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

v3d: Ask the state tracker to lower image accesses off of derefs.

Browse Source 
This saves a bunch of hassle in handling derefs in the backend, and would
be needed for reasonable handling of dynamic indexing of image arrays.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3728>
This commit is contained in:
Eric Anholt
2020-01-23 16:33:24 -08:00
committed by Marge Bot
parent 9c90ecf37f
commit 12cf484d02
4 changed files with 51 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
src/broadcom/compiler/nir_to_vir.c
View File

@@ -1760,11 +1760,8 @@ ntq_emit_ssa_undef(struct v3d_compile *c, nir_ssa_undef_instr *instr)
static void
ntq_emit_image_size(struct v3d_compile *c, nir_intrinsic_instr *instr)
{
assert(instr->intrinsic == nir_intrinsic_image_deref_size);
nir_variable *var = nir_intrinsic_get_var(instr, 0);
unsigned image_index = var->data.driver_location;
const struct glsl_type *sampler_type = glsl_without_array(var->type);
bool is_array = glsl_sampler_type_is_array(sampler_type);
unsigned image_index = nir_src_as_uint(instr->src[0]);
bool is_array = nir_intrinsic_image_array(instr);
ntq_store_dest(c, &instr->dest, 0,
vir_uniform(c, QUNIFORM_IMAGE_WIDTH, image_index));
@@ -2104,18 +2101,18 @@ ntq_emit_intrinsic(struct v3d_compile *c, nir_intrinsic_instr *instr)
ntq_emit_tmu_general(c, instr, true);
break;
case nir_intrinsic_image_deref_load:
case nir_intrinsic_image_deref_store:
case nir_intrinsic_image_deref_atomic_add:
case nir_intrinsic_image_deref_atomic_imin:
case nir_intrinsic_image_deref_atomic_umin:
case nir_intrinsic_image_deref_atomic_imax:
case nir_intrinsic_image_deref_atomic_umax:
case nir_intrinsic_image_deref_atomic_and:
case nir_intrinsic_image_deref_atomic_or:
case nir_intrinsic_image_deref_atomic_xor:
case nir_intrinsic_image_deref_atomic_exchange:
case nir_intrinsic_image_deref_atomic_comp_swap:
case nir_intrinsic_image_load:
case nir_intrinsic_image_store:
case nir_intrinsic_image_atomic_add:
case nir_intrinsic_image_atomic_imin:
case nir_intrinsic_image_atomic_umin:
case nir_intrinsic_image_atomic_imax:
case nir_intrinsic_image_atomic_umax:
case nir_intrinsic_image_atomic_and:
case nir_intrinsic_image_atomic_or:
case nir_intrinsic_image_atomic_xor:
case nir_intrinsic_image_atomic_exchange:
case nir_intrinsic_image_atomic_comp_swap:
v3d40_vir_emit_image_load_store(c, instr);
break;
@@ -2205,7 +2202,7 @@ ntq_emit_intrinsic(struct v3d_compile *c, nir_intrinsic_instr *instr)
ntq_emit_store_output(c, instr);
break;
case nir_intrinsic_image_deref_size:
case nir_intrinsic_image_size:
ntq_emit_image_size(c, instr);
break;
@@ -2553,10 +2550,6 @@ static void
ntq_emit_instr(struct v3d_compile *c, nir_instr *instr)
{
switch (instr->type) {
case nir_instr_type_deref:
/* ignored, will be walked by the intrinsic using it. */
break;
case nir_instr_type_alu:
ntq_emit_alu(c, nir_instr_as_alu(instr));
break;

