a shader token that allows composition of predicated > >> instructions (tgsi_instruction_ext_predicate). However, there is no way > >> one can write to thos predicate registers in the first place. > >> --- > >> src/gallium/include/pipe/p_shader_tokens.h | 1 + > >> 1 files changed, 1 insertions(+), 0 deletions(-) > >> > >> diff --git a/src/gallium/include/pipe/p_shader_tokens.h > >> b/src/gallium/include/pipe/p_shader_tokens.h > >> index de338c4..6aa8b27 100644 > >> --- a/src/gallium/include/pipe/p_shader_tokens.h > >> +++ b/src/gallium/include/pipe/p_shader_tokens.h > >> @@ -79,6 +79,7 @@ enum tgsi_file_type { > >> TGSI_FILE_ADDRESS =6, > >> TGSI_FILE_IMMEDIATE =7, > >> TGSI_FILE_LOOP =8, > >> + TGSI_FILE_PREDICATE =9, > >> TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ > >> }; > >> > > > > Michal, > > > > Is your expectation that all drivers become able to understand > > instructions with predicates? That seems unreasonable. > > > > What is the expected way of setting a predicate register? What > > functionality will use this? > > > > > For example: > > DECL IN[0..1] > DECL OUT[0] > DECL PRED[0] > > 1: MOV OUT[0], IN[0] > 2: SGT PRED[0], IN[0], IN[1] > 3: (PRED[0]) MOV OUT[0], IN[1] > > In (2) we set each component of PRED[0] to 1.0 if the corresponding > components of IN[0] are greater than IN[1], and to 0.0 otherwise. > In (3) we write IN[1] to only those components of OUT[0], for which the > respective components of PRED[0] are non-zero. > > > It seems there are three ways to do conditional execution in TGSI > > currently -- predicates, condition codes and IF/THEN/ELSE instructions. > > > > I'd really prefer to have at most two, and in fact preferably just one. > > Can you take a look at the three alternatives and figure out if one can > > be amputated? > > > > > We could kill off the condition codes -- no driver uses that, and it's > easier for us to emulate them with predicates than the other way round. I think I agree with that. Condition codes are pretty wierd, the only reason I'd keep them around is that there is the NV GPU4 extension sitting there as a ready-made definition of a high-end SM4-level assembly language. I don't know if Ian plans to introduce a MESA version of the program4 extension that more closely matches his program3 extension (ie predicates instead of condition codes). Keith ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Brian Paul-3
::
Rate this Message:
Keith Whitwell wrote:
> On Fri, 2009-10-30 at 04:36 -0700, michal wrote: >> Keith Whitwell pisze: >>> On Fri, 2009-10-30 at 03:43 -0700, michal wrote: >>> >>>> gallium: Add a PREDICATE register file. >>>> >>>> There's already a shader token that allows composition of predicated >>>> instructions (tgsi_instruction_ext_predicate). However, there is no way >>>> one can write to thos predicate registers in the first place. >>>> --- >>>> src/gallium/include/pipe/p_shader_tokens.h | 1 + >>>> 1 files changed, 1 insertions(+), 0 deletions(-) >>>> >>>> diff --git a/src/gallium/include/pipe/p_shader_tokens.h >>>> b/src/gallium/include/pipe/p_shader_tokens.h >>>> index de338c4..6aa8b27 100644 >>>> --- a/src/gallium/include/pipe/p_shader_tokens.h >>>> +++ b/src/gallium/include/pipe/p_shader_tokens.h >>>> @@ -79,6 +79,7 @@ enum tgsi_file_type { >>>> TGSI_FILE_ADDRESS =6, >>>> TGSI_FILE_IMMEDIATE =7, >>>> TGSI_FILE_LOOP =8, >>>> + TGSI_FILE_PREDICATE =9, >>>> TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ >>>> }; >>>> >>> Michal, >>> >>> Is your expectation that all drivers become able to understand >>> instructions with predicates? That seems unreasonable. >>> >>> What is the expected way of setting a predicate register? What >>> functionality will use this? >>> >>> >> For example: >> >> DECL IN[0..1] >> DECL OUT[0] >> DECL PRED[0] >> >> 1: MOV OUT[0], IN[0] >> 2: SGT PRED[0], IN[0], IN[1] >> 3: (PRED[0]) MOV OUT[0], IN[1] >> >> In (2) we set each component of PRED[0] to 1.0 if the corresponding >> components of IN[0] are greater than IN[1], and to 0.0 otherwise. >> In (3) we write IN[1] to only those components of OUT[0], for which the >> respective components of PRED[0] are non-zero. >> >>> It seems there are three ways to do conditional execution in TGSI >>> currently -- predicates, condition codes and IF/THEN/ELSE instructions. >>> >>> I'd really prefer to have at most two, and in fact preferably just one. >>> Can you take a look at the three alternatives and figure out if one can >>> be amputated? >>> >>> >> We could kill off the condition codes -- no driver uses that, and it's >> easier for us to emulate them with predicates than the other way round. > > I think I agree with that. Condition codes are pretty wierd, the only > reason I'd keep them around is that there is the NV GPU4 extension > sitting there as a ready-made definition of a high-end SM4-level > assembly language. > > I don't know if Ian plans to introduce a MESA version of the program4 > extension that more closely matches his program3 extension (ie > predicates instead of condition codes). Just FYI: GL_NV_fragment_program uses condition codes but we haven't supported that extension with Gallium; only the ARB versions. -Brian ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by michal-9
::
Rate this Message:
Brian Paul pisze:
