r600g: Implement GL_ARB_texture_gather

Only supported on evergreen and later. Currently limited
to single component textures as the hardware GATHER4
instruction ignores texture swizzles.

Piglit quick run passes on radeon 6670 with all
applicable textureGather tests, no regressions.

Signed-off-by: Glenn Kennard <glenn.kennard@gmail.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>

4 files changed, 44 insertions, 9 deletions

diff --git a/docs/GL3.txt b/docs/GL3.txt
index 92694cd215e..924f47990a6 100644
--- a/docs/GL3.txt
+++ b/docs/GL3.txt
@@ -118,7 +118,7 @@ GL 4.0:
   GL_ARB_tessellation_shader                           started (Fabian)
   GL_ARB_texture_buffer_object_rgb32                   DONE (i965, nvc0, r600, radeonsi, softpipe)
   GL_ARB_texture_cube_map_array                        DONE (i965, nv50, nvc0, r600, radeonsi, softpipe)
-  GL_ARB_texture_gather                                DONE (i965, nv50, nvc0, radeonsi)
+  GL_ARB_texture_gather                                DONE (i965, nv50, nvc0, radeonsi, r600)
   GL_ARB_texture_query_lod                             DONE (i965, nv50, nvc0, radeonsi)
   GL_ARB_transform_feedback2                           DONE (i965, nv50, nvc0, r600, radeonsi)
   GL_ARB_transform_feedback3                           DONE (i965, nv50, nvc0, r600, radeonsi)
diff --git a/docs/relnotes/10.3.html b/docs/relnotes/10.3.html
index 7d4f53318b7..b757e5f0175 100644
--- a/docs/relnotes/10.3.html
+++ b/docs/relnotes/10.3.html
@@ -49,7 +49,7 @@ Note: some of the new features are only available with certain drivers.
 <li>GL_ARB_sample_shading on radeonsi</li>
 <li>GL_ARB_stencil_texturing on nv50, nvc0, r600, and radeonsi</li>
 <li>GL_ARB_texture_cube_map_array on radeonsi</li>
-<li>GL_ARB_texture_gather on radeonsi</li>
+<li>GL_ARB_texture_gather on radeonsi, r600</li>
 <li>GL_ARB_texture_query_levels on nv50, nvc0, llvmpipe, r600, radeonsi, softpipe</li>
 <li>GL_ARB_texture_query_lod on radeonsi</li>
 <li>GL_ARB_viewport_array on nvc0</li>
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index ca6399fa20e..5bf9c00479b 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -303,6 +303,7 @@ static int r600_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
 	case PIPE_CAP_SEAMLESS_CUBE_MAP_PER_TEXTURE:
 	case PIPE_CAP_CUBE_MAP_ARRAY:
 	case PIPE_CAP_TGSI_VS_LAYER_VIEWPORT:
+	case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
 		return family >= CHIP_CEDAR ? 1 : 0;
 
 	/* Unsupported features. */
@@ -312,7 +313,6 @@ 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:
 	case PIPE_CAP_TEXTURE_QUERY_LOD:
 	case PIPE_CAP_SAMPLE_SHADING:
diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index 6952e3c8226..db928f3ae38 100644
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -4477,7 +4477,8 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 
 	if (inst->Instruction.Opcode == TGSI_OPCODE_TEX2 ||
 	    inst->Instruction.Opcode == TGSI_OPCODE_TXB2 ||
-	    inst->Instruction.Opcode == TGSI_OPCODE_TXL2)
+	    inst->Instruction.Opcode == TGSI_OPCODE_TXL2 ||
+	    inst->Instruction.Opcode == TGSI_OPCODE_TG4)
 		sampler_src_reg = 2;
 
 	src_gpr = tgsi_tex_get_src_gpr(ctx, 0);
@@ -5079,6 +5080,13 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 		case FETCH_OP_SAMPLE_G:
 			opcode = FETCH_OP_SAMPLE_C_G;
 			break;
+		/* Texture gather variants */
+		case FETCH_OP_GATHER4:
+			tex.op = FETCH_OP_GATHER4_C;
+			break;
+		case FETCH_OP_GATHER4_O:
+			tex.op = FETCH_OP_GATHER4_C_O;
+			break;
 		}
 	}
 
