radeonsi: compute how many input SGPRs and VGPRs shaders have

Prologs (shader binaries inserted before the API shader binary) need to
know this, so that they won't change the input registers unintentionally.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 422608eb4cee40f58909d877154ca4742dc4d906..1145f896a399a41c6e9d114235302b8b13714be2 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -3580,6 +3580,26 @@ static void declare_streamout_params(struct si_shader_context *ctx,
        }
 }
 
+static unsigned llvm_get_type_size(LLVMTypeRef type)
+{
+       LLVMTypeKind kind = LLVMGetTypeKind(type);
+
+       switch (kind) {
+       case LLVMIntegerTypeKind:
+               return LLVMGetIntTypeWidth(type) / 8;
+       case LLVMFloatTypeKind:
+               return 4;
+       case LLVMPointerTypeKind:
+               return 8;
+       case LLVMVectorTypeKind:
+               return LLVMGetVectorSize(type) *
+                      llvm_get_type_size(LLVMGetElementType(type));
+       default:
+               assert(0);
+               return 0;
+       }
+}
+
 static void create_function(struct si_shader_context *ctx)
 {
        struct lp_build_tgsi_context *bld_base = &ctx->radeon_bld.soa.bld_base;
@@ -3717,6 +3737,9 @@ static void create_function(struct si_shader_context *ctx)
        radeon_llvm_shader_type(ctx->radeon_bld.main_fn, ctx->type);
        ctx->return_value = LLVMGetUndef(ctx->radeon_bld.return_type);
 
+       shader->num_input_sgprs = 0;
+       shader->num_input_vgprs = 0;
+
        for (i = 0; i <= last_sgpr; ++i) {
                LLVMValueRef P = LLVMGetParam(ctx->radeon_bld.main_fn, i);
 
@@ -3726,8 +3749,17 @@ static void create_function(struct si_shader_context *ctx)
                        LLVMAddAttribute(P, LLVMByValAttribute);
                else
                        LLVMAddAttribute(P, LLVMInRegAttribute);
+
+               shader->num_input_sgprs += llvm_get_type_size(params[i]) / 4;
        }
 
+       /* Unused fragment shader inputs are eliminated by the compiler,
+        * so we don't know yet how many there will be.
+        */
+       if (ctx->type != TGSI_PROCESSOR_FRAGMENT)
+               for (; i < num_params; ++i)
+                       shader->num_input_vgprs += llvm_get_type_size(params[i]) / 4;
+
        if (bld_base->info &&
            (bld_base->info->opcode_count[TGSI_OPCODE_DDX] > 0 ||
             bld_base->info->opcode_count[TGSI_OPCODE_DDY] > 0 ||

diff --git a/src/gallium/drivers/radeonsi/si_shader.h b/src/gallium/drivers/radeonsi/si_shader.h
index dc75e0330e41517a42188d3f6281c4f3d1c5583c..131455b6d0fc9615492007c1a1005935e02523f4 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.h
+++ b/src/gallium/drivers/radeonsi/si_shader.h
@@ -279,6 +279,8 @@ struct si_shader {
        struct radeon_shader_binary     binary;
        struct si_shader_config         config;
 
+       ubyte                   num_input_sgprs;
+       ubyte                   num_input_vgprs;
        unsigned                vs_output_param_offset[PIPE_MAX_SHADER_OUTPUTS];
        bool                    uses_instanceid;
        unsigned                nr_pos_exports;