57
src/broadcom/compiler/v3d40_tex.c
View File

@@ -22,7 +22,6 @@
*/
#include "v3d_compiler.h"
#include "compiler/nir/nir_deref.h"
/* We don't do any address packing. */
#define __gen_user_data void
@@ -236,39 +235,32 @@ v3d40_vir_emit_tex(struct v3d_compile *c, nir_tex_instr *instr)
}
}
static void
type_size_align_1(const struct glsl_type *type, unsigned *size, unsigned *align)
{
*size = 1;
*align = 1;
}
static uint32_t
v3d40_image_load_store_tmu_op(nir_intrinsic_instr *instr)
{
switch (instr->intrinsic) {
case nir_intrinsic_image_deref_load:
case nir_intrinsic_image_deref_store:
case nir_intrinsic_image_load:
case nir_intrinsic_image_store:
return V3D_TMU_OP_REGULAR;
case nir_intrinsic_image_deref_atomic_add:
case nir_intrinsic_image_atomic_add:
return v3d_get_op_for_atomic_add(instr, 3);
case nir_intrinsic_image_deref_atomic_imin:
case nir_intrinsic_image_atomic_imin:
return V3D_TMU_OP_WRITE_SMIN;
case nir_intrinsic_image_deref_atomic_umin:
case nir_intrinsic_image_atomic_umin:
return V3D_TMU_OP_WRITE_UMIN_FULL_L1_CLEAR;
case nir_intrinsic_image_deref_atomic_imax:
case nir_intrinsic_image_atomic_imax:
return V3D_TMU_OP_WRITE_SMAX;
case nir_intrinsic_image_deref_atomic_umax:
case nir_intrinsic_image_atomic_umax:
return V3D_TMU_OP_WRITE_UMAX;
case nir_intrinsic_image_deref_atomic_and:
case nir_intrinsic_image_atomic_and:
return V3D_TMU_OP_WRITE_AND_READ_INC;
case nir_intrinsic_image_deref_atomic_or:
case nir_intrinsic_image_atomic_or:
return V3D_TMU_OP_WRITE_OR_READ_DEC;
case nir_intrinsic_image_deref_atomic_xor:
case nir_intrinsic_image_atomic_xor:
return V3D_TMU_OP_WRITE_XOR_READ_NOT;
case nir_intrinsic_image_deref_atomic_exchange:
case nir_intrinsic_image_atomic_exchange:
return V3D_TMU_OP_WRITE_XCHG_READ_FLUSH;
case nir_intrinsic_image_deref_atomic_comp_swap:
case nir_intrinsic_image_atomic_comp_swap:
return V3D_TMU_OP_WRITE_CMPXCHG_READ_FLUSH;
default:
unreachable("unknown image intrinsic");
@@ -279,11 +271,8 @@ void
v3d40_vir_emit_image_load_store(struct v3d_compile *c,
nir_intrinsic_instr *instr)
{
nir_variable *var = nir_intrinsic_get_var(instr, 0);
const struct glsl_type *sampler_type = glsl_without_array(var->type);
unsigned unit = (var->data.driver_location +
nir_deref_instr_get_const_offset(nir_src_as_deref(instr->src[0]),
type_size_align_1));
unsigned format = nir_intrinsic_format(instr);
unsigned unit = nir_src_as_uint(instr->src[0]);
int tmu_writes = 0;
struct V3D41_TMU_CONFIG_PARAMETER_0 p0_unpacked = {
@@ -291,7 +280,7 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
struct V3D41_TMU_CONFIG_PARAMETER_1 p1_unpacked = {
.per_pixel_mask_enable = true,
.output_type_32_bit = v3d_gl_format_is_return_32(var->data.image.format),
.output_type_32_bit = v3d_gl_format_is_return_32(format),
};
struct V3D41_TMU_CONFIG_PARAMETER_2 p2_unpacked = { 0 };
@@ -302,12 +291,12 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
* need/can to do things slightly different, like not loading the
* amount to add/sub, as that is implicit.
*/
bool atomic_add_replaced = (instr->intrinsic == nir_intrinsic_image_deref_atomic_add &&
bool atomic_add_replaced = (instr->intrinsic == nir_intrinsic_image_atomic_add &&
(p2_unpacked.op == V3D_TMU_OP_WRITE_AND_READ_INC ||
p2_unpacked.op == V3D_TMU_OP_WRITE_OR_READ_DEC));
bool is_1d = false;
switch (glsl_get_sampler_dim(sampler_type)) {
switch (nir_intrinsic_image_dim(instr)) {
case GLSL_SAMPLER_DIM_1D:
is_1d = true;
break;
@@ -329,7 +318,7 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
unreachable("bad image sampler dim");
}
if (glsl_sampler_type_is_array(sampler_type)) {
if (nir_intrinsic_image_array(instr)) {
vir_TMU_WRITE(c, V3D_QPU_WADDR_TMUI,
ntq_get_src(c, instr->src[1],
is_1d ? 1 : 2), &tmu_writes);
@@ -373,7 +362,7 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
vir_WRTMUC(c, QUNIFORM_CONSTANT, p2_packed);
/* Emit the data writes for atomics or image store. */
if (instr->intrinsic != nir_intrinsic_image_deref_load &&
if (instr->intrinsic != nir_intrinsic_image_load &&
!atomic_add_replaced) {
/* Vector for stores, or first atomic argument */
struct qreg src[4];
@@ -385,7 +374,7 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
/* Second atomic argument */
if (instr->intrinsic ==
nir_intrinsic_image_deref_atomic_comp_swap) {
nir_intrinsic_image_atomic_comp_swap) {
vir_TMU_WRITE(c, V3D_QPU_WADDR_TMUD,
ntq_get_src(c, instr->src[4], 0),
&tmu_writes);
@@ -393,7 +382,7 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
}
if (vir_in_nonuniform_control_flow(c) &&
instr->intrinsic != nir_intrinsic_image_deref_load) {
instr->intrinsic != nir_intrinsic_image_load) {
vir_set_pf(vir_MOV_dest(c, vir_nop_reg(), c->execute),
V3D_QPU_PF_PUSHZ);
}
@@ -402,7 +391,7 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
&tmu_writes);
if (vir_in_nonuniform_control_flow(c) &&
instr->intrinsic != nir_intrinsic_image_deref_load) {
instr->intrinsic != nir_intrinsic_image_load) {
struct qinst *last_inst= (struct qinst *)c->cur_block->instructions.prev;
vir_set_cond(last_inst, V3D_QPU_COND_IFA);
}
@@ -423,6 +412,6 @@ v3d40_vir_emit_image_load_store(struct v3d_compile *c,
if (nir_intrinsic_dest_components(instr) == 0)
vir_TMUWT(c);
if (instr->intrinsic != nir_intrinsic_image_deref_load)
if (instr->intrinsic != nir_intrinsic_image_load)
c->tmu_dirty_rcl = true;
}

