diff options
-rw-r--r-- | src/mesa/drivers/dri/i965/brw_context.c | 46 | ||||
-rw-r--r-- | src/mesa/drivers/dri/i965/brw_context.h | 1 | ||||
-rw-r--r-- | src/mesa/drivers/dri/i965/brw_shader.cpp | 50 | ||||
-rw-r--r-- | src/mesa/drivers/dri/i965/brw_shader.h | 3 | ||||
-rw-r--r-- | src/mesa/drivers/dri/i965/brw_vec4.cpp | 2 | ||||
-rw-r--r-- | src/mesa/drivers/dri/i965/intel_screen.c | 1 |
6 files changed, 57 insertions, 46 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c index c0097df3e97..cf408830620 100644 --- a/src/mesa/drivers/dri/i965/brw_context.c +++ b/src/mesa/drivers/dri/i965/brw_context.c @@ -50,6 +50,7 @@ #include "brw_context.h" #include "brw_defines.h" +#include "brw_shader.h" #include "brw_draw.h" #include "brw_state.h" @@ -68,8 +69,6 @@ #include "tnl/t_pipeline.h" #include "util/ralloc.h" -#include "glsl/nir/nir.h" - /*************************************** * Mesa's Driver Functions ***************************************/ @@ -558,48 +557,12 @@ brw_initialize_context_constants(struct brw_context *brw) ctx->Const.Program[MESA_SHADER_FRAGMENT].MaxInputComponents = 128; } - static const nir_shader_compiler_options nir_options = { - .native_integers = true, - /* In order to help allow for better CSE at the NIR level we tell NIR - * to split all ffma instructions during opt_algebraic and we then - * re-combine them as a later step. - */ - .lower_ffma = true, - .lower_sub = true, - }; - /* We want the GLSL compiler to emit code that uses condition codes */ for (int i = 0; i < MESA_SHADER_STAGES; i++) { - ctx->Const.ShaderCompilerOptions[i].MaxIfDepth = brw->gen < 6 ? 16 : UINT_MAX; - ctx->Const.ShaderCompilerOptions[i].EmitCondCodes = true; - ctx->Const.ShaderCompilerOptions[i].EmitNoNoise = true; - ctx->Const.ShaderCompilerOptions[i].EmitNoMainReturn = true; - ctx->Const.ShaderCompilerOptions[i].EmitNoIndirectInput = true; - ctx->Const.ShaderCompilerOptions[i].EmitNoIndirectOutput = - (i == MESA_SHADER_FRAGMENT); - ctx->Const.ShaderCompilerOptions[i].EmitNoIndirectTemp = - (i == MESA_SHADER_FRAGMENT); - ctx->Const.ShaderCompilerOptions[i].EmitNoIndirectUniform = false; - ctx->Const.ShaderCompilerOptions[i].LowerClipDistance = true; + ctx->Const.ShaderCompilerOptions[i] = + brw->intelScreen->compiler->glsl_compiler_options[i]; } - ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].OptimizeForAOS = true; - ctx->Const.ShaderCompilerOptions[MESA_SHADER_GEOMETRY].OptimizeForAOS = true; - - if (brw->scalar_vs) { - /* If we're using the scalar backend for vertex shaders, we need to - * configure these accordingly. - */ - ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].EmitNoIndirectOutput = true; - ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].EmitNoIndirectTemp = true; - ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].OptimizeForAOS = false; - - ctx->Const.ShaderCompilerOptions[MESA_SHADER_VERTEX].NirOptions = &nir_options; - } - - ctx->Const.ShaderCompilerOptions[MESA_SHADER_FRAGMENT].NirOptions = &nir_options; - ctx->Const.ShaderCompilerOptions[MESA_SHADER_COMPUTE].NirOptions = &nir_options; - /* ARB_viewport_array */ if (brw->gen >= 6 && ctx->API == API_OPENGL_CORE) { ctx->Const.MaxViewports = GEN6_NUM_VIEWPORTS; @@ -826,9 +789,6 @@ brwCreateContext(gl_api api, if (INTEL_DEBUG & DEBUG_PERF) brw->perf_debug = true; - if (brw->gen >= 8 && !(INTEL_DEBUG & DEBUG_VEC4VS)) - brw->scalar_vs = true; - brw_initialize_context_constants(brw); ctx->Const.ResetStrategy = notify_reset diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h index 58119ee5c5e..d8fcfffcd10 100644 --- a/src/mesa/drivers/dri/i965/brw_context.h +++ b/src/mesa/drivers/dri/i965/brw_context.h @@ -1137,7 +1137,6 @@ struct brw_context bool has_pln; bool no_simd8; bool use_rep_send; - bool scalar_vs; /** * Some versions of Gen hardware don't do centroid interpolation correctly diff --git a/src/mesa/drivers/dri/i965/brw_shader.cpp b/src/mesa/drivers/dri/i965/brw_shader.cpp index 42d6236e6fd..6e6a2580d1d 100644 --- a/src/mesa/drivers/dri/i965/brw_shader.cpp +++ b/src/mesa/drivers/dri/i965/brw_shader.cpp @@ -84,6 +84,54 @@ brw_compiler_create(void *mem_ctx, const struct brw_device_info *devinfo) brw_fs_alloc_reg_sets(compiler); brw_vec4_alloc_reg_set(compiler); + if (devinfo->gen >= 8 && !