OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

r600g: Implement GL_ARB_sample_shading

Browse Source 
Also fixes two sided lighting which was broken at least
on pre-evergreen by commit b1eb00.

Signed-off-by: Glenn Kennard <glenn.kennard@gmail.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
This commit is contained in:
Glenn Kennard
2014-09-10 11:54:40 +02:00
committed by Marek Olšák
parent 75e97e2e3f
commit a327fa3a06
12 changed files with 385 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/GL3.txt
View File

@@ -110,7 +110,7 @@ GL 4.0, GLSL 4.00:
- Interpolation functions DONE ()
- New overload resolution rules DONE
GL_ARB_gpu_shader_fp64 started (Dave)
GL_ARB_sample_shading DONE (i965, nv50, nvc0, radeonsi)
GL_ARB_sample_shading DONE (i965, nv50, nvc0, r600, radeonsi)
GL_ARB_shader_subroutine not started
GL_ARB_tessellation_shader started (Chris, Ilia)
GL_ARB_texture_buffer_object_rgb32 DONE (i965, nvc0, r600, radeonsi, llvmpipe, softpipe)

1
docs/relnotes/10.4.html
View File

@@ -44,6 +44,7 @@ Note: some of the new features are only available with certain drivers.
</p>
<ul>
<li>GL_ARB_sample_shading on r600</li>
<li>GL_ARB_texture_view on nv50, nvc0</li>
</ul>

