radv/gfx10: Add pipeline state support for tess.

Reviewed-by: Dave Airlie <airlied@redhat.com>
This commit is contained in:
Bas Nieuwenhuizen
2019-07-08 23:44:32 +02:00
committed by Dave Airlie
parent 23c6698ea2
commit 795adbbadd
2 changed files with 45 additions and 10 deletions

View File

@@ -2254,7 +2254,11 @@ radv_fill_shader_keys(struct radv_device *device,
}
if (device->physical_device->rad_info.chip_class >= GFX10) {
keys[MESA_SHADER_VERTEX].vs.out.as_ngg = true;
if (nir[MESA_SHADER_TESS_CTRL]) {
keys[MESA_SHADER_TESS_EVAL].tes.out.as_ngg = true;
} else {
keys[MESA_SHADER_VERTEX].vs.out.as_ngg = true;
}
}
for(int i = 0; i < MESA_SHADER_STAGES; ++i)
@@ -2623,6 +2627,8 @@ radv_pipeline_stage_to_user_data_0(struct radv_pipeline *pipeline,
if (has_gs) {
return chip_class >= GFX10 ? R_00B230_SPI_SHADER_USER_DATA_GS_0 :
R_00B330_SPI_SHADER_USER_DATA_ES_0;
} else if (has_ngg) {
return R_00B230_SPI_SHADER_USER_DATA_GS_0;
} else {
return R_00B130_SPI_SHADER_USER_DATA_VS_0;
}
@@ -3210,6 +3216,8 @@ radv_pipeline_generate_vgt_gs_mode(struct radeon_cmdbuf *ctx_cs,
pipeline->device->physical_device->rad_info.chip_class);
} else if (radv_pipeline_has_ngg(pipeline)) {
const struct radv_shader_variant *vs =
pipeline->shaders[MESA_SHADER_TESS_EVAL] ?
pipeline->shaders[MESA_SHADER_TESS_EVAL] :
pipeline->shaders[MESA_SHADER_VERTEX];
bool enable_prim_id =
outinfo->export_prim_id || vs->info.info.uses_prim_id;
@@ -3489,7 +3497,8 @@ static void
radv_pipeline_generate_tess_shaders(struct radeon_cmdbuf *ctx_cs,
struct radeon_cmdbuf *cs,
struct radv_pipeline *pipeline,
const struct radv_tessellation_state *tess)
const struct radv_tessellation_state *tess,
const struct radv_ngg_state *ngg)
{
if (!radv_pipeline_has_tess(pipeline))
return;
@@ -3500,7 +3509,9 @@ radv_pipeline_generate_tess_shaders(struct radeon_cmdbuf *ctx_cs,
tes = pipeline->shaders[MESA_SHADER_TESS_EVAL];
if (tes) {
if (tes->info.tes.as_es)
if (tes->info.is_ngg) {
radv_pipeline_generate_hw_ngg(ctx_cs, cs, pipeline, tes, ngg);
} else if (tes->info.tes.as_es)
radv_pipeline_generate_hw_es(cs, pipeline, tes);
else
radv_pipeline_generate_hw_vs(ctx_cs, cs, pipeline, tes);
@@ -3919,7 +3930,7 @@ radv_pipeline_generate_pm4(struct radv_pipeline *pipeline,
radv_pipeline_generate_multisample_state(ctx_cs, pipeline);
radv_pipeline_generate_vgt_gs_mode(ctx_cs, pipeline);
radv_pipeline_generate_vertex_shader(ctx_cs, cs, pipeline, tess, ngg);
radv_pipeline_generate_tess_shaders(ctx_cs, cs, pipeline, tess);
radv_pipeline_generate_tess_shaders(ctx_cs, cs, pipeline, tess, ngg);
radv_pipeline_generate_geometry_shader(ctx_cs, cs, pipeline, gs);
radv_pipeline_generate_fragment_shader(ctx_cs, cs, pipeline);
radv_pipeline_generate_ps_inputs(ctx_cs, pipeline);

