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

radv: Always lower indirect derefs after nir_lower_global_vars_to_local.

Browse Source 
Otherwise new local variables can cause hangs on vega.

CC: <mesa-stable@lists.freedesktop.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105098
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
This commit is contained in:
Bas Nieuwenhuizen
2018-02-15 21:24:35 +01:00
parent 2ab1ce30c4
commit 05d84ed68a
3 changed files with 53 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/amd/vulkan/radv_pipeline.c
View File

@@ -1525,9 +1525,16 @@ radv_link_shaders(struct radv_pipeline *pipeline, nir_shader **shaders)
ordered_shaders[i - 1]);
if (progress) {
nir_lower_global_vars_to_local(ordered_shaders[i]);
if (nir_lower_global_vars_to_local(ordered_shaders[i])) {
radv_lower_indirect_derefs(ordered_shaders[i],
pipeline->device->physical_device);
}
radv_optimize_nir(ordered_shaders[i]);
nir_lower_global_vars_to_local(ordered_shaders[i - 1]);
if (nir_lower_global_vars_to_local(ordered_shaders[i - 1])) {
radv_lower_indirect_derefs(ordered_shaders[i - 1],
pipeline->device->physical_device);
}
radv_optimize_nir(ordered_shaders[i - 1]);
}
}

74
src/amd/vulkan/radv_shader.c
View File

@@ -114,6 +114,45 @@ void radv_DestroyShaderModule(
vk_free2(&device->alloc, pAllocator, module);
}
bool
radv_lower_indirect_derefs(struct nir_shader *nir,
struct radv_physical_device *device)
{
/* While it would be nice not to have this flag, we are constrained
* by the reality that LLVM 5.0 doesn't have working VGPR indexing
* on GFX9.
*/
bool llvm_has_working_vgpr_indexing =
device->rad_info.chip_class <= VI;
/* TODO: Indirect indexing of GS inputs is unimplemented.
*
* TCS and TES load inputs directly from LDS or offchip memory, so
* indirect indexing is trivial.
*/
nir_variable_mode indirect_mask = 0;
if (nir->info.stage == MESA_SHADER_GEOMETRY ||
(nir->info.stage != MESA_SHADER_TESS_CTRL &&
nir->info.stage != MESA_SHADER_TESS_EVAL &&
!llvm_has_working_vgpr_indexing)) {
indirect_mask |= nir_var_shader_in;
}
if (!llvm_has_working_vgpr_indexing &&
nir->info.stage != MESA_SHADER_TESS_CTRL)
indirect_mask |= nir_var_shader_out;
/* TODO: We shouldn't need to do this, however LLVM isn't currently
* smart enough to handle indirects without causing excess spilling
* causing the gpu to hang.
*
* See the following thread for more details of the problem:
* https://lists.freedesktop.org/archives/mesa-dev/2017-July/162106.html
*/
indirect_mask |= nir_var_local;
return nir_lower_indirect_derefs(nir, indirect_mask);
}
void
radv_optimize_nir(struct nir_shader *shader)
{
@@ -254,40 +293,6 @@ radv_shader_compile_to_nir(struct radv_device *device,
nir_shader_gather_info(nir, entry_point->impl);
/* While it would be nice not to have this flag, we are constrained
* by the reality that LLVM 5.0 doesn't have working VGPR indexing
* on GFX9.
*/
bool llvm_has_working_vgpr_indexing =
device->physical_device->rad_info.chip_class <= VI;
/* TODO: Indirect indexing of GS inputs is unimplemented.
*
* TCS and TES load inputs directly from LDS or offchip memory, so
* indirect indexing is trivial.
*/
nir_variable_mode indirect_mask = 0;
if (nir->info.stage == MESA_SHADER_GEOMETRY ||
(nir->info.stage != MESA_SHADER_TESS_CTRL &&
nir->info.stage != MESA_SHADER_TESS_EVAL &&
!llvm_has_working_vgpr_indexing)) {
indirect_mask |= nir_var_shader_in;
}
if (!llvm_has_working_vgpr_indexing &&
nir->info.stage != MESA_SHADER_TESS_CTRL)
indirect_mask |= nir_var_shader_out;
/* TODO: We shouldn't need to do this, however LLVM isn't currently
* smart enough to handle indirects without causing excess spilling
* causing the gpu to hang.
*
* See the following thread for more details of the problem:
* https://lists.freedesktop.org/archives/mesa-dev/2017-July/162106.html
*/
indirect_mask |= nir_var_local;
nir_lower_indirect_derefs(nir, indirect_mask);
static const nir_lower_tex_options tex_options = {
.lower_txp = ~0,
};
@@ -298,6 +303,7 @@ radv_shader_compile_to_nir(struct radv_device *device,
nir_lower_var_copies(nir);
nir_lower_global_vars_to_local(nir);
nir_remove_dead_variables(nir, nir_var_local);
radv_lower_indirect_derefs(nir, device->physical_device);
radv_optimize_nir(nir);
return nir;

4
src/amd/vulkan/radv_shader.h
View File

@@ -104,6 +104,10 @@ void
radv_shader_variant_destroy(struct radv_device *device,
struct radv_shader_variant *variant);
bool
radv_lower_indirect_derefs(struct nir_shader *nir,
struct radv_physical_device *device);
const char *
radv_get_shader_name(struct radv_shader_variant *var, gl_shader_stage stage);