25
src/broadcom/compiler/v3d_nir_lower_image_load_store.c
View File

@@ -87,8 +87,7 @@ pack_bits(nir_builder *b, nir_ssa_def *color, const unsigned *bits,
static void
v3d_nir_lower_image_store(nir_builder *b, nir_intrinsic_instr *instr)
{
nir_variable *var = nir_intrinsic_get_var(instr, 0);
enum pipe_format format = var->data.image.format;
enum pipe_format format = nir_intrinsic_format(instr);
const struct util_format_description *desc =
util_format_description(format);
const struct util_format_channel_description *r_chan = &desc->channel[0];
@@ -164,19 +163,20 @@ static void
v3d_nir_lower_image_load(nir_builder *b, nir_intrinsic_instr *instr)
{
static const unsigned bits16[] = {16, 16, 16, 16};
nir_variable *var = nir_intrinsic_get_var(instr, 0);
const struct glsl_type *sampler_type = glsl_without_array(var->type);
enum glsl_base_type base_type =
glsl_get_sampler_result_type(sampler_type);
enum pipe_format format = nir_intrinsic_format(instr);
if (v3d_gl_format_is_return_32(var->data.image.format))
if (v3d_gl_format_is_return_32(format))
return;
b->cursor = nir_after_instr(&instr->instr);
assert(instr->dest.is_ssa);
nir_ssa_def *result = &instr->dest.ssa;
if (base_type == GLSL_TYPE_FLOAT) {
if (util_format_is_pure_uint(format)) {
result = nir_format_unpack_uint(b, result, bits16, 4);
} else if (util_format_is_pure_sint(format)) {
result = nir_format_unpack_sint(b, result, bits16, 4);
} else {
nir_ssa_def *rg = nir_channel(b, result, 0);
nir_ssa_def *ba = nir_channel(b, result, 1);
result = nir_vec4(b,
@@ -184,11 +184,6 @@ v3d_nir_lower_image_load(nir_builder *b, nir_intrinsic_instr *instr)
nir_unpack_half_2x16_split_y(b, rg),
nir_unpack_half_2x16_split_x(b, ba),
nir_unpack_half_2x16_split_y(b, ba));
} else if (base_type == GLSL_TYPE_INT) {
result = nir_format_unpack_sint(b, result, bits16, 4);
} else {
assert(base_type == GLSL_TYPE_UINT);
result = nir_format_unpack_uint(b, result, bits16, 4);
}
nir_ssa_def_rewrite_uses_after(&instr->dest.ssa, nir_src_for_ssa(result),
@@ -214,10 +209,10 @@ v3d_nir_lower_image_load_store(nir_shader *s)
nir_instr_as_intrinsic(instr);
switch (intr->intrinsic) {
case nir_intrinsic_image_deref_load:
case nir_intrinsic_image_load:
v3d_nir_lower_image_load(&b, intr);
break;
case nir_intrinsic_image_deref_store:
case nir_intrinsic_image_store:
v3d_nir_lower_image_store(&b, intr);
break;
default:

3
src/gallium/drivers/v3d/v3d_screen.c
View File

@@ -146,6 +146,9 @@ v3d_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
*/
return 0;
case PIPE_CAP_NIR_IMAGES_AS_DEREF:
return 0;
case PIPE_CAP_PREFER_BLIT_BASED_TEXTURE_TRANSFER:
/* XXX perf: we don't want to emit these extra blits for
* glReadPixels(), since we still have to do an uncached read