@@ -5089,9 +5097,21 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 	tex.resource_id = tex.sampler_id + R600_MAX_CONST_BUFFERS;
 	tex.src_gpr = src_gpr;
 	tex.dst_gpr = ctx->file_offset[inst->Dst[0].Register.File] + inst->Dst[0].Register.Index;
-	tex.dst_sel_x = (inst->Dst[0].Register.WriteMask & 1) ? 0 : 7;
-	tex.dst_sel_y = (inst->Dst[0].Register.WriteMask & 2) ? 1 : 7;
-	tex.dst_sel_z = (inst->Dst[0].Register.WriteMask & 4) ? 2 : 7;
+
+	if (inst->Instruction.Opcode == TGSI_OPCODE_TG4) {
+		int8_t texture_component_select = ctx->literals[4 * inst->Src[1].Register.Index + inst->Src[1].Register.SwizzleX];
+		tex.inst_mod = texture_component_select;
+
+		/* GATHER4 result order is different from TGSI TG4 */
+		tex.dst_sel_x = (inst->Dst[0].Register.WriteMask & 2) ? 1 : 7;
+		tex.dst_sel_y = (inst->Dst[0].Register.WriteMask & 4) ? 2 : 7;
+		tex.dst_sel_z = (inst->Dst[0].Register.WriteMask & 1) ? 0 : 7;
+	}
+	else {
+		tex.dst_sel_x = (inst->Dst[0].Register.WriteMask & 1) ? 0 : 7;
+		tex.dst_sel_y = (inst->Dst[0].Register.WriteMask & 2) ? 1 : 7;
+		tex.dst_sel_z = (inst->Dst[0].Register.WriteMask & 4) ? 2 : 7;
+	}
 	tex.dst_sel_w = (inst->Dst[0].Register.WriteMask & 8) ? 3 : 7;
 
 	if (inst->Instruction.Opcode == TGSI_OPCODE_TXQ_LZ) {
@@ -5132,7 +5152,13 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 
 	tex.offset_x = offset_x;
 	tex.offset_y = offset_y;
-	tex.offset_z = offset_z;
+	if (inst->Instruction.Opcode == TGSI_OPCODE_TG4 &&
+		inst->Texture.Texture == TGSI_TEXTURE_2D_ARRAY) {
+		tex.offset_z = 0;
+	}
+	else {
+		tex.offset_z = offset_z;
+	}
 
 	/* Put the depth for comparison in W.
 	 * TGSI_TEXTURE_SHADOW2D_ARRAY already has the depth in W.
@@ -5166,7 +5192,7 @@ static int tgsi_tex(struct r600_shader_ctx *ctx)
 		tex.coord_type_z = 0;
 
 	/* mask unused source components */
-	if (opcode == FETCH_OP_SAMPLE) {
+	if (opcode == FETCH_OP_SAMPLE || opcode == FETCH_OP_GATHER4) {
 		switch (inst->Texture.Texture) {
 		case TGSI_TEXTURE_2D:
 		case TGSI_TEXTURE_RECT:
@@ -6640,6 +6666,9 @@ static struct r600_shader_tgsi_instruction r600_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_TEX2,	0, FETCH_OP_SAMPLE, tgsi_tex},
 	{TGSI_OPCODE_TXB2,	0, FETCH_OP_SAMPLE_LB, tgsi_tex},
 	{TGSI_OPCODE_TXL2,	0, FETCH_OP_SAMPLE_L, tgsi_tex},
+	{TGSI_OPCODE_IMUL_HI, 0, ALU_OP0_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_UMUL_HI, 0, ALU_OP0_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_TG4,   0, FETCH_OP_GATHER4, tgsi_unsupported},
 	{TGSI_OPCODE_LAST,	0, ALU_OP0_NOP, tgsi_unsupported},
 };
 
@@ -6832,6 +6861,9 @@ static struct r600_shader_tgsi_instruction eg_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_TEX2,	0, FETCH_OP_SAMPLE, tgsi_tex},
 	{TGSI_OPCODE_TXB2,	0, FETCH_OP_SAMPLE_LB, tgsi_tex},
 	{TGSI_OPCODE_TXL2,	0, FETCH_OP_SAMPLE_L, tgsi_tex},
+	{TGSI_OPCODE_IMUL_HI, 0, ALU_OP0_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_UMUL_HI, 0, ALU_OP0_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_TG4,   0, FETCH_OP_GATHER4, tgsi_tex},
 	{TGSI_OPCODE_LAST,	0, ALU_OP0_NOP, tgsi_unsupported},
 };
 
@@ -7025,5 +7057,8 @@ static struct r600_shader_tgsi_instruction cm_shader_tgsi_instruction[] = {
 	{TGSI_OPCODE_TEX2,	0, FETCH_OP_SAMPLE, tgsi_tex},
 	{TGSI_OPCODE_TXB2,	0, FETCH_OP_SAMPLE_LB, tgsi_tex},
 	{TGSI_OPCODE_TXL2,	0, FETCH_OP_SAMPLE_L, tgsi_tex},
+	{TGSI_OPCODE_IMUL_HI, 0, ALU_OP0_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_UMUL_HI, 0, ALU_OP0_NOP, tgsi_unsupported},
+	{TGSI_OPCODE_TG4,   0, FETCH_OP_GATHER4, tgsi_tex},
 	{TGSI_OPCODE_LAST,	0, ALU_OP0_NOP, tgsi_unsupported},
 };