gallium: add texture gather support to gallium (v3)

This adds support to gallium for a TG4 instruction,
and two CAPs. The first CAP is required for GL_ARB_texture_gather.

The second CAP is required to expose GL_ARB_gpu_shader5.

However so far we haven't found any hardware that natively
exposes the textureGatherOffsets feature from GL, so just
lower it for now. If hardware appears for this we can add
another CAP to allow TG4 to take 4 offsets.

v2: add component selection src and a cap to say
hw can do it. (st can use to help control
GL_ARB_gpu_shader5/GLSL 4.00). Add docs.

v3: rename to SM5, add docs.

Reviewed-by: Roland Scheidegger <[email protected]>
Signed-off-by: Dave Airlie <[email protected]>

17 files changed, 73 insertions, 2 deletions

diff --git a/src/gallium/auxiliary/tgsi/tgsi_info.c b/src/gallium/auxiliary/tgsi/tgsi_info.c
index f9936001344..565f274a545 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_info.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_info.c
@@ -221,6 +221,7 @@ static const struct tgsi_opcode_info opcode_info[TGSI_OPCODE_LAST] =
    { 1, 3, 1, 0, 0, 0, OTHR, "TXL2", TGSI_OPCODE_TXL2 },
    { 1, 2, 0, 0, 0, 0, COMP, "IMUL_HI", TGSI_OPCODE_IMUL_HI },
    { 1, 2, 0, 0, 0, 0, COMP, "UMUL_HI", TGSI_OPCODE_UMUL_HI },
+   { 1, 3, 1, 0, 0, 0, OTHR, "TG4", TGSI_OPCODE_TG4 },
 };
 
 const struct tgsi_opcode_info *
diff --git a/src/gallium/docs/source/screen.rst b/src/gallium/docs/source/screen.rst
index bd553f44086..6b5a195765a 100644
--- a/src/gallium/docs/source/screen.rst
+++ b/src/gallium/docs/source/screen.rst
@@ -182,6 +182,12 @@ The integer capabilities:
   vertex components output by a single invocation of a geometry shader.
   This is the product of the number of attribute components per vertex and
   the number of output vertices.
+* ``PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS``: Max number of components
+  in format that texture gather can operate on. 1 == RED, ALPHA etc,
+  4 == All formats.
+* ``PIPE_CAP_TEXTURE_GATHER_SM5``: Whether the texture gather
+  hardware implements the SM5 features, component selection,
+  shadow comparison, and run-time offsets.
 
 
 .. _pipe_capf:
diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst
index be4257255b3..03c5df846f7 100644
--- a/src/gallium/docs/source/tgsi.rst
+++ b/src/gallium/docs/source/tgsi.rst
@@ -986,6 +986,42 @@ XXX doesn't look like most of the opcodes really belong here.
 
   dst.z = texture_depth(unit, lod)
 
+.. opcode:: TG4 - Texture Gather (as per ARB_texture_gather)
+               Gathers the four texels to be used in a bi-linear
+               filtering operation and packs them into a single register.
+               Only works with 2D, 2D array, cubemaps, and cubemaps arrays.
+               For 2D textures, only the addressing modes of the sampler and
+               the top level of any mip pyramid are used. Set W to zero.
+               It behaves like the TEX instruction, but a filtered
+               sample is not generated. The four samples that contribute
+               to filtering are placed into xyzw in clockwise order,
+               starting with the (u,v) texture coordinate delta at the
+               following locations (-, +), (+, +), (+, -), (-, -), where
+               the magnitude of the deltas are half a texel.
+
+               PIPE_CAP_TEXTURE_SM5 enhances this instruction to support
+               shadow per-sample depth compares, single component selection,
+               and a non-constant offset. It doesn't allow support for the
+               GL independent offset to get i0,j0. This would require another
+               CAP is hw can do it natively. For now we lower that before
+               TGSI.
+
+.. math::
+
+   coord = src0
+
+   component = src1
+
+   dst = texture_gather4 (unit, coord, component)
+
+(with SM5 - cube array shadow)
+
+   coord = src0
+   
+   compare = src1
+
+   dst = texture_gather (uint, coord, compare)
+
 
