r600g: initial VS output layer support

This just adds support for emitting the proper value in the VS out misc.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/src/gallium/drivers/r600/evergreen_state.c b/src/gallium/drivers/r600/evergreen_state.c
index e23f434e671fd19dc80ac5eaba4ff4cf1594eb95..c784f2fe20d87f029633931a633b5bfa9dbd41ea 100644 (file)
--- a/src/gallium/drivers/r600/evergreen_state.c
+++ b/src/gallium/drivers/r600/evergreen_state.c
@@ -3726,7 +3726,8 @@ void evergreen_update_vs_state(struct pipe_context *ctx, struct r600_pipe_shader
                S_02881C_VS_OUT_CCDIST0_VEC_ENA((rshader->clip_dist_write & 0x0F) != 0) |
                S_02881C_VS_OUT_CCDIST1_VEC_ENA((rshader->clip_dist_write & 0xF0) != 0) |
                S_02881C_VS_OUT_MISC_VEC_ENA(rshader->vs_out_misc_write) |
-               S_02881C_USE_VTX_POINT_SIZE(rshader->vs_out_point_size);
+               S_02881C_USE_VTX_POINT_SIZE(rshader->vs_out_point_size) |
+               S_02881C_USE_VTX_RENDER_TARGET_INDX(rshader->vs_out_layer);
 }
 
 void *evergreen_create_resolve_blend(struct r600_context *rctx)

diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index 6c80f85f9e3f1dfe803144eb22f3bbbb8fa5ec2e..2d5b8253665d616993c3b40ea809f6562c08c9a2 100644 (file)
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -383,6 +383,7 @@ static int r600_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
        /* Supported on Evergreen. */
        case PIPE_CAP_SEAMLESS_CUBE_MAP_PER_TEXTURE:
        case PIPE_CAP_CUBE_MAP_ARRAY:
+       case PIPE_CAP_TGSI_VS_LAYER:
                return family >= CHIP_CEDAR ? 1 : 0;
 
        /* Unsupported features. */
@@ -392,7 +393,6 @@ 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_TGSI_VS_LAYER:
                return 0;
 
        /* Stream output. */

diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index a58955a81485d69888d320a4a1821daed081450a..0a9f55a94a08b7995aa4b872da85da4b88ff4f16 100644 (file)
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -487,6 +487,7 @@ static int r600_spi_sid(struct r600_shader_io * io)
         */
        if (name == TGSI_SEMANTIC_POSITION ||
                name == TGSI_SEMANTIC_PSIZE ||
+               name == TGSI_SEMANTIC_LAYER ||
                name == TGSI_SEMANTIC_FACE)
                index = 0;
        else {
@@ -618,6 +619,10 @@ static int tgsi_declaration(struct r600_shader_ctx *ctx)
                                ctx->shader->vs_out_misc_write = 1;
                                ctx->shader->vs_out_point_size = 1;
                                break;
+                       case TGSI_SEMANTIC_LAYER:
+                               ctx->shader->vs_out_misc_write = 1;
+                               ctx->shader->vs_out_layer = 1;
+                               break;
                        case TGSI_SEMANTIC_CLIPVERTEX:
                                ctx->clip_vertex_write = TRUE;
                                ctx->cv_output = i;
@@ -1157,7 +1162,7 @@ static int generate_gs_copy_shader(struct r600_context *rctx,
        struct r600_bytecode_output output;
        struct r600_bytecode_cf *cf_jump, *cf_pop,
                *last_exp_pos = NULL, *last_exp_param = NULL;
-       int i, next_pos = 60, next_param = 0;
+       int i, next_clip_pos = 62, next_param = 0;
 
        cshader = calloc(1, sizeof(struct r600_pipe_shader));
        if (!cshader)
@@ -1252,13 +1257,24 @@ static int generate_gs_copy_shader(struct r600_context *rctx,
                output.op = CF_OP_EXPORT;
                switch (out->name) {
                case TGSI_SEMANTIC_POSITION:
-                       output.array_base = next_pos++;
+                       output.array_base = 60;
                        output.type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
                        break;
 