> Keith Whitwell wrote: > >> On Fri, 2009-10-30 at 04:36 -0700, michal wrote: >> >>> Keith Whitwell pisze: >>> >>>> On Fri, 2009-10-30 at 03:43 -0700, michal wrote: >>>> >>>> >>>>> gallium: Add a PREDICATE register file. >>>>> >>>>> There's already a shader token that allows composition of predicated >>>>> instructions (tgsi_instruction_ext_predicate). However, there is no way >>>>> one can write to thos predicate registers in the first place. >>>>> --- >>>>> src/gallium/include/pipe/p_shader_tokens.h | 1 + >>>>> 1 files changed, 1 insertions(+), 0 deletions(-) >>>>> >>>>> diff --git a/src/gallium/include/pipe/p_shader_tokens.h >>>>> b/src/gallium/include/pipe/p_shader_tokens.h >>>>> index de338c4..6aa8b27 100644 >>>>> --- a/src/gallium/include/pipe/p_shader_tokens.h >>>>> +++ b/src/gallium/include/pipe/p_shader_tokens.h >>>>> @@ -79,6 +79,7 @@ enum tgsi_file_type { >>>>> TGSI_FILE_ADDRESS =6, >>>>> TGSI_FILE_IMMEDIATE =7, >>>>> TGSI_FILE_LOOP =8, >>>>> + TGSI_FILE_PREDICATE =9, >>>>> TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ >>>>> }; >>>>> >>>>> >>>> Michal, >>>> >>>> Is your expectation that all drivers become able to understand >>>> instructions with predicates? That seems unreasonable. >>>> >>>> What is the expected way of setting a predicate register? What >>>> functionality will use this? >>>> >>>> >>>> >>> For example: >>> >>> DECL IN[0..1] >>> DECL OUT[0] >>> DECL PRED[0] >>> >>> 1: MOV OUT[0], IN[0] >>> 2: SGT PRED[0], IN[0], IN[1] >>> 3: (PRED[0]) MOV OUT[0], IN[1] >>> >>> In (2) we set each component of PRED[0] to 1.0 if the corresponding >>> components of IN[0] are greater than IN[1], and to 0.0 otherwise. >>> In (3) we write IN[1] to only those components of OUT[0], for which the >>> respective components of PRED[0] are non-zero. >>> >>> >>>> It seems there are three ways to do conditional execution in TGSI >>>> currently -- predicates, condition codes and IF/THEN/ELSE instructions. >>>> >>>> I'd really prefer to have at most two, and in fact preferably just one. >>>> Can you take a look at the three alternatives and figure out if one can >>>> be amputated? >>>> >>>> >>>> >>> We could kill off the condition codes -- no driver uses that, and it's >>> easier for us to emulate them with predicates than the other way round. >>> >> I think I agree with that. Condition codes are pretty wierd, the only >> reason I'd keep them around is that there is the NV GPU4 extension >> sitting there as a ready-made definition of a high-end SM4-level >> assembly language. >> >> I don't know if Ian plans to introduce a MESA version of the program4 >> extension that more closely matches his program3 extension (ie >> predicates instead of condition codes). >> > > Just FYI: GL_NV_fragment_program uses condition codes but we haven't > supported that extension with Gallium; only the ARB versions. > > their future. Attached is an updated patch that obsoletes one TGSI token and fixes the other one, so we can specify swizzles and negation of predicate registers, per GL_MESA_gpu_program3. Thanks for comments. >From d1efdb692ae99871585554ddeaff75e700349d70 Mon Sep 17 00:00:00 2001 From: Michal Krol <michal@...> Date: Fri, 30 Oct 2009 13:55:14 +0000 Subject: [PATCH] gallium: Add a PREDICATE register file. There is little point in having a special TGSI token just to handle predicate register updates. Remove tgsi_dst_register_ext_predicate token and instead use a new PREDICATE register file to update predicates. Actually, the contents of the obsolete token are being moved to tgsi_instruction_ext_predicate, where they should be from the very beginning. --- src/gallium/include/pipe/p_shader_tokens.h | 40 +++++++--------------------- 1 files changed, 10 insertions(+), 30 deletions(-) diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h index de338c4..f3b8a7b 100644 --- a/src/gallium/include/pipe/p_shader_tokens.h +++ b/src/gallium/include/pipe/p_shader_tokens.h @@ -79,6 +79,7 @@ enum tgsi_file_type { TGSI_FILE_ADDRESS =6, TGSI_FILE_IMMEDIATE =7, TGSI_FILE_LOOP =8, + TGSI_FILE_PREDICATE =9, TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ }; @@ -427,11 +428,15 @@ struct tgsi_instruction_ext_texture struct tgsi_instruction_ext_predicate { - unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_PREDICATE */ - unsigned PredDstIndex : 4; /* UINT */ - unsigned PredWriteMask : 4; /* TGSI_WRITEMASK_ */ - unsigned Padding : 19; - unsigned Extended : 1; /* BOOL */ + unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_PREDICATE */ + unsigned PredSwizzleX : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSwizzleY : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSwizzleZ : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSwizzleW : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSrcIndex : 4; /* UINT */ + unsigned Negate : 1; /* BOOL */ + unsigned Padding : 14; + unsigned Extended : 1; /* BOOL */ }; /** @@ -548,7 +553,6 @@ struct tgsi_dst_register #define TGSI_DST_REGISTER_EXT_TYPE_CONDCODE 0 #define TGSI_DST_REGISTER_EXT_TYPE_MODULATE 1 -#define TGSI_DST_REGISTER_EXT_TYPE_PREDICATE 2 struct tgsi_dst_register_ext { @@ -566,9 +570,6 @@ struct tgsi_dst_register_ext * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_MODULATE, * it should be cast to tgsi_dst_register_ext_modulate. * - * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_PREDICATE, - * it should be cast to tgsi_dst_register_ext_predicate. - * * If tgsi_dst_register_ext::Extended is TRUE, another tgsi_dst_register_ext * follows. */ @@ -602,27 +603,6 @@ struct tgsi_dst_register_ext_modulate unsigned Extended : 1; /* BOOL */ }; -/* - * Currently, the following constraints apply. - * - * - PredSwizzleXYZW is either set to identity or replicate. - * - PredSrcIndex is 0. - */ - -struct tgsi_dst_register_ext_predicate -{ - unsigned Type : 4; /* TGSI_DST_REGISTER_EXT_TYPE_PREDICATE */ - unsigned PredSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSrcIndex : 4; /* UINT */ - unsigned Negate : 1; /* BOOL */ - unsigned Padding : 14; - unsigned Extended : 1; /* BOOL */ -}; - - #ifdef __cplusplus } #endif -- 1.6.4.msysgit.0 ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Keith Whitwell-3