85
src/gallium/drivers/r600/evergreen_state.c
View File

@@ -1400,7 +1400,7 @@ static void evergreen_set_framebuffer_state(struct pipe_context *ctx,
/* MSAA. */
if (rctx->b.chip_class == EVERGREEN)
rctx->framebuffer.atom.num_dw += 14; /* Evergreen */
rctx->framebuffer.atom.num_dw += 17; /* Evergreen */
else
rctx->framebuffer.atom.num_dw += 28; /* Cayman */
@@ -1420,8 +1420,22 @@ static void evergreen_set_framebuffer_state(struct pipe_context *ctx,
}
rctx->framebuffer.atom.dirty = true;
r600_set_sample_locations_constant_buffer(rctx);
}
static void evergreen_set_min_samples(struct pipe_context *ctx, unsigned min_samples)
{
struct r600_context *rctx = (struct r600_context *)ctx;
if (rctx->ps_iter_samples == min_samples)
return;
rctx->ps_iter_samples = min_samples;
if (rctx->framebuffer.nr_samples > 1) {
rctx->framebuffer.atom.dirty = true;
}
}
/* 8xMSAA */
static uint32_t sample_locs_8x[] = {
@@ -1475,7 +1489,7 @@ static void evergreen_get_sample_position(struct pipe_context *ctx,
}
}
static void evergreen_emit_msaa_state(struct r600_context *rctx, int nr_samples)
static void evergreen_emit_msaa_state(struct r600_context *rctx, int nr_samples, int ps_iter_samples)
{
struct radeon_winsys_cs *cs = rctx->b.rings.gfx.cs;
@@ -1508,10 +1522,12 @@ static void evergreen_emit_msaa_state(struct r600_context *rctx, int nr_samples)
S_028C00_EXPAND_LINE_WIDTH(1)); /* R_028C00_PA_SC_LINE_CNTL */
radeon_emit(cs, S_028C04_MSAA_NUM_SAMPLES(util_logbase2(nr_samples)) |
S_028C04_MAX_SAMPLE_DIST(max_dist)); /* R_028C04_PA_SC_AA_CONFIG */
r600_write_context_reg(cs, EG_R_028A4C_PA_SC_MODE_CNTL_1, EG_S_028A4C_PS_ITER_SAMPLE(ps_iter_samples > 1));
} else {
r600_write_context_reg_seq(cs, R_028C00_PA_SC_LINE_CNTL, 2);
radeon_emit(cs, S_028C00_LAST_PIXEL(1)); /* R_028C00_PA_SC_LINE_CNTL */
radeon_emit(cs, 0); /* R_028C04_PA_SC_AA_CONFIG */
r600_write_context_reg(cs, EG_R_028A4C_PA_SC_MODE_CNTL_1, 0);
}
}
@@ -1672,10 +1688,10 @@ static void evergreen_emit_framebuffer_state(struct r600_context *rctx, struct r
radeon_emit(cs, br); /* R_028208_PA_SC_WINDOW_SCISSOR_BR */
if (rctx->b.chip_class == EVERGREEN) {
evergreen_emit_msaa_state(rctx, rctx->framebuffer.nr_samples);
evergreen_emit_msaa_state(rctx, rctx->framebuffer.nr_samples, rctx->ps_iter_samples);
} else {
cayman_emit_msaa_sample_locs(cs, rctx->framebuffer.nr_samples);
cayman_emit_msaa_config(cs, rctx->framebuffer.nr_samples, 1);
cayman_emit_msaa_config(cs, rctx->framebuffer.nr_samples, rctx->ps_iter_samples);
}
}
@@ -2432,8 +2448,6 @@ void evergreen_init_common_regs(struct r600_command_buffer *cb,
r600_store_value(cb, tmp); /* R_008C0C_SQ_GPR_RESOURCE_MGMT_3 */
}
r600_store_context_reg(cb, R_028A4C_PA_SC_MODE_CNTL_1, 0);
/* The cs checker requires this register to be set. */
r600_store_context_reg(cb, R_028800_DB_DEPTH_CONTROL, 0);
@@ -2786,11 +2800,19 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
struct r600_command_buffer *cb = &shader->command_buffer;
struct r600_shader *rshader = &shader->shader;
unsigned i, exports_ps, num_cout, spi_ps_in_control_0, spi_input_z, spi_ps_in_control_1, db_shader_control = 0;
int pos_index = -1, face_index = -1;
int pos_index = -1, face_index = -1, fixed_pt_position_index = -1;
int ninterp = 0;
boolean have_linear = FALSE, have_centroid = FALSE, have_perspective = FALSE;
unsigned spi_baryc_cntl, sid, tmp, num = 0;
unsigned z_export = 0, stencil_export = 0;
boolean have_perspective = FALSE, have_linear = FALSE;
static const unsigned spi_baryc_enable_bit[6] = {
S_0286E0_PERSP_SAMPLE_ENA(1),
S_0286E0_PERSP_CENTER_ENA(1),
S_0286E0_PERSP_CENTROID_ENA(1),
S_0286E0_LINEAR_SAMPLE_ENA(1),
S_0286E0_LINEAR_CENTER_ENA(1),
S_0286E0_LINEAR_CENTROID_ENA(1)
};
unsigned spi_baryc_cntl = 0, sid, tmp, num = 0;
unsigned z_export = 0, stencil_export = 0, mask_export = 0;
unsigned sprite_coord_enable = rctx->rasterizer ? rctx->rasterizer->sprite_coord_enable : 0;
uint32_t spi_ps_input_cntl[32];
@@ -2813,14 +2835,19 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
if (face_index == -1)
face_index = i; /* lives in same register, same enable bit */
}
else if (rshader->input[i].name == TGSI_SEMANTIC_SAMPLEID) {
fixed_pt_position_index = i;
}
else {
ninterp++;
if (rshader->input[i].interpolate == TGSI_INTERPOLATE_LINEAR)
have_linear = TRUE;
if (rshader->input[i].interpolate == TGSI_INTERPOLATE_PERSPECTIVE)
have_perspective = TRUE;
if (rshader->input[i].centroid)
have_centroid = TRUE;
int k = eg_get_interpolator_index(
rshader->input[i].interpolate,
rshader->input[i].interpolate_location);
if (k >= 0) {
spi_baryc_cntl |= spi_baryc_enable_bit[k];
have_perspective |= k < 3;
have_linear |= !(k < 3);
}
}
sid = rshader->input[i].spi_sid;
@@ -2852,17 +2879,22 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
z_export = 1;
if (rshader->output[i].name == TGSI_SEMANTIC_STENCIL)
stencil_export = 1;
if (rshader->output[i].name == TGSI_SEMANTIC_SAMPLEMASK &&
rctx->framebuffer.nr_samples > 1 && rctx->ps_iter_samples > 0)
mask_export = 1;
}
if (rshader->uses_kill)
db_shader_control |= S_02880C_KILL_ENABLE(1);
db_shader_control |= S_02880C_Z_EXPORT_ENABLE(z_export);
db_shader_control |= S_02880C_STENCIL_EXPORT_ENABLE(stencil_export);
db_shader_control |= S_02880C_MASK_EXPORT_ENABLE(mask_export);
exports_ps = 0;
for (i = 0; i < rshader->noutput; i++) {
if (rshader->output[i].name == TGSI_SEMANTIC_POSITION ||
rshader->output[i].name == TGSI_SEMANTIC_STENCIL)
rshader->output[i].name == TGSI_SEMANTIC_STENCIL ||
rshader->output[i].name == TGSI_SEMANTIC_SAMPLEMASK)
exports_ps |= 1;
}
@@ -2878,6 +2910,8 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
ninterp = 1;
have_perspective = TRUE;
}
if (!spi_baryc_cntl)
spi_baryc_cntl |= spi_baryc_enable_bit[0];
if (!have_perspective && !have_linear)
have_perspective = TRUE;
@@ -2888,7 +2922,7 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
spi_input_z = 0;
if (pos_index != -1) {
spi_ps_in_control_0 |= S_0286CC_POSITION_ENA(1) |
S_0286CC_POSITION_CENTROID(rshader->input[pos_index].centroid) |
S_0286CC_POSITION_CENTROID(rshader->input[pos_index].interpolate_location == TGSI_INTERPOLATE_LOC_CENTROID) |
S_0286CC_POSITION_ADDR(rshader->input[pos_index].gpr);
spi_input_z |= S_0286D8_PROVIDE_Z_TO_SPI(1);
}
@@ -2898,14 +2932,10 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
spi_ps_in_control_1 |= S_0286D0_FRONT_FACE_ENA(1) |
S_0286D0_FRONT_FACE_ADDR(rshader->input[face_index].gpr);
}
spi_baryc_cntl = 0;
if (have_perspective)
spi_baryc_cntl |= S_0286E0_PERSP_CENTER_ENA(1) |
S_0286E0_PERSP_CENTROID_ENA(have_centroid);
if (have_linear)
spi_baryc_cntl |= S_0286E0_LINEAR_CENTER_ENA(1) |
S_0286E0_LINEAR_CENTROID_ENA(have_centroid);
if (fixed_pt_position_index != -1) {
spi_ps_in_control_1 |= S_0286D0_FIXED_PT_POSITION_ENA(1) |
S_0286D0_FIXED_PT_POSITION_ADDR(rshader->input[fixed_pt_position_index].gpr);
}
r600_store_context_reg_seq(cb, R_0286CC_SPI_PS_IN_CONTROL_0, 2);
r600_store_value(cb, spi_ps_in_control_0); /* R_0286CC_SPI_PS_IN_CONTROL_0 */
@@ -2924,7 +2954,7 @@ void evergreen_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader
/* After that, the NOP relocation packet must be emitted (shader->bo, RADEON_USAGE_READ). */
shader->db_shader_control = db_shader_control;
shader->ps_depth_export = z_export | stencil_export;
shader->ps_depth_export = z_export | stencil_export | mask_export;
shader->sprite_coord_enable = sprite_coord_enable;
if (rctx->rasterizer)
@@ -3446,6 +3476,7 @@ void evergreen_init_state_functions(struct r600_context *rctx)
rctx->b.b.create_sampler_view = evergreen_create_sampler_view;
rctx->b.b.set_framebuffer_state = evergreen_set_framebuffer_state;
rctx->b.b.set_polygon_stipple = evergreen_set_polygon_stipple;
rctx->b.b.set_min_samples = evergreen_set_min_samples;
rctx->b.b.set_scissor_states = evergreen_set_scissor_states;
if (rctx->b.chip_class == EVERGREEN)

