TXQ : Texture Query

SPA 5.0:
        {@{!}Pg}   TXQ{.B}{.NODEP}{.phase}   Rd, Ra, #query, #tsPtrIdxU13 {, #wmskU04}    {&req_6}   {&rdN}   {&wrN}   {?sched}   ;   
        {@{!}Pg}   TXQ{.B}{.NODEP}{.phase}   Rd, Ra, #query, #tidU08, #smpU05, #wmskU04   {&req_6}   {&rdN}   {&wrN}   {?sched}   ;   

  .B:      Bindless mode, where the texture header pointer and sampler pointer is packed into a 32 bit register as:
           samplerPtr[31:20] | headerPtr[19:0]
           Data is sent via register Ra.

  .NODEP:  Indicates that there is no subsequent quad derivatives to be calculated.
           Threads that have been "killed" will be disabled to stop unnecessary texture fetches.

  .phase:  Allows control on the current warps texture hash, used for scheduling.
               < NONE >
               .T - postfix increment of the 3 bit texture component of the hash.
               .P - postfix increment of the 5 bit phase component, and zero out the 3 bit texture component of the hash. 


The following 3 queries are supported as part of SPA 3.0:
  - TEX_HEADER_DIMENSION
      Input is one coordinate containing a u32 LOD level
      Output is:

    
TXQ return value table

    
 Texture Type    
    
 R      
    
 G      
    
  B         
    
 A        


    
 ONE_D           
    
 width  
    
 zero   
    
 zero       
    
 # of mip-map Levels 


    
 TWO_D           
    
 width  
    
 height 
    
 zero/one*  
    
 # of mip-map Levels 


    
 THREE_D         
    
 width  
    
 height 
    
 depth      
    
 # of mip-map Levels 


    
 CUBEMAP         
    
 width  
    
 height 
    
 zero       
    
 # of mip-map Levels 


    
 ONE_D_ARRAY     
    
 width  
    
 length 
    
 zero       
    
 # of mip-map Levels 


    
 TWO_D_ARRAY     
    
 width  
    
 height 
    
 length     
    
 # of mip-map Levels 


    
 ONE_D_BUFFER    
    
 width  
    
 zero 
    
 zero   
    
 one  


    
 TWO_D_NO_MIPMAP 
    
 width  
    
 height 
    
 zero/depth* 
    
 one     


    
 CUBEMAP_ARRAY   
    
 width  
    
 height 
    
 length      
    
 # of mip-map Levels 



    *zero is for MODE_1X1 case, otherwise the other value is returned.  

  - TEX_HEADER_TEXTURE_TYPE
      No input data register required.
      Output is:
        (R) u32: 0            // reserved for "type", an 8 bit field set by SW in the texture header
        (G) u32: 0            // reserved for "format"
        (B) u32: ms count
        (A) u32: 0            // unused
  - TEX_HEADER_SAMPLER_POS
      Input is one coordinate containing the sample index within multisample pattern
      Output is:
        (R) u32: sample_position    //{4.12,4.12} format
        (G) u32: 0
        (B) u32: 0
        (A) u32: 0
      The format for sample_position is a packed dx/dy which is also shared
      with IPA and PIXLD.  The format is documented on the IPA ISA page.

  #tsPtrIdxU13:
           This immediate index (word address) is a used to fetch the packed header+sampler pointer entry from constant cache.
           The bank from which it is fetched is determined by bundle state. The constant bank entry is 32 bit
           structure of the form "samplerPtr[31:20] | headerPtr[19:0]".
           Note: Ignored if .B option is used.
           In SetSamplerBinding.ViaHeaderBinding (i.e. OGL) mode, the headerPtr  would be used as the samplerPtr
           as well. 
           Any header pointer greater than one specified in SetTexHeaderPoolC.MaximumIndex will be regarded as
           an "invalid" texture (i.e. equivalent to BIND_GROUP_TEXTURE_HEADER_VALID_FALSE in fermi).
           Any sampler pointer greater than one specified in SetSamplerHeaderPoolC.MaximumIndex will be regarded
           as an "invalid" texture (i.e. equivalent to BIND_GROUP_TEXTURE_HEADER_VALID_FALSE in fermi).
  
  #tidU08, #smpU05:
           This is the "almost" Fermi-compatible specification of tsPtrIdxU13 which allows running of legacy
           apps/traces where sass will transform these into tsPtrIdxU13 as follows:
           #tsPtrIdxU13 = {#smpU05, #tidU08}

  #wmskU04       destination write mask (decimated contiguous writes)
     Allows for write masking the returning data writes via a bit enable
     for each of R,G,B,A. A four-vector is always returned from TEX.
     #wmskU04 defaults to 0xf.