intel/compiler: Pass shader_stats for each SIMD mode
Passing shader_stats to the fs_generator constructor means that the SIMD8 shader stats from the visitor (such as the scheduler mode) will be reported out for the SIMD16/SIMD32 versions as well. As you can see, we are now passing 'shader_stats' and 'stats' to generate_code(), which is obviously odd looking. Ian rebased and committed an old patch of mine which added the shader_stats struct on July 30 in commitdabb5d4bee
(i965/fs: Add a shader_stats struct.) and shortly after on August 12 Jason added the brw_compile_stats struct in commit134607760a
(intel/compiler: Fill a compiler statistics struct). I'd like to combine the two, but I'm not sure how. shader_stats is an input to generate_code() while brw_compile_stats is an output and is only used by the Vulkan driver. Leave it as is for now... Reviewed-by: Ian Romanick <ian.d.romanick@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4093>
This commit is contained in:
@@ -8601,6 +8601,7 @@ brw_compile_fs(const struct brw_compiler *compiler, void *log_data,
|
||||
brw_compute_flat_inputs(prog_data, shader);
|
||||
|
||||
cfg_t *simd8_cfg = NULL, *simd16_cfg = NULL, *simd32_cfg = NULL;
|
||||
struct shader_stats v8_shader_stats, v16_shader_stats, v32_shader_stats;
|
||||
|
||||
fs_visitor v8(compiler, log_data, mem_ctx, &key->base,
|
||||
&prog_data->base, shader, 8,
|
||||
@@ -8612,6 +8613,7 @@ brw_compile_fs(const struct brw_compiler *compiler, void *log_data,
|
||||
return NULL;
|
||||
} else if (likely(!(INTEL_DEBUG & DEBUG_NO8))) {
|
||||
simd8_cfg = v8.cfg;
|
||||
v8_shader_stats = v8.shader_stats;
|
||||
prog_data->base.dispatch_grf_start_reg = v8.payload.num_regs;
|
||||
prog_data->reg_blocks_8 = brw_register_blocks(v8.grf_used);
|
||||
}
|
||||
@@ -8639,6 +8641,7 @@ brw_compile_fs(const struct brw_compiler *compiler, void *log_data,
|
||||
v16.fail_msg);
|
||||
} else {
|
||||
simd16_cfg = v16.cfg;
|
||||
v16_shader_stats = v16.shader_stats;
|
||||
prog_data->dispatch_grf_start_reg_16 = v16.payload.num_regs;
|
||||
prog_data->reg_blocks_16 = brw_register_blocks(v16.grf_used);
|
||||
}
|
||||
@@ -8659,6 +8662,7 @@ brw_compile_fs(const struct brw_compiler *compiler, void *log_data,
|
||||
v32.fail_msg);
|
||||
} else {
|
||||
simd32_cfg = v32.cfg;
|
||||
v32_shader_stats = v32.shader_stats;
|
||||
prog_data->dispatch_grf_start_reg_32 = v32.payload.num_regs;
|
||||
prog_data->reg_blocks_32 = brw_register_blocks(v32.grf_used);
|
||||
}
|
||||
@@ -8712,8 +8716,7 @@ brw_compile_fs(const struct brw_compiler *compiler, void *log_data,
|
||||
}
|
||||
|
||||
fs_generator g(compiler, log_data, mem_ctx, &prog_data->base,
|
||||
v8.shader_stats, v8.runtime_check_aads_emit,
|
||||
MESA_SHADER_FRAGMENT);
|
||||
v8.runtime_check_aads_emit, MESA_SHADER_FRAGMENT);
|
||||
|
||||
if (unlikely(INTEL_DEBUG & DEBUG_WM)) {
|
||||
g.enable_debug(ralloc_asprintf(mem_ctx, "%s fragment shader %s",
|
||||
@@ -8724,19 +8727,19 @@ brw_compile_fs(const struct brw_compiler *compiler, void *log_data,
|
||||
|
||||
if (simd8_cfg) {
|
||||
prog_data->dispatch_8 = true;
|
||||
g.generate_code(simd8_cfg, 8, stats);
|
||||
g.generate_code(simd8_cfg, 8, v8_shader_stats, stats);
|
||||
stats = stats ? stats + 1 : NULL;