::
Rate this Message:
On Fri, 2009-10-30 at 10:19 -0700, michal wrote:
> Brian Paul pisze: > > Keith Whitwell wrote: > > > >> On Fri, 2009-10-30 at 04:36 -0700, michal wrote: > >> > >>> Keith Whitwell pisze: > >>> > >>>> On Fri, 2009-10-30 at 03:43 -0700, michal wrote: > >>>> > >>>> > >>>>> gallium: Add a PREDICATE register file. > >>>>> > >>>>> There's already a shader token that allows composition of predicated > >>>>> instructions (tgsi_instruction_ext_predicate). However, there is no way > >>>>> one can write to thos predicate registers in the first place. > >>>>> --- > >>>>> src/gallium/include/pipe/p_shader_tokens.h | 1 + > >>>>> 1 files changed, 1 insertions(+), 0 deletions(-) > >>>>> > >>>>> diff --git a/src/gallium/include/pipe/p_shader_tokens.h > >>>>> b/src/gallium/include/pipe/p_shader_tokens.h > >>>>> index de338c4..6aa8b27 100644 > >>>>> --- a/src/gallium/include/pipe/p_shader_tokens.h > >>>>> +++ b/src/gallium/include/pipe/p_shader_tokens.h > >>>>> @@ -79,6 +79,7 @@ enum tgsi_file_type { > >>>>> TGSI_FILE_ADDRESS =6, > >>>>> TGSI_FILE_IMMEDIATE =7, > >>>>> TGSI_FILE_LOOP =8, > >>>>> + TGSI_FILE_PREDICATE =9, > >>>>> TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ > >>>>> }; > >>>>> > >>>>> > >>>> Michal, > >>>> > >>>> Is your expectation that all drivers become able to understand > >>>> instructions with predicates? That seems unreasonable. > >>>> > >>>> What is the expected way of setting a predicate register? What > >>>> functionality will use this? > >>>> > >>>> > >>>> > >>> For example: > >>> > >>> DECL IN[0..1] > >>> DECL OUT[0] > >>> DECL PRED[0] > >>> > >>> 1: MOV OUT[0], IN[0] > >>> 2: SGT PRED[0], IN[0], IN[1] > >>> 3: (PRED[0]) MOV OUT[0], IN[1] > >>> > >>> In (2) we set each component of PRED[0] to 1.0 if the corresponding > >>> components of IN[0] are greater than IN[1], and to 0.0 otherwise. > >>> In (3) we write IN[1] to only those components of OUT[0], for which the > >>> respective components of PRED[0] are non-zero. > >>> > >>> > >>>> It seems there are three ways to do conditional execution in TGSI > >>>> currently -- predicates, condition codes and IF/THEN/ELSE instructions. > >>>> > >>>> I'd really prefer to have at most two, and in fact preferably just one. > >>>> Can you take a look at the three alternatives and figure out if one can > >>>> be amputated? > >>>> > >>>> > >>>> > >>> We could kill off the condition codes -- no driver uses that, and it's > >>> easier for us to emulate them with predicates than the other way round. > >>> > >> I think I agree with that. Condition codes are pretty wierd, the only > >> reason I'd keep them around is that there is the NV GPU4 extension > >> sitting there as a ready-made definition of a high-end SM4-level > >> assembly language. > >> > >> I don't know if Ian plans to introduce a MESA version of the program4 > >> extension that more closely matches his program3 extension (ie > >> predicates instead of condition codes). > >> > > > > Just FYI: GL_NV_fragment_program uses condition codes but we haven't > > supported that extension with Gallium; only the ARB versions. > > > > > > We could always remove condition codes later, when Ian decides about > their future. > > Attached is an updated patch that obsoletes one TGSI token and fixes the > other one, so we can specify swizzles and negation of predicate > registers, per GL_MESA_gpu_program3. > > Thanks for comments. OK, I think I'd prefer to remove condition codes as part of this -- there are no users for them (that we care about), and we don't want drivers to have to implement both techniques. If in the future we want condition codes in the mesa state tracker, we'll have to do the work of converting them to predicates and/or IF/THEN/ELSE, but it will probably less effort than trying to teach all the drivers about condition codes. Can I ask for a third version that removes condition codes? In terms of drivers supporting this, we probably want another pipe_cap flag, probably PIPE_CAP_GPU3, to indicate that a particular driver has GPU3/SM3 support. Can you add that to the interface as well? Keith ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by michal-9
::
Rate this Message:
Keith Whitwell pisze:
> On Fri, 2009-10-30 at 10:19 -0700, michal wrote: > >> Brian Paul pisze: >> >>> Keith Whitwell wrote: >>> >>> >>>> On Fri, 2009-10-30 at 04:36 -0700, michal wrote: >>>> >>>> >>>>> Keith Whitwell pisze: >>>>> >>>>> >>>>>> On Fri, 2009-10-30 at 03:43 -0700, michal wrote: >>>>>> >>>>>> >>>>>> >>>>>>> gallium: Add a PREDICATE register file. >>>>>>> >>>>>>> There's already a shader token that allows composition of predicated >>>>>>> instructions (tgsi_instruction_ext_predicate). However, there is no way >>>>>>> one can write to thos predicate registers in the first place. >>>>>>> --- >>>>>>> src/gallium/include/pipe/p_shader_tokens.h | 1 + >>>>>>> 1 files changed, 1 insertions(+), 0 deletions(-) >>>>>>> >>>>>>> diff --git a/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> b/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> index de338c4..6aa8b27 100644 >>>>>>> --- a/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> +++ b/src/gallium/include/pipe/p_shader_tokens.h >>>>>>> @@ -79,6 +79,7 @@ enum tgsi_file_type { >>>>>>> TGSI_FILE_ADDRESS =6, >>>>>>> TGSI_FILE_IMMEDIATE =7, >>>>>>> TGSI_FILE_LOOP =8, >>>>>>> + TGSI_FILE_PREDICATE =9, >>>>>>> TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ >>>>>>> }; >>>>>>> >>>>>>> >>>>>>> >>>>>> Michal, >>>>>> >>>>>> Is your expectation that all drivers become able to understand >>>>>> instructions with predicates? That seems unreasonable. >>>>>> >>>>>> What is the expected way of setting a predicate register? What >>>>>> functionality will use this? >>>>>> >>>>>> >>>>>> >>>>>> >>>>> For example: >>>>> >>>>> DECL IN[0..1] >>>>> DECL OUT[0] >>>>> DECL PRED[0] >>>>> >>>>> 1: MOV OUT[0], IN[0] >>>>> 2: SGT PRED[0], IN[0], IN[1] >>>>> 3: (PRED[0]) MOV OUT[0], IN[1] >>>>> >>>>> In (2) we set each component of PRED[0] to 1.0 if the corresponding >>>>> components of IN[0] are greater than IN[1], and to 0.0 otherwise. >>>>> In (3) we write IN[1] to only those components of OUT[0], for which the >>>>> respective components of PRED[0] are non-zero. >>>>> >>>>> >>>>> >>>>>> It seems there are three ways to do conditional execution in TGSI >>>>>> currently -- predicates, condition codes and IF/THEN/ELSE instructions. >>>>>> >>>>>> I'd really prefer to have at most two, and in fact preferably just one. >>>>>> Can you take a look at the three alternatives and figure out if one can >>>>>> be amputated? >>>>>> >>>>>> >>>>>> >>>>>> >>>>> We could kill off the condition codes -- no driver uses that, and it's >>>>> easier for us to emulate them with predicates than the other way round. >>>>> >>>>> >>>> I think I agree with that. Condition codes are pretty wierd, the only >>>> reason I'd keep them around is that there is the NV GPU4 extension >>>> sitting there as a ready-made definition of a high-end SM4-level >>>> assembly language. >>>> >>>> I don't know if Ian plans to introduce a MESA version of the program4 >>>> extension that more closely matches his program3 extension (ie >>>> predicates instead of condition codes). >>>> >>>> >>> Just FYI: GL_NV_fragment_program uses condition codes but we haven't >>> supported that extension with Gallium; only the ARB versions. >>> >>> >>> >> We could always remove condition codes later, when Ian decides about >> their future. >> >> Attached is an updated patch that obsoletes one TGSI token and fixes the >> other one, so we can specify swizzles and negation of predicate >> registers, per GL_MESA_gpu_program3. >> >> Thanks for comments. >> > > OK, I think I'd prefer to remove condition codes as part of this -- > there are no users for them (that we care about), and we don't want > drivers to have to implement both techniques. > > If in the future we want condition codes in the mesa state tracker, > we'll have to do the work of converting them to predicates and/or > IF/THEN/ELSE, but it will probably less effort than trying to teach all > the drivers about condition codes. > > Can I ask for a third version that removes condition codes? > > In terms of drivers supporting this, we probably want another pipe_cap > flag, probably PIPE_CAP_GPU3, to indicate that a particular driver has > GPU3/SM3 support. Can you add that to the interface as well? > > >From d3102528484decff0a6d1effb27545c4d76976d1 Mon Sep 17 00:00:00 2001 From: Michal Krol <michal@...> Date: Fri, 30 Oct 2009 18:19:52 +0000 Subject: [PATCH] gallium: Cleanup predicate and condition code TGSI tokens. There is little point in having a special TGSI token just to handle predicate register updates. Remove tgsi_dst_register_ext_predicate token and instead use a new PREDICATE register file to update predicates. Actually, the contents of the obsolete token are being moved to tgsi_instruction_ext_predicate, where they should be from the very beginning. Remove the NVIDIA-specific condition code tokens -- nobody uses them and they can be emulated with predicates if needed. Introduce PIPE_CAP_GPU3 that indicates whether a driver supports SM3-level instructions, and in particular predicates. --- src/gallium/include/pipe/p_defines.h | 1 + src/gallium/include/pipe/p_shader_tokens.h | 111 ++++------------------------ 2 files changed, 17 insertions(+), 95 deletions(-) diff --git a/src/gallium/include/pipe/p_defines.h b/src/gallium/include/pipe/p_defines.h index 52887ea..98cb9e8 100644 --- a/src/gallium/include/pipe/p_defines.h +++ b/src/gallium/include/pipe/p_defines.h @@ -333,6 +333,7 @@ enum pipe_transfer_usage { #define PIPE_CAP_MAX_VERTEX_TEXTURE_UNITS 26 #define PIPE_CAP_TGSI_CONT_SUPPORTED 27 #define PIPE_CAP_BLEND_EQUATION_SEPARATE 28 +#define PIPE_CAP_GPU3 29 /*< GPU3/SM3 supported */ /** diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h index de338c4..8ec0f9c 100644 --- a/src/gallium/include/pipe/p_shader_tokens.h +++ b/src/gallium/include/pipe/p_shader_tokens.h @@ -79,6 +79,7 @@ enum tgsi_file_type { TGSI_FILE_ADDRESS =6, TGSI_FILE_IMMEDIATE =7, TGSI_FILE_LOOP =8, + TGSI_FILE_PREDICATE =9, TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ }; @@ -319,7 +320,6 @@ struct tgsi_instruction * instruction, including the instruction word. */ -#define TGSI_INSTRUCTION_EXT_TYPE_NV 0 #define TGSI_INSTRUCTION_EXT_TYPE_LABEL 1 #define TGSI_INSTRUCTION_EXT_TYPE_TEXTURE 2 #define TGSI_INSTRUCTION_EXT_TYPE_PREDICATE 3 @@ -332,9 +332,6 @@ struct tgsi_instruction_ext }; /* - * If tgsi_instruction_ext::Type is TGSI_INSTRUCTION_EXT_TYPE_NV, it should - * be cast to tgsi_instruction_ext_nv. - * * If tgsi_instruction_ext::Type is TGSI_INSTRUCTION_EXT_TYPE_LABEL, it * should be cast to tgsi_instruction_ext_label. * @@ -348,56 +345,11 @@ struct tgsi_instruction_ext * follows. */ -#define TGSI_PRECISION_DEFAULT 0 -#define TGSI_PRECISION_FLOAT32 1 -#define TGSI_PRECISION_FLOAT16 2 -#define TGSI_PRECISION_FIXED12 3 - -#define TGSI_CC_GT 0 -#define TGSI_CC_EQ 1 -#define TGSI_CC_LT 2 -#define TGSI_CC_GE 3 -#define TGSI_CC_LE 4 -#define TGSI_CC_NE 5 -#define TGSI_CC_TR 6 -#define TGSI_CC_FL 7 - #define TGSI_SWIZZLE_X 0 #define TGSI_SWIZZLE_Y 1 #define TGSI_SWIZZLE_Z 2 #define TGSI_SWIZZLE_W 3 -/** - * Precision controls the precision at which the operation should be executed. - * - * CondDstUpdate enables condition code register writes. When this field is - * TRUE, CondDstIndex specifies the index of the condition code register to - * update. - * - * CondFlowEnable enables conditional execution of the operation. When this - * field is TRUE, CondFlowIndex specifies the index of the condition code - * register to test against CondMask with component swizzle controled by - * CondSwizzleX, CondSwizzleY, CondSwizzleZ and CondSwizzleW. If the test fails, - * the operation is not executed. - */ - -struct tgsi_instruction_ext_nv -{ - unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_NV */ - unsigned Precision : 4; /* TGSI_PRECISION_ */ - unsigned CondDstIndex : 4; /* UINT */ - unsigned CondFlowIndex : 4; /* UINT */ - unsigned CondMask : 4; /* TGSI_CC_ */ - unsigned CondSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned CondDstUpdate : 1; /* BOOL */ - unsigned CondFlowEnable : 1; /* BOOL */ - unsigned Padding : 1; - unsigned Extended : 1; /* BOOL */ -}; - struct tgsi_instruction_ext_label { unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_LABEL */ @@ -425,13 +377,23 @@ struct tgsi_instruction_ext_texture unsigned Extended : 1; /* BOOL */ }; +/* + * Currently, the following constraints apply. + * + * - PredSwizzleXYZW is either set to identity or replicate. + * - PredSrcIndex is 0. + */ struct tgsi_instruction_ext_predicate { - unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_PREDICATE */ - unsigned PredDstIndex : 4; /* UINT */ - unsigned PredWriteMask : 4; /* TGSI_WRITEMASK_ */ - unsigned Padding : 19; - unsigned Extended : 1; /* BOOL */ + unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_PREDICATE */ + unsigned PredSwizzleX : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSwizzleY : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSwizzleZ : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSwizzleW : 2; /* TGSI_SWIZZLE_ */ + unsigned PredSrcIndex : 4; /* UINT */ + unsigned Negate : 1; /* BOOL */ + unsigned Padding : 14; + unsigned Extended : 1; /* BOOL */ }; /** @@ -546,9 +508,7 @@ struct tgsi_dst_register * Then, if tgsi_dst_register::Indirect is TRUE, tgsi_src_register follows. */ -#define TGSI_DST_REGISTER_EXT_TYPE_CONDCODE 0 #define TGSI_DST_REGISTER_EXT_TYPE_MODULATE 1 -#define TGSI_DST_REGISTER_EXT_TYPE_PREDICATE 2 struct tgsi_dst_register_ext { @@ -560,30 +520,12 @@ struct tgsi_dst_register_ext /** * Extra destination register modifiers * - * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_CONDCODE, - * it should be cast to tgsi_dst_register_ext_condcode. - * * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_MODULATE, * it should be cast to tgsi_dst_register_ext_modulate. * - * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_PREDICATE, - * it should be cast to tgsi_dst_register_ext_predicate. - * * If tgsi_dst_register_ext::Extended is TRUE, another tgsi_dst_register_ext * follows. */ -struct tgsi_dst_register_ext_concode -{ - unsigned Type : 4; /* TGSI_DST_REGISTER_EXT_TYPE_CONDCODE */ - unsigned CondMask : 4; /* TGSI_CC_ */ - unsigned CondSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSrcIndex : 4; /* UINT */ - unsigned Padding : 11; - unsigned Extended : 1; /* BOOL */ -}; #define TGSI_MODULATE_1X 0 #define TGSI_MODULATE_2X 1 @@ -602,27 +544,6 @@ struct tgsi_dst_register_ext_modulate unsigned Extended : 1; /* BOOL */ }; -/* - * Currently, the following constraints apply. - * - * - PredSwizzleXYZW is either set to identity or replicate. - * - PredSrcIndex is 0. - */ - -struct tgsi_dst_register_ext_predicate -{ - unsigned Type : 4; /* TGSI_DST_REGISTER_EXT_TYPE_PREDICATE */ - unsigned PredSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSrcIndex : 4; /* UINT */ - unsigned Negate : 1; /* BOOL */ - unsigned Padding : 14; - unsigned Extended : 1; /* BOOL */ -}; - - #ifdef __cplusplus } #endif -- 1.6.4.msysgit.0 ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Keith Whitwell-3
::
Rate this Message:
On Fri, 2009-10-30 at 11:24 -0700, michal wrote:
> > +/* > + * Currently, the following constraints apply. > + * > + * - PredSwizzleXYZW is either set to identity or replicate. > + * - PredSrcIndex is 0. > + */ Michal, This is looking a lot better. In terms of the above comment, is this talking about the semantics of PIPE_CAP_GPU3 ? Or is GPU3 supposed to do full PredSwizzle/PredSrcIndex, just we haven't implemented it somewhere (eg in tgsi_exec.c)? I'd think we want to either: - remove fields from the token so that the comment isn't necessary, - remove the comment and have GPU3 mean that the full semantics are available - come up with yet another cap bit to say whether or not full predicate semantics are implemented by a particular driver. Needless to say I don't like the last option, so I guess that means we need to decide now whether the full semantics in the token are in or out. How does SM3 fall on these issues? Keith ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by michal-9
::
Rate this Message:
Keith Whitwell pisze:
> On Fri, 2009-10-30 at 11:24 -0700, michal wrote: > >> +/* >> + * Currently, the following constraints apply. >> + * >> + * - PredSwizzleXYZW is either set to identity or replicate. >> + * - PredSrcIndex is 0. >> + */ >> > > Michal, > > This is looking a lot better. In terms of the above comment, is this > talking about the semantics of PIPE_CAP_GPU3 ? Or is GPU3 supposed to > do full PredSwizzle/PredSrcIndex, just we haven't implemented it > somewhere (eg in tgsi_exec.c)? > > I'd think we want to either: > - remove fields from the token so that the comment isn't necessary, > - remove the comment and have GPU3 mean that the full semantics are > available > - come up with yet another cap bit to say whether or not full predicate > semantics are implemented by a particular driver. > > Needless to say I don't like the last option, so I guess that means we > need to decide now whether the full semantics in the token are in or > out. > > How does SM3 fall on these issues? > > > to be either .xyzw or component replicate. The GL_MESA_gpu_program3 spec allows arbitrary swizzles (there's nothing in the document that would say otherwise). I say, rename PIPE_CAP_GPU3 to PIPE_CAP_SM3 to indicate predicates are supported with the mentioned swizzle constraints. When the dust settles on gpu_program3 spec, the state tracker will compensate for the lack of arbitrary swizzles if needed. Also, add PIPE_CAP_MAX_PREDICATES to query the number of predicate registers supported by the driver. That will allow us to remove the `PredSrcIndex is 0' constraint. ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by michal-9
::
Rate this Message:
michal pisze:
> Keith Whitwell pisze: > >> On Fri, 2009-10-30 at 11:24 -0700, michal wrote: >> >> >>> +/* >>> + * Currently, the following constraints apply. >>> + * >>> + * - PredSwizzleXYZW is either set to identity or replicate. >>> + * - PredSrcIndex is 0. >>> + */ >>> >>> >> Michal, >> >> This is looking a lot better. In terms of the above comment, is this >> talking about the semantics of PIPE_CAP_GPU3 ? Or is GPU3 supposed to >> do full PredSwizzle/PredSrcIndex, just we haven't implemented it >> somewhere (eg in tgsi_exec.c)? >> >> I'd think we want to either: >> - remove fields from the token so that the comment isn't necessary, >> - remove the comment and have GPU3 mean that the full semantics are >> available >> - come up with yet another cap bit to say whether or not full predicate >> semantics are implemented by a particular driver. >> >> Needless to say I don't like the last option, so I guess that means we >> need to decide now whether the full semantics in the token are in or >> out. >> >> How does SM3 fall on these issues? >> >> >> >> > The SM3 specification explicitly states that the predicate swizzle needs > to be either .xyzw or component replicate. The GL_MESA_gpu_program3 spec > allows arbitrary swizzles (there's nothing in the document that would > say otherwise). > > I say, rename PIPE_CAP_GPU3 to PIPE_CAP_SM3 to indicate predicates are > supported with the mentioned swizzle constraints. When the dust settles > on gpu_program3 spec, the state tracker will compensate for the lack of > arbitrary swizzles if needed. > > Also, add PIPE_CAP_MAX_PREDICATES to query the number of predicate > registers supported by the driver. That will allow us to remove the > `PredSrcIndex is 0' constraint. > > >From 085a5e8c33b2ed6347de2e86d9e972d70438c014 Mon Sep 17 00:00:00 2001 From: Michal Krol <michal@...> Date: Sat, 31 Oct 2009 09:09:26 +0000 Subject: [PATCH] gallium: Cleanup predicate and condition code TGSI tokens. There is little point in having a special TGSI token just to handle predicate register updates. Remove tgsi_dst_register_ext_predicate token and instead use a new PREDICATE register file to update predicates. Actually, the contents of the obsolete token are being moved to tgsi_instruction_ext_predicate, where they should be from the very beginning. Remove the NVIDIA-specific condition code tokens -- nobody uses them and they can be emulated with predicates if needed. Introduce PIPE_CAP_SM3 that indicates whether a driver supports SM3-level instructions, and in particular predicates. Add PIPE_CAP_MAX_PREDICATE_REGISTERS that can be used to query the driver how many predicate registers it supports (currently it would be 1). --- src/gallium/include/pipe/p_defines.h | 2 + src/gallium/include/pipe/p_shader_tokens.h | 117 ++++----------------------- 2 files changed, 20 insertions(+), 99 deletions(-) diff --git a/src/gallium/include/pipe/p_defines.h b/src/gallium/include/pipe/p_defines.h index 52887ea..6a61aea 100644 --- a/src/gallium/include/pipe/p_defines.h +++ b/src/gallium/include/pipe/p_defines.h @@ -333,6 +333,8 @@ enum pipe_transfer_usage { #define PIPE_CAP_MAX_VERTEX_TEXTURE_UNITS 26 #define PIPE_CAP_TGSI_CONT_SUPPORTED 27 #define PIPE_CAP_BLEND_EQUATION_SEPARATE 28 +#define PIPE_CAP_SM3 29 /*< Shader Model 3 supported */ +#define PIPE_CAP_MAX_PREDICATE_REGISTERS 30 /** diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h index de338c4..d4c8aad 100644 --- a/src/gallium/include/pipe/p_shader_tokens.h +++ b/src/gallium/include/pipe/p_shader_tokens.h @@ -1,6 +1,7 @@ /************************************************************************** * * Copyright 2008 Tungsten Graphics, Inc., Cedar Park, Texas. + * Copyright 2009 VMware, Inc. * All Rights Reserved. * * Permission is hereby granted, free of charge, to any person obtaining a @@ -25,8 +26,8 @@ * **************************************************************************/ -#ifndef TGSI_TOKEN_H -#define TGSI_TOKEN_H +#ifndef