3
src/gallium/drivers/r600/evergreend.h
View File

@@ -803,6 +803,9 @@
#define S_02880C_KILL_ENABLE(x) (((x) & 0x1) << 6)
#define G_02880C_KILL_ENABLE(x) (((x) >> 6) & 0x1)
#define C_02880C_KILL_ENABLE 0xFFFFFFBF
#define S_02880C_MASK_EXPORT_ENABLE(x) (((x) & 0x1) << 8)
#define G_02880C_MASK_EXPORT_ENABLE(x) (((x) >> 8) & 0x1)
#define C_02880C_MASK_EXPORT_ENABLE 0XFFFFFEFF
#define S_02880C_DUAL_EXPORT_ENABLE(x) (((x) & 0x1) << 9)
#define G_02880C_DUAL_EXPORT_ENABLE(x) (((x) >> 9) & 0x1)
#define C_02880C_DUAL_EXPORT_ENABLE 0xFFFFFDFF

2
src/gallium/drivers/r600/r600_pipe.c
View File

@@ -265,6 +265,7 @@ static int r600_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
case PIPE_CAP_BUFFER_MAP_PERSISTENT_COHERENT:
case PIPE_CAP_TGSI_VS_WINDOW_SPACE_POSITION:
case PIPE_CAP_TGSI_VS_LAYER_VIEWPORT:
case PIPE_CAP_SAMPLE_SHADING:
return 1;
case PIPE_CAP_COMPUTE:
@@ -319,7 +320,6 @@ 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_SAMPLE_SHADING:
case PIPE_CAP_TEXTURE_GATHER_OFFSETS:
case PIPE_CAP_DRAW_INDIRECT:
case PIPE_CAP_CONDITIONAL_RENDER_INVERTED:

10
src/gallium/drivers/r600/r600_pipe.h
View File

@@ -52,6 +52,14 @@
#define R600_TXQ_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 1)
#define R600_BUFFER_INFO_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 2)
#define R600_GS_RING_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS + 3)
/* Currently R600_MAX_CONST_BUFFERS is too large, the hardware only has 16 buffers, but the driver is
* trying to use 17. Avoid accidentally aliasing with user UBOs for SAMPLE_POSITIONS by using an id<16.
* UCP/SAMPLE_POSITIONS are never accessed by same shader stage so they can use the same id.
*
* Fixing this properly would require the driver to combine its buffers into a single hardware buffer,
* which would also allow supporting the d3d 11 mandated minimum of 15 user const buffers.
*/
#define R600_SAMPLE_POSITIONS_CONST_BUFFER (R600_MAX_USER_CONST_BUFFERS)
#define R600_MAX_CONST_BUFFER_SIZE (4096 * sizeof(float[4]))
@@ -452,6 +460,7 @@ struct r600_context {
bool force_blend_disable;
boolean dual_src_blend;
unsigned zwritemask;
int ps_iter_samples;
/* Index buffer. */
struct pipe_index_buffer index_buffer;
@@ -639,6 +648,7 @@ void r600_sampler_views_dirty(struct r600_context *rctx,
void r600_sampler_states_dirty(struct r600_context *rctx,
struct r600_sampler_states *state);
void r600_constant_buffers_dirty(struct r600_context *rctx, struct r600_constbuf_state *state);
void r600_set_sample_locations_constant_buffer(struct r600_context *rctx);
uint32_t r600_translate_stencil_op(int s_op);
uint32_t r600_translate_fill(uint32_t func);
unsigned r600_tex_wrap(unsigned wrap);