|
||||
}
|
||||
|
||||
if (simd16_cfg) {
|
||||
prog_data->dispatch_16 = true;
|
||||
prog_data->prog_offset_16 = g.generate_code(simd16_cfg, 16, stats);
|
||||
prog_data->prog_offset_16 = g.generate_code(simd16_cfg, 16, v16_shader_stats, stats);
|
||||
stats = stats ? stats + 1 : NULL;
|
||||
}
|
||||
|
||||
if (simd32_cfg) {
|
||||
prog_data->dispatch_32 = true;
|
||||
prog_data->prog_offset_32 = g.generate_code(simd32_cfg, 32, stats);
|
||||
prog_data->prog_offset_32 = g.generate_code(simd32_cfg, 32, v32_shader_stats, stats);
|
||||
stats = stats ? stats + 1 : NULL;
|
||||
}
|
||||
|
||||
@@ -8979,8 +8982,7 @@ brw_compile_cs(const struct brw_compiler *compiler, void *log_data,
|
||||
*error_str = ralloc_strdup(mem_ctx, fail_msg);
|
||||
} else {
|
||||
fs_generator g(compiler, log_data, mem_ctx, &prog_data->base,
|
||||
v->shader_stats, v->runtime_check_aads_emit,
|
||||
MESA_SHADER_COMPUTE);
|
||||
v->runtime_check_aads_emit, MESA_SHADER_COMPUTE);
|
||||
if (INTEL_DEBUG & DEBUG_CS) {
|
||||
char *name = ralloc_asprintf(mem_ctx, "%s compute shader %s",
|
||||
src_shader->info.label ?
|
||||
@@ -8989,7 +8991,7 @@ brw_compile_cs(const struct brw_compiler *compiler, void *log_data,
|
||||
g.enable_debug(name);
|
||||
}
|
||||
|
||||
g.generate_code(v->cfg, prog_data->simd_size, stats);
|
||||
g.generate_code(v->cfg, prog_data->simd_size, v->shader_stats, stats);
|
||||
|
||||
ret = g.get_assembly();
|
||||
}
|
||||
|
@@ -467,13 +467,13 @@ public:
|
||||
fs_generator(const struct brw_compiler *compiler, void *log_data,
|
||||
void *mem_ctx,
|
||||
struct brw_stage_prog_data *prog_data,
|
||||
struct shader_stats shader_stats,
|
||||
bool runtime_check_aads_emit,
|
||||
gl_shader_stage stage);
|
||||
~fs_generator();
|
||||
|
||||
void enable_debug(const char *shader_name);
|
||||
int generate_code(const cfg_t *cfg, int dispatch_width,
|
||||
struct shader_stats shader_stats,
|
||||
struct brw_compile_stats *stats);
|
||||
const unsigned *get_assembly();
|
||||
|
||||
@@ -572,7 +572,6 @@ private:
|
||||
unsigned dispatch_width; /**< 8, 16 or 32 */
|
||||
|
||||
exec_list discard_halt_patches;
|
||||
struct shader_stats shader_stats;
|
||||
bool runtime_check_aads_emit;
|
||||
bool debug_flag;
|
||||
const char *shader_name;
|
||||
|
@@ -186,14 +186,12 @@ brw_reg_from_fs_reg(const struct gen_device_info *devinfo, fs_inst *inst,
|
||||
fs_generator::fs_generator(const struct brw_compiler *compiler, void *log_data,
|
||||
void *mem_ctx,
|
||||
struct brw_stage_prog_data *prog_data,
|
||||
struct shader_stats shader_stats,
|
||||
bool runtime_check_aads_emit,
|
||||
gl_shader_stage stage)
|
||||
|
||||
: compiler(compiler), log_data(log_data),
|
||||
devinfo(compiler->devinfo),
|
||||
prog_data(prog_data),
|
||||
shader_stats(shader_stats),
|
||||
runtime_check_aads_emit(runtime_check_aads_emit), debug_flag(false),
|
||||
stage(stage), mem_ctx(mem_ctx)
|
||||
{
|
||||
@@ -1698,6 +1696,7 @@ fs_generator::enable_debug(const char *shader_name)
|
||||
|
||||
int
|
||||
fs_generator::generate_code(const cfg_t *cfg, int dispatch_width,
|
||||
struct shader_stats shader_stats,
|
||||
struct brw_compile_stats *stats)
|
||||
{
|
||||
/* align to 64 byte boundary. */
|
||||
|