View File

@@ -710,16 +710,21 @@ static void radv_postprocess_config(const struct radv_physical_device *pdevice,
switch (stage) {
case MESA_SHADER_TESS_EVAL:
if (info->tes.as_es) {
if (info->is_ngg) {
config_out->rsrc1 |= S_00B228_MEM_ORDERED(pdevice->rad_info.chip_class >= GFX10);
config_out->rsrc2 |= S_00B22C_OC_LDS_EN(1);
} else if (info->tes.as_es) {
assert(pdevice->rad_info.chip_class <= GFX8);
vgpr_comp_cnt = info->info.uses_prim_id ? 3 : 2;
config_out->rsrc2 |= S_00B12C_OC_LDS_EN(1);
} else {
bool enable_prim_id = info->tes.export_prim_id || info->info.uses_prim_id;
vgpr_comp_cnt = enable_prim_id ? 3 : 2;
config_out->rsrc1 |= S_00B128_MEM_ORDERED(pdevice->rad_info.chip_class >= GFX10);
config_out->rsrc2 |= S_00B12C_OC_LDS_EN(1);
}
config_out->rsrc2 |= S_00B12C_OC_LDS_EN(1);
break;
case MESA_SHADER_TESS_CTRL:
if (pdevice->rad_info.chip_class >= GFX9) {
@@ -727,7 +732,11 @@ static void radv_postprocess_config(const struct radv_physical_device *pdevice,
* VGPR0-3: (VertexID, RelAutoindex, InstanceID / StepRate0, InstanceID).
* StepRate0 is set to 1. so that VGPR3 doesn't have to be loaded.
*/
vgpr_comp_cnt = info->info.vs.needs_instance_id ? 2 : 1;
if (pdevice->rad_info.chip_class >= GFX10) {
vgpr_comp_cnt = info->info.vs.needs_instance_id ? 3 : 1;
} else {
vgpr_comp_cnt = info->info.vs.needs_instance_id ? 2 : 1;
}
} else {
config_out->rsrc2 |= S_00B12C_OC_LDS_EN(1);
}
@@ -786,12 +795,27 @@ static void radv_postprocess_config(const struct radv_physical_device *pdevice,
}
if (pdevice->rad_info.chip_class >= GFX10 &&
stage == MESA_SHADER_VERTEX) {
(stage == MESA_SHADER_VERTEX || stage == MESA_SHADER_TESS_EVAL)) {
unsigned gs_vgpr_comp_cnt, es_vgpr_comp_cnt;
/* VGPR5-8: (VertexID, UserVGPR0, UserVGPR1, UserVGPR2 / InstanceID) */
es_vgpr_comp_cnt = info->info.vs.needs_instance_id ? 3 : 0;
gs_vgpr_comp_cnt = 3;
if (stage == MESA_SHADER_VERTEX) {
es_vgpr_comp_cnt = info->info.vs.needs_instance_id ? 3 : 0;
} else if (stage == MESA_SHADER_TESS_EVAL) {
es_vgpr_comp_cnt = info->info.vs.needs_instance_id ? 3 : 2;
}
bool tes_triangles = stage == MESA_SHADER_TESS_EVAL &&
info->tes.primitive_mode >= 4; /* GL_TRIANGLES */
if (info->info.uses_invocation_id || stage == MESA_SHADER_VERTEX) {
gs_vgpr_comp_cnt = 3; /* VGPR3 contains InvocationID. */
} else if (info->info.uses_prim_id) {
gs_vgpr_comp_cnt = 2; /* VGPR2 contains PrimitiveID. */
} else if (info->gs.vertices_in >= 3 || tes_triangles) {
gs_vgpr_comp_cnt = 1; /* VGPR1 contains offsets 2, 3 */
} else {
gs_vgpr_comp_cnt = 0; /* VGPR0 contains offsets 0, 1 */
}
config_out->rsrc1 |= S_00B228_GS_VGPR_COMP_CNT(gs_vgpr_comp_cnt);
config_out->rsrc2 |= S_00B22C_ES_VGPR_COMP_CNT(es_vgpr_comp_cnt) |