292
src/gallium/drivers/r600/r600_shader.c
View File

@@ -64,6 +64,7 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
struct r600_pipe_shader *pipeshader,
struct r600_shader_key key);
static void r600_add_gpr_array(struct r600_shader *ps, int start_gpr,
int size, unsigned comp_mask) {
@@ -267,6 +268,11 @@ struct r600_shader_src {
uint32_t value[4];
};
struct eg_interp {
boolean enabled;
unsigned ij_index;
};
struct r600_shader_ctx {
struct tgsi_shader_info info;
struct tgsi_parse_context parse;
@@ -283,13 +289,11 @@ struct r600_shader_ctx {
uint32_t max_driver_temp_used;
boolean use_llvm;
/* needed for evergreen interpolation */
boolean input_centroid;
boolean input_linear;
boolean input_perspective;
int num_interp_gpr;
struct eg_interp eg_interpolators[6]; // indexed by Persp/Linear * 3 + sample/center/centroid
/* evergreen/cayman also store sample mask in face register */
int face_gpr;
boolean has_samplemask;
/* sample id is .w component stored in fixed point position register */
int fixed_pt_position_gpr;
int colors_used;
boolean clip_vertex_write;
unsigned cv_output;
@@ -320,6 +324,12 @@ static int tgsi_endif(struct r600_shader_ctx *ctx);
static int tgsi_bgnloop(struct r600_shader_ctx *ctx);
static int tgsi_endloop(struct r600_shader_ctx *ctx);
static int tgsi_loop_brk_cont(struct r600_shader_ctx *ctx);
static int tgsi_fetch_rel_const(struct r600_shader_ctx *ctx,
unsigned int cb_idx, unsigned int offset, unsigned ar_chan,
unsigned int dst_reg);
static void r600_bytecode_src(struct r600_bytecode_alu_src *bc_src,
const struct r600_shader_src *shader_src,
unsigned chan);
static int tgsi_is_supported(struct r600_shader_ctx *ctx)
{
@@ -364,27 +374,41 @@ static int tgsi_is_supported(struct r600_shader_ctx *ctx)
return 0;
}
int eg_get_interpolator_index(unsigned interpolate, unsigned location)
{
if (interpolate == TGSI_INTERPOLATE_COLOR ||
interpolate == TGSI_INTERPOLATE_LINEAR ||
interpolate == TGSI_INTERPOLATE_PERSPECTIVE)
{
int is_linear = interpolate == TGSI_INTERPOLATE_LINEAR;
int loc;
switch(location) {
case TGSI_INTERPOLATE_LOC_CENTER:
loc = 1;
break;
case TGSI_INTERPOLATE_LOC_CENTROID:
loc = 2;
break;
case TGSI_INTERPOLATE_LOC_SAMPLE:
default:
loc = 0; break;
}
return is_linear * 3 + loc;
}
return -1;
}
static void evergreen_interp_assign_ij_index(struct r600_shader_ctx *ctx,
int input)
{
int ij_index = 0;
if (ctx->shader->input[input].interpolate == TGSI_INTERPOLATE_PERSPECTIVE) {
if (ctx->shader->input[input].centroid)
ij_index++;
} else if (ctx->shader->input[input].interpolate == TGSI_INTERPOLATE_LINEAR) {
/* if we have perspective add one */
if (ctx->input_perspective) {
ij_index++;
/* if we have perspective centroid */
if (ctx->input_centroid)
ij_index++;
}
if (ctx->shader->input[input].centroid)
ij_index++;
}
ctx->shader->input[input].ij_index = ij_index;
int i = eg_get_interpolator_index(
ctx->shader->input[input].interpolate,
ctx->shader->input[input].interpolate_location);
assert(i >= 0);
ctx->shader->input[input].ij_index = ctx->eg_interpolators[i].ij_index;
}
static int evergreen_interp_alu(struct r600_shader_ctx *ctx, int input)
@@ -582,13 +606,15 @@ static int tgsi_declaration(struct r600_shader_ctx *ctx)
ctx->shader->input[i].name = d->Semantic.Name;
ctx->shader->input[i].sid = d->Semantic.Index;
ctx->shader->input[i].interpolate = d->Interp.Interpolate;
ctx->shader->input[i].centroid = d->Interp.Location == TGSI_INTERPOLATE_LOC_CENTROID;
ctx->shader->input[i].interpolate_location = d->Interp.Location;
ctx->shader->input[i].gpr = ctx->file_offset[TGSI_FILE_INPUT] + d->Range.First;
if (ctx->type == TGSI_PROCESSOR_FRAGMENT) {
ctx->shader->input[i].spi_sid = r600_spi_sid(&ctx->shader->input[i]);
switch (ctx->shader->input[i].name) {
case TGSI_SEMANTIC_FACE:
if (ctx->face_gpr == -1)
if (ctx->face_gpr != -1)
ctx->shader->input[i].gpr = ctx->face_gpr; /* already allocated by allocate_system_value_inputs */
else
ctx->face_gpr = ctx->shader->input[i].gpr;
break;
case TGSI_SEMANTIC_COLOR:
@@ -679,14 +705,11 @@ static int tgsi_declaration(struct r600_shader_ctx *ctx)
break;
case TGSI_FILE_SYSTEM_VALUE:
if (d->Semantic.Name == TGSI_SEMANTIC_SAMPLEMASK) {
ctx->has_samplemask = true;
/* lives in Front Face GPR */
if (ctx->face_gpr == -1)
ctx->face_gpr = ctx->file_offset[TGSI_FILE_SYSTEM_VALUE] + d->Range.First;
break;
}
else if (d->Semantic.Name == TGSI_SEMANTIC_INSTANCEID) {
if (d->Semantic.Name == TGSI_SEMANTIC_SAMPLEMASK ||