(INTEL_DEBUG & DEBUG_VEC4VS)) + compiler->scalar_vs = true; + + nir_shader_compiler_options *nir_options = + rzalloc(compiler, nir_shader_compiler_options); + nir_options->native_integers = true; + /* In order to help allow for better CSE at the NIR level we tell NIR + * to split all ffma instructions during opt_algebraic and we then + * re-combine them as a later step. + */ + nir_options->lower_ffma = true; + nir_options->lower_sub = true; + + /* We want the GLSL compiler to emit code that uses condition codes */ + for (int i = 0; i < MESA_SHADER_STAGES; i++) { + compiler->glsl_compiler_options[i].MaxUnrollIterations = 32; + compiler->glsl_compiler_options[i].MaxIfDepth = + devinfo->gen < 6 ? 16 : UINT_MAX; + + compiler->glsl_compiler_options[i].EmitCondCodes = true; + compiler->glsl_compiler_options[i].EmitNoNoise = true; + compiler->glsl_compiler_options[i].EmitNoMainReturn = true; + compiler->glsl_compiler_options[i].EmitNoIndirectInput = true; + compiler->glsl_compiler_options[i].EmitNoIndirectOutput = + (i == MESA_SHADER_FRAGMENT); + compiler->glsl_compiler_options[i].EmitNoIndirectTemp = + (i == MESA_SHADER_FRAGMENT); + compiler->glsl_compiler_options[i].EmitNoIndirectUniform = false; + compiler->glsl_compiler_options[i].LowerClipDistance = true; + } + + compiler->glsl_compiler_options[MESA_SHADER_VERTEX].OptimizeForAOS = true; + compiler->glsl_compiler_options[MESA_SHADER_GEOMETRY].OptimizeForAOS = true; + + if (compiler->scalar_vs) { + /* If we're using the scalar backend for vertex shaders, we need to + * configure these accordingly. + */ + compiler->glsl_compiler_options[MESA_SHADER_VERTEX].EmitNoIndirectOutput = true; + compiler->glsl_compiler_options[MESA_SHADER_VERTEX].EmitNoIndirectTemp = true; + compiler->glsl_compiler_options[MESA_SHADER_VERTEX].OptimizeForAOS = false; + + compiler->glsl_compiler_options[MESA_SHADER_VERTEX].NirOptions = nir_options; + } + + compiler->glsl_compiler_options[MESA_SHADER_FRAGMENT].NirOptions = nir_options; + compiler->glsl_compiler_options[MESA_SHADER_COMPUTE].NirOptions = nir_options; + return compiler; } @@ -139,7 +187,7 @@ is_scalar_shader_stage(struct brw_context *brw, int stage) case MESA_SHADER_FRAGMENT: return true; case MESA_SHADER_VERTEX: - return brw->scalar_vs; + return brw->intelScreen->compiler->scalar_vs; default: return false; } diff --git a/src/mesa/drivers/dri/i965/brw_shader.h b/src/mesa/drivers/dri/i965/brw_shader.h index fe510e7f7c4..ac4df738009 100644 --- a/src/mesa/drivers/dri/i965/brw_shader.h +++ b/src/mesa/drivers/dri/i965/brw_shader.h @@ -89,6 +89,9 @@ struct brw_compiler { void (*shader_debug_log)(void *, const char *str, ...) PRINTFLIKE(2, 3); void (*shader_perf_log)(void *, const char *str, ...) PRINTFLIKE(2, 3); + + bool scalar_vs; + struct gl_shader_compiler_options glsl_compiler_options[MESA_SHADER_STAGES]; }; enum PACKED register_file { diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp index 572bc174986..82f055f229e 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp @@ -1882,7 +1882,7 @@ brw_vs_emit(struct brw_context *brw, if (unlikely(INTEL_DEBUG & DEBUG_VS)) brw_dump_ir("vertex", prog, &shader->base, &c->vp->program.Base); - if (brw->scalar_vs) { + if (brw->intelScreen->compiler->scalar_vs) { if (!c->vp->program.Base.nir) { /* Normally we generate NIR in LinkShader() or * ProgramStringNotify(), but Mesa's fixed-function vertex program diff --git a/src/mesa/drivers/dri/i965/intel_screen.c b/src/mesa/drivers/dri/i965/intel_screen.c index 3ba75d8278b..f9398d7859e 100644 --- a/src/mesa/drivers/dri/i965/intel_screen.c +++ b/src/mesa/drivers/dri/i965/intel_screen.c @@ -39,6 +39,7 @@ #include "swrast/s_renderbuffer.h" #include "util/ralloc.h" #include "brw_shader.h" +#include "glsl/nir/nir.h" #include "utils.h" #include "xmlpool.h" |