 Integer ISA
 ^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/src/gallium/drivers/freedreno/freedreno_screen.c b/src/gallium/drivers/freedreno/freedreno_screen.c
index e1b5daef39f..c53300f406f 100644
--- a/src/gallium/drivers/freedreno/freedreno_screen.c
+++ b/src/gallium/drivers/freedreno/freedreno_screen.c
@@ -203,6 +203,8 @@ fd_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
 	case PIPE_CAP_QUERY_PIPELINE_STATISTICS:
 	case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
         case PIPE_CAP_TGSI_VS_LAYER:
+	case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+	case PIPE_CAP_TEXTURE_GATHER_SM5:
 		return 0;
 
 	/* Stream output. */
diff --git a/src/gallium/drivers/i915/i915_screen.c b/src/gallium/drivers/i915/i915_screen.c
index 9f08f862888..c5d2888ea78 100644
--- a/src/gallium/drivers/i915/i915_screen.c
+++ b/src/gallium/drivers/i915/i915_screen.c
@@ -216,6 +216,8 @@ i915_get_param(struct pipe_screen *screen, enum pipe_cap cap)
    case PIPE_CAP_TEXTURE_BUFFER_OBJECTS:
    case PIPE_CAP_TGSI_TEXCOORD:
    case PIPE_CAP_PREFER_BLIT_BASED_TEXTURE_TRANSFER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
 
    case PIPE_CAP_MAX_DUAL_SOURCE_RENDER_TARGETS:
diff --git a/src/gallium/drivers/ilo/ilo_screen.c b/src/gallium/drivers/ilo/ilo_screen.c
index 9c363acb4f7..255166431ac 100644
--- a/src/gallium/drivers/ilo/ilo_screen.c
+++ b/src/gallium/drivers/ilo/ilo_screen.c
@@ -433,6 +433,8 @@ ilo_get_param(struct pipe_screen *screen, enum pipe_cap param)
    case PIPE_CAP_MIXED_FRAMEBUFFER_SIZES:
       return true;
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
 
    default:
diff --git a/src/gallium/drivers/llvmpipe/lp_screen.c b/src/gallium/drivers/llvmpipe/lp_screen.c
index 43142e7fb55..4ab19497ca1 100644
--- a/src/gallium/drivers/llvmpipe/lp_screen.c
+++ b/src/gallium/drivers/llvmpipe/lp_screen.c
@@ -235,6 +235,8 @@ llvmpipe_get_param(struct pipe_screen *screen, enum pipe_cap param)
    case PIPE_CAP_ENDIANNESS:
       return PIPE_ENDIAN_NATIVE;
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
    }
    /* should only get here on unhandled cases */
diff --git a/src/gallium/drivers/nouveau/nv30/nv30_screen.c b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
index 9854708b371..8862a5d5e61 100644
--- a/src/gallium/drivers/nouveau/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
@@ -128,6 +128,8 @@ nv30_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
    case PIPE_CAP_MAX_TEXTURE_BUFFER_SIZE:
    case PIPE_CAP_MIXED_FRAMEBUFFER_SIZES:
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
    case PIPE_CAP_VERTEX_BUFFER_OFFSET_4BYTE_ALIGNED_ONLY:
    case PIPE_CAP_VERTEX_BUFFER_STRIDE_4BYTE_ALIGNED_ONLY:
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_screen.c b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
index 781b39158b4..c683cf190b4 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
@@ -196,6 +196,8 @@ nv50_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
    case PIPE_CAP_ENDIANNESS:
       return PIPE_ENDIAN_LITTLE;
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
    case PIPE_CAP_MAX_VIEWPORTS:
       return NV50_MAX_VIEWPORTS;
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
index f04771de452..a07cacdfbf8 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
@@ -174,6 +174,8 @@ nvc0_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
    case PIPE_CAP_ENDIANNESS:
       return PIPE_ENDIAN_LITTLE;
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
    case PIPE_CAP_MAX_VIEWPORTS:
       return 1;
diff --git a/src/gallium/drivers/r300/r300_screen.c b/src/gallium/drivers/r300/r300_screen.c
index fcb01e80864..26d73e47ccd 100644
--- a/src/gallium/drivers/r300/r300_screen.c
+++ b/src/gallium/drivers/r300/r300_screen.c
@@ -166,6 +166,8 @@ static int r300_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
         case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
         case PIPE_CAP_MAX_TEXTURE_BUFFER_SIZE:
         case PIPE_CAP_TGSI_VS_LAYER:
+        case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+        case PIPE_CAP_TEXTURE_GATHER_SM5:
             return 0;
 