d->Semantic.Name == TGSI_SEMANTIC_SAMPLEID ||
d->Semantic.Name == TGSI_SEMANTIC_SAMPLEPOS) {
break; /* Already handled from allocate_system_value_inputs */
} else if (d->Semantic.Name == TGSI_SEMANTIC_INSTANCEID) {
if (!ctx->native_integers) {
struct r600_bytecode_alu alu;
memset(&alu, 0, sizeof(struct r600_bytecode_alu));
@@ -720,12 +743,69 @@ static int r600_get_temp(struct r600_shader_ctx *ctx)
return ctx->temp_reg + ctx->max_driver_temp_used++;
}
static int allocate_system_value_inputs(struct r600_shader_ctx *ctx, int gpr_offset)
{
struct tgsi_parse_context parse;
struct {
boolean enabled;
int *reg;
unsigned name, alternate_name;
} inputs[2] = {
{ false, &ctx->face_gpr, TGSI_SEMANTIC_SAMPLEMASK, ~0u }, /* lives in Front Face GPR.z */
{ false, &ctx->fixed_pt_position_gpr, TGSI_SEMANTIC_SAMPLEID, TGSI_SEMANTIC_SAMPLEPOS } /* SAMPLEID is in Fixed Point Position GPR.w */
};
int i, k, num_regs = 0;
if (tgsi_parse_init(&parse, ctx->tokens) != TGSI_PARSE_OK) {
return 0;
}
while (!tgsi_parse_end_of_tokens(&parse)) {
tgsi_parse_token(&parse);
if (parse.FullToken.Token.Type == TGSI_TOKEN_TYPE_DECLARATION) {
struct tgsi_full_declaration *d = &parse.FullToken.FullDeclaration;
if (d->Declaration.File == TGSI_FILE_SYSTEM_VALUE) {
for (k = 0; k < Elements(inputs); k++) {
if (d->Semantic.Name == inputs[k].name ||
d->Semantic.Name == inputs[k].alternate_name) {
inputs[k].enabled = true;
}
}
}
}
}
tgsi_parse_free(&parse);
for (i = 0; i < Elements(inputs); i++) {
boolean enabled = inputs[i].enabled;
int *reg = inputs[i].reg;
unsigned name = inputs[i].name;
if (enabled) {
int gpr = gpr_offset + num_regs++;
// add to inputs, allocate a gpr
k = ctx->shader->ninput ++;
ctx->shader->input[k].name = name;
ctx->shader->input[k].sid = 0;
ctx->shader->input[k].interpolate = TGSI_INTERPOLATE_CONSTANT;
ctx->shader->input[k].interpolate_location = TGSI_INTERPOLATE_LOC_CENTER;
*reg = ctx->shader->input[k].gpr = gpr;
}
}
return gpr_offset + num_regs;
}
/*
* for evergreen we need to scan the shader to find the number of GPRs we need to
* reserve for interpolation.
* reserve for interpolation and system values
*
* we need to know if we are going to emit
* any centroid inputs
* any sample or centroid inputs
* if perspective and linear are required
*/
static int evergreen_gpr_count(struct r600_shader_ctx *ctx)
@@ -733,39 +813,92 @@ static int evergreen_gpr_count(struct r600_shader_ctx *ctx)
int i;
int num_baryc;
ctx->input_linear = FALSE;
ctx->input_perspective = FALSE;
ctx->input_centroid = FALSE;
ctx->num_interp_gpr = 1;
memset(&ctx->eg_interpolators, 0, sizeof(ctx->eg_interpolators));
/* any centroid inputs */
for (i = 0; i < ctx->info.num_inputs; i++) {
/* skip position/face */
int k;
/* skip position/face/mask/sampleid */
if (ctx->info.input_semantic_name[i] == TGSI_SEMANTIC_POSITION ||
ctx->info.input_semantic_name[i] == TGSI_SEMANTIC_FACE ||
ctx->info.input_semantic_name[i] == TGSI_SEMANTIC_SAMPLEMASK)
ctx->info.input_semantic_name[i] == TGSI_SEMANTIC_SAMPLEMASK ||
ctx->info.input_semantic_name[i] == TGSI_SEMANTIC_SAMPLEID)
continue;
if (ctx->info.input_interpolate[i] == TGSI_INTERPOLATE_LINEAR)
ctx->input_linear = TRUE;
if (ctx->info.input_interpolate[i] == TGSI_INTERPOLATE_PERSPECTIVE)
ctx->input_perspective = TRUE;
if (ctx->info.input_interpolate_loc[i] == TGSI_INTERPOLATE_LOC_CENTROID)
ctx->input_centroid = TRUE;
k = eg_get_interpolator_index(
ctx->info.input_interpolate[i],
ctx->info.input_interpolate_loc[i]);
if (k >= 0)
ctx->eg_interpolators[k].enabled = TRUE;
}
/* assign gpr to each interpolator according to priority */
num_baryc = 0;
/* ignoring sample for now */
if (ctx->input_perspective)
num_baryc++;
if (ctx->input_linear)
num_baryc++;
if (ctx->input_centroid)
num_baryc *= 2;
for (i = 0; i < Elements(ctx->eg_interpolators); i++) {
if (ctx->eg_interpolators[i].enabled) {
ctx->eg_interpolators[i].ij_index = num_baryc;
num_baryc ++;
}
}
ctx->num_interp_gpr += (num_baryc + 1) >> 1;
/* XXX PULL MODEL and LINE STIPPLE */
/* XXX PULL MODEL and LINE STIPPLE, FIXED PT POS */
return ctx->num_interp_gpr;
num_baryc = (num_baryc + 1) >> 1;
return allocate_system_value_inputs(ctx, num_baryc);
}
/* sample_id_sel == NULL means fetch for current sample */
static int load_sample_position(struct r600_shader_ctx *ctx, struct r600_shader_src *sample_id, int chan_sel)
{
struct r600_bytecode_vtx vtx;
int r, t1;
assert(ctx->fixed_pt_position_gpr != -1);