@@ -1361,8 +1361,7 @@ brw_compile_tes(const struct brw_compiler *compiler,
|
||||
prog_data->base.dispatch_mode = DISPATCH_MODE_SIMD8;
|
||||
|
||||
fs_generator g(compiler, log_data, mem_ctx,
|
||||
&prog_data->base.base, v.shader_stats, false,
|
||||
MESA_SHADER_TESS_EVAL);
|
||||
&prog_data->base.base, false, MESA_SHADER_TESS_EVAL);
|
||||
if (unlikely(INTEL_DEBUG & DEBUG_TES)) {
|
||||
g.enable_debug(ralloc_asprintf(mem_ctx,
|
||||
"%s tessellation evaluation shader %s",
|
||||
@@ -1371,7 +1370,7 @@ brw_compile_tes(const struct brw_compiler *compiler,
|
||||
nir->info.name));
|
||||
}
|
||||
|
||||
g.generate_code(v.cfg, 8, stats);
|
||||
g.generate_code(v.cfg, 8, v.shader_stats, stats);
|
||||
|
||||
assembly = g.get_assembly();
|
||||
} else {
|
||||
|
@@ -2988,8 +2988,8 @@ brw_compile_vs(const struct brw_compiler *compiler, void *log_data,
|
||||
prog_data->base.base.dispatch_grf_start_reg = v.payload.num_regs;
|
||||
|
||||
fs_generator g(compiler, log_data, mem_ctx,
|
||||
&prog_data->base.base, v.shader_stats,
|
||||
v.runtime_check_aads_emit, MESA_SHADER_VERTEX);
|
||||
&prog_data->base.base, v.runtime_check_aads_emit,
|
||||
MESA_SHADER_VERTEX);
|
||||
if (INTEL_DEBUG & DEBUG_VS) {
|
||||
const char *debug_name =
|
||||
ralloc_asprintf(mem_ctx, "%s vertex shader %s",
|
||||
@@ -2999,7 +2999,7 @@ brw_compile_vs(const struct brw_compiler *compiler, void *log_data,
|
||||
|
||||
g.enable_debug(debug_name);
|
||||
}
|
||||
g.generate_code(v.cfg, 8, stats);
|
||||
g.generate_code(v.cfg, 8, v.shader_stats, stats);
|
||||
assembly = g.get_assembly();
|
||||
}
|
||||
|
||||
|
@@ -857,8 +857,7 @@ brw_compile_gs(const struct brw_compiler *compiler, void *log_data,
|
||||
prog_data->base.base.dispatch_grf_start_reg = v.payload.num_regs;
|
||||
|
||||
fs_generator g(compiler, log_data, mem_ctx,
|
||||
&prog_data->base.base, v.shader_stats,
|
||||
false, MESA_SHADER_GEOMETRY);
|
||||
&prog_data->base.base, false, MESA_SHADER_GEOMETRY);
|
||||
if (unlikely(INTEL_DEBUG & DEBUG_GS)) {
|
||||
const char *label =
|
||||
shader->info.label ? shader->info.label : "unnamed";
|
||||
@@ -866,7 +865,7 @@ brw_compile_gs(const struct brw_compiler *compiler, void *log_data,
|
||||
label, shader->info.name);
|
||||
g.enable_debug(name);
|
||||
}
|
||||
g.generate_code(v.cfg, 8, stats);
|
||||
g.generate_code(v.cfg, 8, v.shader_stats, stats);
|
||||
return g.get_assembly();
|
||||
}
|
||||
}
|
||||
|
@@ -441,8 +441,7 @@ brw_compile_tcs(const struct brw_compiler *compiler,
|
||||
prog_data->base.base.dispatch_grf_start_reg = v.payload.num_regs;
|
||||
|
||||
fs_generator g(compiler, log_data, mem_ctx,
|
||||
&prog_data->base.base, v.shader_stats, false,
|
||||
MESA_SHADER_TESS_CTRL);
|
||||
&prog_data->base.base, false, MESA_SHADER_TESS_CTRL);
|
||||
if (unlikely(INTEL_DEBUG & DEBUG_TCS)) {
|
||||
g.enable_debug(ralloc_asprintf(mem_ctx,
|
||||
"%s tessellation control shader %s",
|
||||
@@ -451,7 +450,7 @@ brw_compile_tcs(const struct brw_compiler *compiler,
|
||||
nir->info.name));
|
||||
}
|
||||
|
||||
g.generate_code(v.cfg, 8, stats);
|
||||
g.generate_code(v.cfg, 8, v.shader_stats, stats);
|
||||
|
||||
assembly = g.get_assembly();
|
||||
} else {
|
||||
|
Reference in New Issue
Block a user