P_SHADER_TOKENS_H +#define P_SHADER_TOKENS_H #ifdef __cplusplus extern "C" { @@ -79,6 +80,7 @@ enum tgsi_file_type { TGSI_FILE_ADDRESS =6, TGSI_FILE_IMMEDIATE =7, TGSI_FILE_LOOP =8, + TGSI_FILE_PREDICATE =9, TGSI_FILE_COUNT /**< how many TGSI_FILE_ types */ }; @@ -319,7 +321,6 @@ struct tgsi_instruction * instruction, including the instruction word. */ -#define TGSI_INSTRUCTION_EXT_TYPE_NV 0 #define TGSI_INSTRUCTION_EXT_TYPE_LABEL 1 #define TGSI_INSTRUCTION_EXT_TYPE_TEXTURE 2 #define TGSI_INSTRUCTION_EXT_TYPE_PREDICATE 3 @@ -332,9 +333,6 @@ struct tgsi_instruction_ext }; /* - * If tgsi_instruction_ext::Type is TGSI_INSTRUCTION_EXT_TYPE_NV, it should - * be cast to tgsi_instruction_ext_nv. - * * If tgsi_instruction_ext::Type is TGSI_INSTRUCTION_EXT_TYPE_LABEL, it * should be cast to tgsi_instruction_ext_label. * @@ -348,56 +346,11 @@ struct tgsi_instruction_ext * follows. */ -#define TGSI_PRECISION_DEFAULT 0 -#define TGSI_PRECISION_FLOAT32 1 -#define TGSI_PRECISION_FLOAT16 2 -#define TGSI_PRECISION_FIXED12 3 - -#define TGSI_CC_GT 0 -#define TGSI_CC_EQ 1 -#define TGSI_CC_LT 2 -#define TGSI_CC_GE 3 -#define TGSI_CC_LE 4 -#define TGSI_CC_NE 5 -#define TGSI_CC_TR 6 -#define TGSI_CC_FL 7 - #define TGSI_SWIZZLE_X 0 #define TGSI_SWIZZLE_Y 1 #define TGSI_SWIZZLE_Z 2 #define TGSI_SWIZZLE_W 3 -/** - * Precision controls the precision at which the operation should be executed. - * - * CondDstUpdate enables condition code register writes. When this field is - * TRUE, CondDstIndex specifies the index of the condition code register to - * update. - * - * CondFlowEnable enables conditional execution of the operation. When this - * field is TRUE, CondFlowIndex specifies the index of the condition code - * register to test against CondMask with component swizzle controled by - * CondSwizzleX, CondSwizzleY, CondSwizzleZ and CondSwizzleW. If the test fails, - * the operation is not executed. - */ - -struct tgsi_instruction_ext_nv -{ - unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_NV */ - unsigned Precision : 4; /* TGSI_PRECISION_ */ - unsigned CondDstIndex : 4; /* UINT */ - unsigned CondFlowIndex : 4; /* UINT */ - unsigned CondMask : 4; /* TGSI_CC_ */ - unsigned CondSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned CondDstUpdate : 1; /* BOOL */ - unsigned CondFlowEnable : 1; /* BOOL */ - unsigned Padding : 1; - unsigned Extended : 1; /* BOOL */ -}; - struct tgsi_instruction_ext_label { unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_LABEL */ @@ -425,13 +378,21 @@ struct tgsi_instruction_ext_texture unsigned Extended : 1; /* BOOL */ }; +/* + * For SM3, the following constraint applies. + * - Swizzle is either set to identity or replicate. + */ struct tgsi_instruction_ext_predicate { - unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_PREDICATE */ - unsigned PredDstIndex : 4; /* UINT */ - unsigned PredWriteMask : 4; /* TGSI_WRITEMASK_ */ - unsigned Padding : 19; - unsigned Extended : 1; /* BOOL */ + unsigned Type : 4; /* TGSI_INSTRUCTION_EXT_TYPE_PREDICATE */ + unsigned SwizzleX : 2; /* TGSI_SWIZZLE_x */ + unsigned SwizzleY : 2; /* TGSI_SWIZZLE_x */ + unsigned SwizzleZ : 2; /* TGSI_SWIZZLE_x */ + unsigned SwizzleW : 2; /* TGSI_SWIZZLE_x */ + unsigned Negate : 1; /* BOOL */ + unsigned SrcIndex : 8; /* UINT */ + unsigned Padding : 10; + unsigned Extended : 1; /* BOOL */ }; /** @@ -546,9 +507,7 @@ struct tgsi_dst_register * Then, if tgsi_dst_register::Indirect is TRUE, tgsi_src_register follows. */ -#define TGSI_DST_REGISTER_EXT_TYPE_CONDCODE 0 #define TGSI_DST_REGISTER_EXT_TYPE_MODULATE 1 -#define TGSI_DST_REGISTER_EXT_TYPE_PREDICATE 2 struct tgsi_dst_register_ext { @@ -560,30 +519,12 @@ struct tgsi_dst_register_ext /** * Extra destination register modifiers * - * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_CONDCODE, - * it should be cast to tgsi_dst_register_ext_condcode. - * * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_MODULATE, * it should be cast to tgsi_dst_register_ext_modulate. * - * If tgsi_dst_register_ext::Type is TGSI_DST_REGISTER_EXT_TYPE_PREDICATE, - * it should be cast to tgsi_dst_register_ext_predicate. - * * If tgsi_dst_register_ext::Extended is TRUE, another tgsi_dst_register_ext * follows. */ -struct tgsi_dst_register_ext_concode -{ - unsigned Type : 4; /* TGSI_DST_REGISTER_EXT_TYPE_CONDCODE */ - unsigned CondMask : 4; /* TGSI_CC_ */ - unsigned CondSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned CondSrcIndex : 4; /* UINT */ - unsigned Padding : 11; - unsigned Extended : 1; /* BOOL */ -}; #define TGSI_MODULATE_1X 0 #define TGSI_MODULATE_2X 1 @@ -602,30 +543,8 @@ struct tgsi_dst_register_ext_modulate unsigned Extended : 1; /* BOOL */ }; -/* - * Currently, the following constraints apply. - * - * - PredSwizzleXYZW is either set to identity or replicate. - * - PredSrcIndex is 0. - */ - -struct tgsi_dst_register_ext_predicate -{ - unsigned Type : 4; /* TGSI_DST_REGISTER_EXT_TYPE_PREDICATE */ - unsigned PredSwizzleX : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleY : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleZ : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSwizzleW : 2; /* TGSI_SWIZZLE_ */ - unsigned PredSrcIndex : 4; /* UINT */ - unsigned Negate : 1; /* BOOL */ - unsigned Padding : 14; - unsigned Extended : 1; /* BOOL */ -}; - - #ifdef __cplusplus } #endif -#endif /* TGSI_TOKEN_H */ - +#endif /* P_SHADER_TOKENS_H */ -- 1.6.4.msysgit.0 ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Keith Whitwell-3
::
Rate this Message:
OK, looks good Michal. Go ahead and apply when you're ready.
