nir: Add nir_lower_tex options to lower sampler return formats.

I've been doing this in the nir-to-vir and nir-to-qir backends of v3d and
vc4, but nir could potentially do some useful stuff for us (like avoiding
unpack/repacks) if we give it the information.

v2: Skip lowering for txs/query_levels
v3: Fix a crash on old-style shadow
v4: Rename to tex_packing, use nir_format_unpack_sint/uint helpers, pack
    the enum.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This commit is contained in:
Eric Anholt
2018-12-19 13:53:39 -08:00
parent a74f2aeb4f
commit f217a94542
2 changed files with 83 additions and 0 deletions

View File

@@ -2933,6 +2933,16 @@ bool nir_lower_subgroups(nir_shader *shader,
bool nir_lower_system_values(nir_shader *shader);
enum PACKED nir_lower_tex_packing {
nir_lower_tex_packing_none = 0,
/* The sampler returns up to 2 32-bit words of half floats or 16-bit signed
* or unsigned ints based on the sampler type
*/
nir_lower_tex_packing_16,
/* The sampler returns 1 32-bit word of 4x8 unorm */
nir_lower_tex_packing_8,
};
typedef struct nir_lower_tex_options {
/**
* bitmask of (1 << GLSL_SAMPLER_DIM_x) to control for which
@@ -3044,6 +3054,8 @@ typedef struct nir_lower_tex_options {
* with nir_texop_txl. This includes cube maps.
*/
bool lower_txd_offset_clamp;
enum nir_lower_tex_packing lower_tex_packing[32];
} nir_lower_tex_options;
bool nir_lower_tex(nir_shader *shader,

View File

@@ -801,6 +801,69 @@ linearize_srgb_result(nir_builder *b, nir_tex_instr *tex)
result->parent_instr);
}
/**
* Lowers texture instructions from giving a vec4 result to a vec2 of f16,
* i16, or u16, or a single unorm4x8 value.
*
* Note that we don't change the destination num_components, because
* nir_tex_instr_dest_size() will still return 4. The driver is just expected
* to not store the other channels, given that nothing at the NIR level will
* read them.
*/
static void
lower_tex_packing(nir_builder *b, nir_tex_instr *tex,
const nir_lower_tex_options *options)
{
nir_ssa_def *color = &tex->dest.ssa;
b->cursor = nir_after_instr(&tex->instr);
switch (options->lower_tex_packing[tex->sampler_index]) {
case nir_lower_tex_packing_none:
return;
case nir_lower_tex_packing_16: {
static const unsigned bits[4] = {16, 16, 16, 16};
switch (nir_alu_type_get_base_type(tex->dest_type)) {
case nir_type_float:
if (tex->is_shadow && tex->is_new_style_shadow) {
color = nir_unpack_half_2x16_split_x(b, nir_channel(b, color, 0));
} else {
nir_ssa_def *rg = nir_channel(b, color, 0);
nir_ssa_def *ba = nir_channel(b, color, 1);
color = nir_vec4(b,
nir_unpack_half_2x16_split_x(b, rg),
nir_unpack_half_2x16_split_y(b, rg),
nir_unpack_half_2x16_split_x(b, ba),
nir_unpack_half_2x16_split_y(b, ba));
}
break;
case nir_type_int:
color = nir_format_unpack_sint(b, color, bits, 4);
break;
case nir_type_uint:
color = nir_format_unpack_uint(b, color, bits, 4);
break;
default:
unreachable("unknown base type");
}
break;
}
case nir_lower_tex_packing_8:
assert(nir_alu_type_get_base_type(tex->dest_type) == nir_type_float);
color = nir_unpack_unorm_4x8(b, nir_channel(b, color, 0));
break;
}
nir_ssa_def_rewrite_uses_after(&tex->dest.ssa, nir_src_for_ssa(color),
color->parent_instr);
}
static bool
nir_lower_tex_block(nir_block *block, nir_builder *b,
const nir_lower_tex_options *options)
@@ -899,6 +962,14 @@ nir_lower_tex_block(nir_block *block, nir_builder *b,
progress = true;
}
if (options->lower_tex_packing[tex->sampler_index] !=
nir_lower_tex_packing_none &&
tex->op != nir_texop_txs &&
tex->op != nir_texop_query_levels) {
lower_tex_packing(b, tex, options);
progress = true;
}
if (tex->op == nir_texop_txd &&
(options->lower_txd ||
(options->lower_txd_shadow && tex->is_shadow) ||