t1 = r600_get_temp(ctx);
memset(&vtx, 0, sizeof(struct r600_bytecode_vtx));
vtx.op = FETCH_OP_VFETCH;
vtx.buffer_id = R600_SAMPLE_POSITIONS_CONST_BUFFER;
vtx.fetch_type = 2; /* VTX_FETCH_NO_INDEX_OFFSET */
if (sample_id == NULL) {
vtx.src_gpr = ctx->fixed_pt_position_gpr; // SAMPLEID is in .w;
vtx.src_sel_x = 3;
}
else {
struct r600_bytecode_alu alu;
memset(&alu, 0, sizeof(struct r600_bytecode_alu));
alu.op = ALU_OP1_MOV;
r600_bytecode_src(&alu.src[0], sample_id, chan_sel);
alu.dst.sel = t1;
alu.dst.write = 1;
alu.last = 1;
r = r600_bytecode_add_alu(ctx->bc, &alu);
if (r)
return r;
vtx.src_gpr = t1;
vtx.src_sel_x = 0;
}
vtx.mega_fetch_count = 16;
vtx.dst_gpr = t1;
vtx.dst_sel_x = 0;
vtx.dst_sel_y = 1;
vtx.dst_sel_z = 7;
vtx.dst_sel_w = 7;
vtx.data_format = FMT_32_32_32_32_FLOAT;
vtx.num_format_all = 2;
vtx.format_comp_all = 1;
vtx.use_const_fields = 0;
vtx.offset = 1; // first element is size of buffer
vtx.endian = r600_endian_swap(32);
vtx.srf_mode_all = 1; /* SRF_MODE_NO_ZERO */
r = r600_bytecode_add_vtx(ctx->bc, &vtx);
if (r)
return r;
return t1;
}
static void tgsi_src(struct r600_shader_ctx *ctx,
@@ -797,10 +930,22 @@ static void tgsi_src(struct r600_shader_ctx *ctx,
} else if (tgsi_src->Register.File == TGSI_FILE_SYSTEM_VALUE) {
if (ctx->info.system_value_semantic_name[tgsi_src->Register.Index] == TGSI_SEMANTIC_SAMPLEMASK) {
r600_src->swizzle[0] = 2; // Z value
r600_src->swizzle[0] = 2;
r600_src->swizzle[0] = 2;
r600_src->swizzle[0] = 2;
r600_src->swizzle[1] = 2;
r600_src->swizzle[2] = 2;
r600_src->swizzle[3] = 2;
r600_src->sel = ctx->face_gpr;
} else if (ctx->info.system_value_semantic_name[tgsi_src->Register.Index] == TGSI_SEMANTIC_SAMPLEID) {
r600_src->swizzle[0] = 3; // W value
r600_src->swizzle[1] = 3;
r600_src->swizzle[2] = 3;
r600_src->swizzle[3] = 3;
r600_src->sel = ctx->fixed_pt_position_gpr;
} else if (ctx->info.system_value_semantic_name[tgsi_src->Register.Index] == TGSI_SEMANTIC_SAMPLEPOS) {
r600_src->swizzle[0] = 0;
r600_src->swizzle[1] = 1;
r600_src->swizzle[2] = 4;
r600_src->swizzle[3] = 4;
r600_src->sel = load_sample_position(ctx, NULL, -1);
} else if (ctx->info.system_value_semantic_name[tgsi_src->Register.Index] == TGSI_SEMANTIC_INSTANCEID) {
r600_src->swizzle[0] = 3;
r600_src->swizzle[1] = 3;
@@ -1612,7 +1757,7 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
ctx.gs_next_vertex = 0;
ctx.face_gpr = -1;
ctx.has_samplemask = false;
ctx.fixed_pt_position_gpr = -1;
ctx.fragcoord_input = -1;
ctx.colors_used = 0;
ctx.clip_vertex_write = 0;
@@ -1661,8 +1806,11 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
r600_bytecode_add_cfinst(ctx.bc, CF_OP_CALL_FS);
}
}
if (ctx.type == TGSI_PROCESSOR_FRAGMENT && ctx.bc->chip_class >= EVERGREEN) {
ctx.file_offset[TGSI_FILE_INPUT] = evergreen_gpr_count(&ctx);
if (ctx.type == TGSI_PROCESSOR_FRAGMENT) {
if (ctx.bc->chip_class >= EVERGREEN)
ctx.file_offset[TGSI_FILE_INPUT] = evergreen_gpr_count(&ctx);
else
ctx.file_offset[TGSI_FILE_INPUT] = allocate_system_value_inputs(&ctx, ctx.file_offset[TGSI_FILE_INPUT]);
}
if (ctx.type == TGSI_PROCESSOR_GEOMETRY) {
/* FIXME 1 would be enough in some cases (3 or less input vertices) */
@@ -1775,14 +1923,6 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
shader->ring_item_size = ctx.next_ring_offset;
/* Need to tell setup to program FACE register */
if (ctx.has_samplemask && ctx.face_gpr != -1) {
i = ctx.shader->ninput++;
ctx.shader->input[i].name = TGSI_SEMANTIC_SAMPLEMASK;
ctx.shader->input[i].spi_sid = 0;
ctx.shader->input[i].gpr = ctx.face_gpr;
}
/* Process two side if needed */
if (shader->two_side && ctx.colors_used) {
int i, count = ctx.shader->ninput;
@@ -1795,6 +1935,7 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
int gpr = ctx.file_offset[TGSI_FILE_INPUT] +
ctx.info.file_max[TGSI_FILE_INPUT] + 1;
/* if two sided and neither face or sample mask is used by shader, ensure face_gpr is emitted */
if (ctx.face_gpr == -1) {
i = ctx.shader->ninput++;
ctx.shader->input[i].name = TGSI_SEMANTIC_FACE;
@@ -2162,6 +2303,13 @@ static int r600_shader_from_tgsi(struct r600_context *rctx,
output[j].swizzle_y = 1;
output[j].swizzle_z = output[j].swizzle_w = 7;
output[j].type = V_SQ_CF_ALLOC_EXPORT_WORD0_SQ_EXPORT_PIXEL;
} else if (shader->output[i].name == TGSI_SEMANTIC_SAMPLEMASK) {
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_PIXEL;
} else {
R600_ERR("unsupported fragment output name %d\n", shader->output[i].name);
r = -EINVAL;