         /* SWTCL-only features. */
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index 0f75a53748f..630e21d3484 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -399,6 +399,8 @@ static int r600_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
 	case PIPE_CAP_FRAGMENT_COLOR_CLAMPED:
 	case PIPE_CAP_VERTEX_COLOR_CLAMPED:
 	case PIPE_CAP_USER_VERTEX_BUFFERS:
+	case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+	case PIPE_CAP_TEXTURE_GATHER_SM5:
 		return 0;
 
 	/* Stream output. */
diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index c64621bf223..c69be584c2f 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -285,6 +285,8 @@ static int si_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
 	case PIPE_CAP_QUADS_FOLLOW_PROVOKING_VERTEX_CONVENTION:
 	case PIPE_CAP_USER_VERTEX_BUFFERS:
 	case PIPE_CAP_CUBE_MAP_ARRAY:
+	case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+	case PIPE_CAP_TEXTURE_GATHER_SM5:
 		return 0;
 
 	case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
diff --git a/src/gallium/drivers/softpipe/sp_screen.c b/src/gallium/drivers/softpipe/sp_screen.c
index 46ac519db12..0eae9ed473c 100644
--- a/src/gallium/drivers/softpipe/sp_screen.c
+++ b/src/gallium/drivers/softpipe/sp_screen.c
@@ -185,6 +185,8 @@ softpipe_get_param(struct pipe_screen *screen, enum pipe_cap param)
    case PIPE_CAP_ENDIANNESS:
       return PIPE_ENDIAN_NATIVE;
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
    }
    /* should only get here on unhandled cases */
diff --git a/src/gallium/drivers/svga/svga_screen.c b/src/gallium/drivers/svga/svga_screen.c
index d5ae69a70d9..ae2623d09c9 100644
--- a/src/gallium/drivers/svga/svga_screen.c
+++ b/src/gallium/drivers/svga/svga_screen.c
@@ -266,6 +266,8 @@ svga_get_param(struct pipe_screen *screen, enum pipe_cap param)
    case PIPE_CAP_QUERY_PIPELINE_STATISTICS:
    case PIPE_CAP_MAX_TEXTURE_BUFFER_SIZE:
    case PIPE_CAP_TGSI_VS_LAYER:
+   case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
+   case PIPE_CAP_TEXTURE_GATHER_SM5:
       return 0;
    case PIPE_CAP_MIN_MAP_BUFFER_ALIGNMENT:
       return 64;
diff --git a/src/gallium/include/pipe/p_defines.h b/src/gallium/include/pipe/p_defines.h
index 83815cdf2da..764c2484f87 100644
--- a/src/gallium/include/pipe/p_defines.h
+++ b/src/gallium/include/pipe/p_defines.h
@@ -522,7 +522,9 @@ enum pipe_cap {
    PIPE_CAP_MIXED_FRAMEBUFFER_SIZES = 86,
    PIPE_CAP_TGSI_VS_LAYER = 87,
    PIPE_CAP_MAX_GEOMETRY_OUTPUT_VERTICES = 88,
-   PIPE_CAP_MAX_GEOMETRY_TOTAL_OUTPUT_COMPONENTS = 89
+   PIPE_CAP_MAX_GEOMETRY_TOTAL_OUTPUT_COMPONENTS = 89,
+   PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS = 90,
+   PIPE_CAP_TEXTURE_GATHER_SM5 = 91
 };
 
 #define PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_NV50 (1 << 0)
diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h
index 8750bd2da2e..8fa6a0afaeb 100644
--- a/src/gallium/include/pipe/p_shader_tokens.h
+++ b/src/gallium/include/pipe/p_shader_tokens.h
@@ -453,7 +453,9 @@ struct tgsi_property_data {
 #define TGSI_OPCODE_IMUL_HI             180
 #define TGSI_OPCODE_UMUL_HI             181
 
-#define TGSI_OPCODE_LAST                182
+#define TGSI_OPCODE_TG4                 182
+
+#define TGSI_OPCODE_LAST                183
 
 #define TGSI_SAT_NONE            0  /* do not saturate */
 #define TGSI_SAT_ZERO_ONE        1  /* clamp to [0,1] */