Keith ________________________________________ From: michal [michal@...] Sent: Saturday, October 31, 2009 2:12 AM To: Keith Whitwell Cc: mesa3d-dev Subject: Re: [Mesa3d-dev] [PATCH] gallium: Add a PREDICATE register file. michal pisze: > Keith Whitwell pisze: > >> On Fri, 2009-10-30 at 11:24 -0700, michal wrote: >> >> >>> +/* >>> + * Currently, the following constraints apply. >>> + * >>> + * - PredSwizzleXYZW is either set to identity or replicate. >>> + * - PredSrcIndex is 0. >>> + */ >>> >>> >> Michal, >> >> This is looking a lot better. In terms of the above comment, is this >> talking about the semantics of PIPE_CAP_GPU3 ? Or is GPU3 supposed to >> do full PredSwizzle/PredSrcIndex, just we haven't implemented it >> somewhere (eg in tgsi_exec.c)? >> >> I'd think we want to either: >> - remove fields from the token so that the comment isn't necessary, >> - remove the comment and have GPU3 mean that the full semantics are >> available >> - come up with yet another cap bit to say whether or not full predicate >> semantics are implemented by a particular driver. >> >> Needless to say I don't like the last option, so I guess that means we >> need to decide now whether the full semantics in the token are in or >> out. >> >> How does SM3 fall on these issues? >> >> >> >> > The SM3 specification explicitly states that the predicate swizzle needs > to be either .xyzw or component replicate. The GL_MESA_gpu_program3 spec > allows arbitrary swizzles (there's nothing in the document that would > say otherwise). > > I say, rename PIPE_CAP_GPU3 to PIPE_CAP_SM3 to indicate predicates are > supported with the mentioned swizzle constraints. When the dust settles > on gpu_program3 spec, the state tracker will compensate for the lack of > arbitrary swizzles if needed. > > Also, add PIPE_CAP_MAX_PREDICATES to query the number of predicate > registers supported by the driver. That will allow us to remove the > `PredSrcIndex is 0' constraint. > > ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
|
|
Re: [PATCH] gallium: Add a PREDICATE register file.
by Ian Romanick-4
::
Rate this Message:
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1 michal wrote: > Keith Whitwell pisze: >> On Fri, 2009-10-30 at 11:24 -0700, michal wrote: >> >>> +/* >>> + * Currently, the following constraints apply. >>> + * >>> + * - PredSwizzleXYZW is either set to identity or replicate. >>> + * - PredSrcIndex is 0. >>> + */ >>> >> Michal, >> >> This is looking a lot better. In terms of the above comment, is this >> talking about the semantics of PIPE_CAP_GPU3 ? Or is GPU3 supposed to >> do full PredSwizzle/PredSrcIndex, just we haven't implemented it >> somewhere (eg in tgsi_exec.c)? >> >> I'd think we want to either: >> - remove fields from the token so that the comment isn't necessary, >> - remove the comment and have GPU3 mean that the full semantics are >> available >> - come up with yet another cap bit to say whether or not full predicate >> semantics are implemented by a particular driver. >> >> Needless to say I don't like the last option, so I guess that means we >> need to decide now whether the full semantics in the token are in or >> out. >> >> How does SM3 fall on these issues? >> > The SM3 specification explicitly states that the predicate swizzle needs > to be either .xyzw or component replicate. The GL_MESA_gpu_program3 spec > allows arbitrary swizzles (there's nothing in the document that would > say otherwise). This is one of the areas still open for discussion. Nicolai was looking into whether R500 could do the arbitrary swizzles without too much work. If R500 can't handle it, then I'll add the restriction to the spec. > I say, rename PIPE_CAP_GPU3 to PIPE_CAP_SM3 to indicate predicates are > supported with the mentioned swizzle constraints. When the dust settles > on gpu_program3 spec, the state tracker will compensate for the lack of > arbitrary swizzles if needed. > > Also, add PIPE_CAP_MAX_PREDICATES to query the number of predicate > registers supported by the driver. That will allow us to remove the > `PredSrcIndex is 0' constraint. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAkrs4L4ACgkQX1gOwKyEAw/3iwCfcqECydkzG9yQtVnahtJI0zh6 RmMAn0nR1WCcW0vI2zdj7/scUglmhoP+ =jHxh -----END PGP SIGNATURE----- ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@... https://lists.sourceforge.net/lists/listinfo/mesa3d-dev |
| Free embeddable forum powered by Nabble | Forum Help |