6
src/gallium/drivers/r600/r600_shader.h
View File

@@ -33,7 +33,7 @@ struct r600_shader_io {
int spi_sid;
unsigned interpolate;
unsigned ij_index;
boolean centroid;
unsigned interpolate_location; // TGSI_INTERPOLATE_LOC_CENTER, CENTROID, SAMPLE
unsigned lds_pos; /* for evergreen */
unsigned back_color_input;
unsigned write_mask;
@@ -115,4 +115,8 @@ struct r600_pipe_shader {
unsigned ps_depth_export;
};
/* return the table index 0-5 for TGSI_INTERPOLATE_LINEAR/PERSPECTIVE and
TGSI_INTERPOLATE_LOC_CENTER/SAMPLE/COUNT. Other input values return -1. */
int eg_get_interpolator_index(unsigned interpolate, unsigned location);
#endif

60
src/gallium/drivers/r600/r600_state.c
View File

@@ -486,7 +486,12 @@ static void *r600_create_rs_state(struct pipe_context *ctx,
sc_mode_cntl = S_028A4C_MSAA_ENABLE(state->multisample) |
S_028A4C_LINE_STIPPLE_ENABLE(state->line_stipple_enable) |
S_028A4C_FORCE_EOV_CNTDWN_ENABLE(1);
S_028A4C_FORCE_EOV_CNTDWN_ENABLE(1) |
S_028A4C_PS_ITER_SAMPLE(state->multisample && rctx->ps_iter_samples > 1);
if (rctx->b.family == CHIP_RV770) {
/* workaround possible rendering corruption on RV770 with hyperz together with sample shading */
sc_mode_cntl |= S_028A4C_TILE_COVER_DISABLE(state->multisample && rctx->ps_iter_samples > 1);
}
if (rctx->b.chip_class >= R700) {
sc_mode_cntl |= S_028A4C_FORCE_EOV_REZ_ENABLE(1) |
S_028A4C_R700_ZMM_LINE_OFFSET(1) |
@@ -1245,6 +1250,8 @@ static void r600_set_framebuffer_state(struct pipe_context *ctx,
}
rctx->framebuffer.atom.dirty = true;
r600_set_sample_locations_constant_buffer(rctx);
}
static uint32_t sample_locs_2x[] = {
@@ -1524,6 +1531,21 @@ static void r600_emit_framebuffer_state(struct r600_context *rctx, struct r600_a
r600_emit_msaa_state(rctx, rctx->framebuffer.nr_samples);
}
static void r600_set_min_samples(struct pipe_context *ctx, unsigned min_samples)
{
struct r600_context *rctx = (struct r600_context *)ctx;
if (rctx->ps_iter_samples == min_samples)
return;
rctx->ps_iter_samples = min_samples;
if (rctx->framebuffer.nr_samples > 1) {
rctx->rasterizer_state.atom.dirty = true;
if (rctx->b.chip_class == R600)
rctx->db_misc_state.atom.dirty = true;
}
}
static void r600_emit_cb_misc_state(struct r600_context *rctx, struct r600_atom *atom)
{
struct radeon_winsys_cs *cs = rctx->b.rings.gfx.cs;
@@ -1603,6 +1625,10 @@ static void r600_emit_db_misc_state(struct r600_context *rctx, struct r600_atom
} else {
db_render_override |= S_028D10_FORCE_HIZ_ENABLE(V_028D10_FORCE_DISABLE);
}
if (rctx->b.chip_class == R600 && rctx->framebuffer.nr_samples > 1 && rctx->ps_iter_samples > 0) {
/* sample shading and hyperz causes lockups on R6xx chips */
db_render_override |= S_028D10_FORCE_HIZ_ENABLE(V_028D10_FORCE_DISABLE);
}
if (a->flush_depthstencil_through_cb) {
assert(a->copy_depth || a->copy_stencil);
@@ -2418,10 +2444,10 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
struct r600_command_buffer *cb = &shader->command_buffer;
struct r600_shader *rshader = &shader->shader;
unsigned i, exports_ps, num_cout, spi_ps_in_control_0, spi_input_z, spi_ps_in_control_1, db_shader_control;
int pos_index = -1, face_index = -1;
int pos_index = -1, face_index = -1, fixed_pt_position_index = -1;
unsigned tmp, sid, ufi = 0;
int need_linear = 0;
unsigned z_export = 0, stencil_export = 0;
unsigned z_export = 0, stencil_export = 0, mask_export = 0;
unsigned sprite_coord_enable = rctx->rasterizer ? rctx->rasterizer->sprite_coord_enable : 0;
if (!cb->buf) {
@@ -2434,8 +2460,10 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
for (i = 0; i < rshader->ninput; i++) {
if (rshader->input[i].name == TGSI_SEMANTIC_POSITION)
pos_index = i;
if (rshader->input[i].name == TGSI_SEMANTIC_FACE)
if (rshader->input[i].name == TGSI_SEMANTIC_FACE && face_index == -1)
face_index = i;
if (rshader->input[i].name == TGSI_SEMANTIC_SAMPLEID)
fixed_pt_position_index = i;
sid = rshader->input[i].spi_sid;
@@ -2452,9 +2480,12 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
tmp |= S_028644_PT_SPRITE_TEX(1);
}
if (rshader->input[i].centroid)
if (rshader->input[i].interpolate_location == TGSI_INTERPOLATE_LOC_CENTROID)
tmp |= S_028644_SEL_CENTROID(1);
if (rshader->input[i].interpolate_location == TGSI_INTERPOLATE_LOC_SAMPLE)
tmp |= S_028644_SEL_SAMPLE(1);
if (rshader->input[i].interpolate == TGSI_INTERPOLATE_LINEAR) {
need_linear = 1;
tmp |= S_028644_SEL_LINEAR(1);
@@ -2469,16 +2500,21 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
z_export = 1;
if (rshader->output[i].name == TGSI_SEMANTIC_STENCIL)
stencil_export = 1;
if (rshader->output[i].name == TGSI_SEMANTIC_SAMPLEMASK &&
rctx->framebuffer.nr_samples > 1 && rctx->ps_iter_samples > 0)
mask_export = 1;
}
db_shader_control |= S_02880C_Z_EXPORT_ENABLE(z_export);
db_shader_control |= S_02880C_STENCIL_REF_EXPORT_ENABLE(stencil_export);
db_shader_control |= S_02880C_MASK_EXPORT_ENABLE(mask_export);
if (rshader->uses_kill)
db_shader_control |= S_02880C_KILL_ENABLE(1);
exports_ps = 0;
for (i = 0; i < rshader->noutput; i++) {
if (rshader->output[i].name == TGSI_SEMANTIC_POSITION ||
rshader->output[i].name == TGSI_SEMANTIC_STENCIL) {
rshader->output[i].name == TGSI_SEMANTIC_STENCIL ||
rshader->output[i].name == TGSI_SEMANTIC_SAMPLEMASK) {
exports_ps |= 1;
}
}
@@ -2497,9 +2533,10 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
spi_input_z = 0;
if (pos_index != -1) {
spi_ps_in_control_0 |= (S_0286CC_POSITION_ENA(1) |
S_0286CC_POSITION_CENTROID(rshader->input[pos_index].centroid) |
S_0286CC_POSITION_CENTROID(rshader->input[pos_index].interpolate_location == TGSI_INTERPOLATE_LOC_CENTROID) |
S_0286CC_POSITION_ADDR(rshader->input[pos_index].gpr) |
S_0286CC_BARYC_SAMPLE_CNTL(1));
S_0286CC_BARYC_SAMPLE_CNTL(1)) |
S_0286CC_POSITION_SAMPLE(rshader->input[pos_index].interpolate_location == TGSI_INTERPOLATE_LOC_SAMPLE);
spi_input_z |= S_0286D8_PROVIDE_Z_TO_SPI(1);
}
@@ -2508,6 +2545,10 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
spi_ps_in_control_1 |= S_0286D0_FRONT_FACE_ENA(1) |
S_0286D0_FRONT_FACE_ADDR(rshader->input[face_index].gpr);
}
if (fixed_pt_position_index != -1) {
spi_ps_in_control_1 |= S_0286D0_FIXED_PT_POSITION_ENA(1) |
S_0286D0_FIXED_PT_POSITION_ADDR(rshader->input[fixed_pt_position_index].gpr);
}
/* HW bug in original R600 */
if (rctx->b.family == CHIP_R600)
@@ -2531,7 +2572,7 @@ void r600_update_ps_state(struct pipe_context *ctx, struct r600_pipe_shader *sha
/* only set some bits here, the other bits are set in the dsa state */
shader->db_shader_control = db_shader_control;
shader->ps_depth_export = z_export | stencil_export;
shader->ps_depth_export = z_export | stencil_export | mask_export;
shader->sprite_coord_enable = sprite_coord_enable;
if (rctx->rasterizer)
@@ -3046,6 +3087,7 @@ void r600_init_state_functions(struct r600_context *rctx)
rctx->b.b.create_sampler_view = r600_create_sampler_view;
rctx->b.b.set_framebuffer_state = r600_set_framebuffer_state;
rctx->b.b.set_polygon_stipple = r600_set_polygon_stipple;
rctx->b.b.set_min_samples = r600_set_min_samples;
rctx->b.b.set_scissor_states = r600_set_scissor_states;
rctx->b.b.get_sample_position = r600_get_sample_position;
rctx->b.dma_copy = r600_dma_copy;