                case TGSI_SEMANTIC_PSIZE:
-                       output.array_base = next_pos++;
+                       output.array_base = 61;
+                       output.type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
+                       output.swizzle_y = 7;
+                       output.swizzle_z = 7;
+                       output.swizzle_w = 7;
+                       break;
+               case TGSI_SEMANTIC_LAYER:
+                       output.array_base = 61;
                        output.type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
+                       output.swizzle_x = 7;
+                       output.swizzle_y = 7;
+                       output.swizzle_z = 0;
+                       output.swizzle_w = 7;
                        break;
                case TGSI_SEMANTIC_CLIPDIST:
                        /* spi_sid is 0 for clipdistance outputs that were generated
@@ -1269,7 +1285,7 @@ static int generate_gs_copy_shader(struct r600_context *rctx,
                                r600_bytecode_add_output(ctx.bc, &output);
                                last_exp_param = ctx.bc->cf_last;
                        }
-                       output.array_base = next_pos++;
+                       output.array_base = next_clip_pos++;
                        output.type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
                        break;
                case TGSI_SEMANTIC_FOG:
@@ -1299,7 +1315,7 @@ static int generate_gs_copy_shader(struct r600_context *rctx,
                output.burst_count = 1;
                output.type = 2;
                output.op = CF_OP_EXPORT;
-               output.array_base = next_pos++;
+               output.array_base = 60;
                output.type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
                r600_bytecode_add_output(ctx.bc, &output);
                last_exp_pos = ctx.bc->cf_last;
@@ -1430,12 +1446,13 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
        unsigned output_done, noutput;
        unsigned opcode;
        int i, j, k, r = 0;
-       int next_pos_base = 60, next_param_base = 0;
+       int next_param_base = 0, next_clip_base;
        int max_color_exports = MAX2(key.nr_cbufs, 1);
        /* Declarations used by llvm code */
        bool use_llvm = false;
        bool indirect_gprs;
        bool ring_outputs = false;
+       bool pos_emitted = false;
 
 #ifdef R600_USE_LLVM
        use_llvm = !(rscreen->b.debug_flags & DBG_NO_LLVM);
@@ -1863,7 +1880,9 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
                if (key.vs_as_es)
                        emit_gs_ring_writes(&ctx, FALSE);
        } else {
-               /* export output */
+               /* Export output */
+               next_clip_base = shader->vs_out_misc_write ? 62 : 61;
+
                for (i = 0, j = 0; i < noutput; i++, j++) {
                        memset(&output[j], 0, sizeof(struct r600_bytecode_output));
                        output[j].gpr = shader->output[i].gpr;
@@ -1879,20 +1898,35 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
                        case TGSI_PROCESSOR_VERTEX:
                                switch (shader->output[i].name) {
                                case TGSI_SEMANTIC_POSITION:
-                                       output[j].array_base = next_pos_base++;
+                                       output[j].array_base = 60;
                                        output[j].type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
+                                       pos_emitted = true;
                                        break;
 
                                case TGSI_SEMANTIC_PSIZE:
-                                       output[j].array_base = next_pos_base++;
+                                       output[j].array_base = 61;
+                                       output[j].swizzle_y = 7;
+                                       output[j].swizzle_z = 7;
+                                       output[j].swizzle_w = 7;
+                                       output[j].type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
+                                       pos_emitted = true;
+                                       break;
+                               case TGSI_SEMANTIC_LAYER:
+                                       output[j].array_base = 61;
+                                       output[j].swizzle_x = 7;
+                                       output[j].swizzle_y = 7;
+                                       output[j].swizzle_z = 0;
+                                       output[j].swizzle_w = 7;
                                        output[j].type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
+                                       pos_emitted = true;
                                        break;
                                case TGSI_SEMANTIC_CLIPVERTEX:
                                        j--;
                                        break;
                                case TGSI_SEMANTIC_CLIPDIST:
-                                       output[j].array_base = next_pos_base++;
+                                       output[j].array_base = next_clip_base++;
                                        output[j].type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
+                                       pos_emitted = true;
                                        /* spi_sid is 0 for clipdistance outputs that were generated
                                         * for clipvertex - we don't need to pass them to PS */
                                        if (shader->output[i].spi_sid) {
@@ -1970,7 +2004,7 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
                }
 
                /* add fake position export */
-               if (ctx.type == TGSI_PROCESSOR_VERTEX && next_pos_base == 60) {
+               if (ctx.type == TGSI_PROCESSOR_VERTEX && pos_emitted == false) {
                        memset(&output[j], 0, sizeof(struct r600_bytecode_output));
                        output[j].gpr = 0;
                        output[j].elem_size = 3;
@@ -1980,7 +2014,7 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
                        output[j].swizzle_w = 7;
                        output[j].burst_count = 1;
                        output[j].type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_POS;
-                       output[j].array_base = next_pos_base;
+                       output[j].array_base = 60;
                        output[j].op = CF_OP_EXPORT;
                        j++;
                }

diff --git a/src/gallium/drivers/r600/r600_shader.h b/src/gallium/drivers/r600/r600_shader.h
index d31c65f4bc865ed936ed02898925ce09af17e269..89602c7013f6f0425371b6296b53dd5b5a1added 100644 (file)
--- a/src/gallium/drivers/r600/r600_shader.h
+++ b/src/gallium/drivers/r600/r600_shader.h
@@ -62,6 +62,7 @@ struct r600_shader {
        /* flag is set if the shader writes VS_OUT_MISC_VEC (e.g. for PSIZE) */
        boolean                 vs_out_misc_write;
        boolean                 vs_out_point_size;
+       boolean                 vs_out_layer;
        boolean                 has_txq_cube_array_z_comp;
        boolean                 uses_tex_buffers;
        boolean                 gs_prim_id_input;