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

iris: Handle runtime-specified local memory size

Browse Source 
The value specified in pipe_compute_state is in addition to the implicit
value computed by NIR.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7047>
This commit is contained in:
Jason Ekstrand
2020-10-06 15:57:21 -05:00
parent d9adb55a4d
commit 67ee9c5f55
3 changed files with 11 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/gallium/drivers/iris/iris_context.h
View File

@@ -385,6 +385,9 @@ struct iris_uncompiled_shader {
/** Size (in bytes) of the kernel input data */
unsigned kernel_input_size;
/** Size (in bytes) of the local (shared) data passed as kernel inputs */
unsigned kernel_shared_size;
};
enum iris_surface_group {

1
src/gallium/drivers/iris/iris_program.c
View File

@@ -2405,6 +2405,7 @@ iris_create_compute_state(struct pipe_context *ctx,
struct iris_uncompiled_shader *ish =
iris_create_uncompiled_shader(ctx, nir, NULL);
ish->kernel_input_size = state->req_input_mem;
ish->kernel_shared_size = state->req_local_mem;
// XXX: disallow more than 64KB of shared variables

10
src/gallium/drivers/iris/iris_state.c
View File

@@ -4464,14 +4464,11 @@ iris_store_cs_state(struct iris_context *ice,
const struct gen_device_info *devinfo,
struct iris_compiled_shader *shader)
{
struct brw_stage_prog_data *prog_data = shader->prog_data;
struct brw_cs_prog_data *cs_prog_data = (void *) shader->prog_data;
void *map = shader->derived_data;
iris_pack_state(GENX(INTERFACE_DESCRIPTOR_DATA), map, desc) {
desc.ConstantURBEntryReadLength = cs_prog_data->push.per_thread.regs;
desc.SharedLocalMemorySize =
encode_slm_size(GEN_GEN, prog_data->total_shared);
desc.BarrierEnable = cs_prog_data->uses_barrier;
desc.CrossThreadConstantDataReadLength =
cs_prog_data->push.cross_thread.regs;
@@ -6652,6 +6649,8 @@ iris_upload_gpgpu_walker(struct iris_context *ice,
const struct gen_device_info *devinfo = &screen->devinfo;
struct iris_binder *binder = &ice->state.binder;
struct iris_shader_state *shs = &ice->state.shaders[MESA_SHADER_COMPUTE];
struct iris_uncompiled_shader *ish =
ice->shaders.uncompiled[MESA_SHADER_COMPUTE];
struct iris_compiled_shader *shader =
ice->shaders.prog[MESA_SHADER_COMPUTE];
struct brw_stage_prog_data *prog_data = shader->prog_data;
@@ -6741,7 +6740,12 @@ iris_upload_gpgpu_walker(struct iris_context *ice,
IRIS_STAGE_DIRTY_CS)) {
uint32_t desc[GENX(INTERFACE_DESCRIPTOR_DATA_length)];
unsigned slm_size = prog_data->total_shared;
if (ish->kernel_shared_size)
slm_size = ALIGN(slm_size, 8) + ish->kernel_shared_size;
iris_pack_state(GENX(INTERFACE_DESCRIPTOR_DATA), desc, idd) {
idd.SharedLocalMemorySize = encode_slm_size(GEN_GEN, slm_size);
idd.KernelStartPointer =
KSP(shader) + brw_cs_prog_data_prog_offset(cs_prog_data, simd_size);
idd.SamplerStatePointer = shs->sampler_table.offset;