20
src/gallium/drivers/r600/r600_state_common.c
View File

@@ -1085,6 +1085,26 @@ static void r600_setup_txq_cube_array_constants(struct r600_context *rctx, int s
pipe_resource_reference(&cb.buffer, NULL);
}
/* set sample xy locations as array of fragment shader constants */
void r600_set_sample_locations_constant_buffer(struct r600_context *rctx)
{
struct pipe_constant_buffer constbuf = {0};
float values[4*16] = {0.0f};
int i;
struct pipe_context *ctx = &rctx->b.b;
assert(rctx->framebuffer.nr_samples <= Elements(values)/4);
for (i = 0; i < rctx->framebuffer.nr_samples; i++) {
ctx->get_sample_position(ctx, rctx->framebuffer.nr_samples, i, &values[4*i]);
}
constbuf.user_buffer = values;
constbuf.buffer_size = rctx->framebuffer.nr_samples * 4 * 4;
ctx->set_constant_buffer(ctx, PIPE_SHADER_FRAGMENT,
R600_SAMPLE_POSITIONS_CONST_BUFFER, &constbuf);
pipe_resource_reference(&constbuf.buffer, NULL);
}
static void update_shader_atom(struct pipe_context *ctx,
struct r600_shader_state *state,
struct r600_pipe_shader *shader)

3
src/gallium/drivers/r600/r600d.h
View File

@@ -841,6 +841,9 @@
#define S_02880C_KILL_ENABLE(x) (((x) & 0x1) << 6)
#define G_02880C_KILL_ENABLE(x) (((x) >> 6) & 0x1)
#define C_02880C_KILL_ENABLE 0xFFFFFFBF
#define S_02880C_MASK_EXPORT_ENABLE(x) (((x) & 0x1) << 8)
#define G_02880C_MASK_EXPORT_ENABLE(x) (((x) >> 8) & 0x1)
#define C_02880C_MASK_EXPORT_ENABLE 0xFFFFFEFF
#define S_02880C_DUAL_EXPORT_ENABLE(x) (((x) & 0x1) << 9)
#define G_02880C_DUAL_EXPORT_ENABLE(x) (((x) >> 9) & 0x1)
#define C_02880C_DUAL_EXPORT_ENABLE 0xFFFFFDFF

21
src/gallium/drivers/r600/sb/sb_bc_parser.cpp
View File

@@ -147,25 +147,28 @@ int bc_parser::parse_decls() {
bool ps_interp = ctx.hw_class >= HW_CLASS_EVERGREEN
&& sh->target == TARGET_PS;
unsigned linear = 0, persp = 0, centroid = 1;
bool ij_interpolators[6];
memset(ij_interpolators, 0, sizeof(ij_interpolators));
for (unsigned i = 0; i < pshader->ninput; ++i) {
r600_shader_io & in = pshader->input[i];
bool preloaded = sh->target == TARGET_PS && !(ps_interp && in.spi_sid);
sh->add_input(in.gpr, preloaded, /*in.write_mask*/ 0x0F);
if (ps_interp && in.spi_sid) {
if (in.interpolate == TGSI_INTERPOLATE_LINEAR ||
in.interpolate == TGSI_INTERPOLATE_COLOR)
linear = 1;
else if (in.interpolate == TGSI_INTERPOLATE_PERSPECTIVE)
persp = 1;
if (in.centroid)
centroid = 2;
int k = eg_get_interpolator_index(in.interpolate, in.interpolate_location);
if (k >= 0)
ij_interpolators[k] |= true;
}
}
if (ps_interp) {
unsigned mask = (1 << (2 * (linear + persp) * centroid)) - 1;
/* add the egcm ij interpolators to live inputs */
unsigned num_ij = 0;
for (unsigned i = 0; i < Elements(ij_interpolators); i++) {
num_ij += ij_interpolators[i];
}
unsigned mask = (1 << (2 * num_ij)) - 1;
unsigned gpr = 0;
while (mask) {