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

intel/compiler: Lower flrp32 on Gen11+

Browse Source 
The LRP instruction is no more.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This commit is contained in:
Matt Turner
2017-06-14 16:20:41 -07:00
parent 2134ea3800
commit 89fe5190a2
5 changed files with 26 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
src/intel/compiler/brw_compiler.c
View File

@@ -46,20 +46,28 @@
.use_interpolated_input_intrinsics = true, \ .use_interpolated_input_intrinsics = true, \
.vertex_id_zero_based = true .vertex_id_zero_based = true
#define COMMON_SCALAR_OPTIONS \
.lower_pack_half_2x16 = true, \
.lower_pack_snorm_2x16 = true, \
.lower_pack_snorm_4x8 = true, \
.lower_pack_unorm_2x16 = true, \
.lower_pack_unorm_4x8 = true, \
.lower_unpack_half_2x16 = true, \
.lower_unpack_snorm_2x16 = true, \
.lower_unpack_snorm_4x8 = true, \
.lower_unpack_unorm_2x16 = true, \
.lower_unpack_unorm_4x8 = true, \
.max_unroll_iterations = 32
static const struct nir_shader_compiler_options scalar_nir_options = { static const struct nir_shader_compiler_options scalar_nir_options = {
COMMON_OPTIONS, COMMON_OPTIONS,
.lower_pack_half_2x16 = true, COMMON_SCALAR_OPTIONS,
.lower_pack_snorm_2x16 = true, };
.lower_pack_snorm_4x8 = true,
.lower_pack_unorm_2x16 = true, static const struct nir_shader_compiler_options scalar_nir_options_gen11 = {
.lower_pack_unorm_4x8 = true, COMMON_OPTIONS,
.lower_unpack_half_2x16 = true, COMMON_SCALAR_OPTIONS,
.lower_unpack_snorm_2x16 = true, .lower_flrp32 = true,
.lower_unpack_snorm_4x8 = true,
.lower_unpack_unorm_2x16 = true,
.lower_unpack_unorm_4x8 = true,
.vs_inputs_dual_locations = true,
.max_unroll_iterations = 32,
}; };
static const struct nir_shader_compiler_options vector_nir_options = { static const struct nir_shader_compiler_options vector_nir_options = {
@@ -149,7 +157,8 @@ brw_compiler_create(void *mem_ctx, const struct gen_device_info *devinfo)
compiler->glsl_compiler_options[i].OptimizeForAOS = !is_scalar; compiler->glsl_compiler_options[i].OptimizeForAOS = !is_scalar;
if (is_scalar) { if (is_scalar) {
compiler->glsl_compiler_options[i].NirOptions = &scalar_nir_options; compiler->glsl_compiler_options[i].NirOptions =
devinfo->gen < 11 ? &scalar_nir_options : &scalar_nir_options_gen11;
} else { } else {
compiler->glsl_compiler_options[i].NirOptions = compiler->glsl_compiler_options[i].NirOptions =
devinfo->gen < 6 ? &vector_nir_options : &vector_nir_options_gen6; devinfo->gen < 6 ? &vector_nir_options : &vector_nir_options_gen6;

2
src/intel/compiler/brw_fs_builder.h
View File

@@ -540,7 +540,7 @@ namespace brw {
LRP(const dst_reg &dst, const src_reg &x, const src_reg &y, LRP(const dst_reg &dst, const src_reg &x, const src_reg &y,
const src_reg &a) const const src_reg &a) const
{ {
if (shader->devinfo->gen >= 6) { if (shader->devinfo->gen >= 6 && shader->devinfo->gen <= 10) {
/* The LRP instruction actually does op1 * op0 + op2 * (1 - op0), so /* The LRP instruction actually does op1 * op0 + op2 * (1 - op0), so
* we need to reorder the operands. * we need to reorder the operands.
*/ */

2
src/intel/compiler/brw_fs_generator.cpp
View File

@@ -1826,7 +1826,7 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width)
break; break;
case BRW_OPCODE_LRP: case BRW_OPCODE_LRP:
assert(devinfo->gen >= 6); assert(devinfo->gen >= 6 && devinfo->gen <= 10);
if (devinfo->gen < 10) if (devinfo->gen < 10)
brw_set_default_access_mode(p, BRW_ALIGN_16); brw_set_default_access_mode(p, BRW_ALIGN_16);
brw_LRP(p, dst, src[0], src[1], src[2]); brw_LRP(p, dst, src[0], src[1], src[2]);

2
src/intel/compiler/brw_vec4_builder.h
View File

@@ -501,7 +501,7 @@ namespace brw {
LRP(const dst_reg &dst, const src_reg &x, const src_reg &y, LRP(const dst_reg &dst, const src_reg &x, const src_reg &y,
const src_reg &a) const const src_reg &a) const
{ {
if (shader->devinfo->gen >= 6) { if (shader->devinfo->gen >= 6 && shader->devinfo->gen <= 10) {
/* The LRP instruction actually does op1 * op0 + op2 * (1 - op0), so /* The LRP instruction actually does op1 * op0 + op2 * (1 - op0), so
* we need to reorder the operands. * we need to reorder the operands.
*/ */

2
src/intel/compiler/brw_vec4_visitor.cpp
View File

@@ -735,7 +735,7 @@ vec4_instruction *
vec4_visitor::emit_lrp(const dst_reg &dst, vec4_visitor::emit_lrp(const dst_reg &dst,
const src_reg &x, const src_reg &y, const src_reg &a) const src_reg &x, const src_reg &y, const src_reg &a)
{ {
if (devinfo->gen >= 6) { if (devinfo->gen >= 6 && devinfo->gen <= 10) {
/* Note that the instruction's argument order is reversed from GLSL /* Note that the instruction's argument order is reversed from GLSL
* and the IR. * and the IR.
*/ */