radeonsi: prepare depth export registers at compile time

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 3ed4ad2..5f4f1bf 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -1413,6 +1413,7 @@ static void si_llvm_emit_fs_epilogue(struct lp_build_tgsi_context * bld_base)
                        out_ptr = si_shader_ctx->radeon_bld.soa.outputs[depth_index][2];
                        args[5] = LLVMBuildLoad(base->gallivm->builder, out_ptr, "");
                        mask |= 0x1;
+                       si_shader_ctx->shader->db_shader_control |= S_02880C_Z_EXPORT_ENABLE(1);
                }
 
                if (stencil_index >= 0) {
@@ -1422,8 +1423,15 @@ static void si_llvm_emit_fs_epilogue(struct lp_build_tgsi_context * bld_base)
                         * breaks some stencil piglit tests
                         */
                        mask |= 0x3;
+                       si_shader_ctx->shader->db_shader_control |=
+                               S_02880C_STENCIL_TEST_VAL_EXPORT_ENABLE(1);
                }
 
+               if (stencil_index >= 0)
+                       si_shader_ctx->shader->spi_shader_z_format = V_028710_SPI_SHADER_32_GR;
+               else
+                       si_shader_ctx->shader->spi_shader_z_format = V_028710_SPI_SHADER_32_R;
+
                /* Specify which components to enable */
                args[0] = lp_build_const_int32(base->gallivm, mask);
 

diff --git a/src/gallium/drivers/radeonsi/si_shader.h b/src/gallium/drivers/radeonsi/si_shader.h
index d667baf..5e0db92 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.h
+++ b/src/gallium/drivers/radeonsi/si_shader.h
@@ -179,6 +179,8 @@ struct si_pipe_shader {
        unsigned                        lds_size;
        unsigned                        spi_ps_input_ena;
        unsigned                        spi_shader_col_format;
+       unsigned                        spi_shader_z_format;
+       unsigned                        db_shader_control;
        unsigned                        cb_shader_mask;
        bool                            cb0_is_integer;
        unsigned                        sprite_coord_enable;

diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index 46ab8de..52ecf26 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -233,7 +233,7 @@ static void si_pipe_shader_ps(struct pipe_context *ctx, struct si_pipe_shader *s
        struct si_pm4_state *pm4;
        unsigned i, spi_ps_in_control, db_shader_control;
        unsigned num_sgprs, num_user_sgprs;
-       unsigned spi_baryc_cntl = 0, spi_ps_input_ena, spi_shader_z_format;
+       unsigned spi_baryc_cntl = 0, spi_ps_input_ena;
        uint64_t va;
 
        si_pm4_delete_state(sctx, ps, shader->pm4);
@@ -264,12 +264,8 @@ static void si_pipe_shader_ps(struct pipe_context *ctx, struct si_pipe_shader *s
                }
        }
 
-       for (i = 0; i < shader->shader.noutput; i++) {
-               if (shader->shader.output[i].name == TGSI_SEMANTIC_POSITION)
-                       db_shader_control |= S_02880C_Z_EXPORT_ENABLE(1);
-               if (shader->shader.output[i].name == TGSI_SEMANTIC_STENCIL)
-                       db_shader_control |= S_02880C_STENCIL_TEST_VAL_EXPORT_ENABLE(1);
-       }
+       db_shader_control |= shader->db_shader_control;
+
        if (shader->shader.uses_kill || shader->key.ps.alpha_func != PIPE_FUNC_ALWAYS)
                db_shader_control |= S_02880C_KILL_ENABLE(1);
 
@@ -292,13 +288,7 @@ static void si_pipe_shader_ps(struct pipe_context *ctx, struct si_pipe_shader *s
        si_pm4_set_reg(pm4, R_0286D0_SPI_PS_INPUT_ADDR, spi_ps_input_ena);
        si_pm4_set_reg(pm4, R_0286D8_SPI_PS_IN_CONTROL, spi_ps_in_control);
 
-       if (G_02880C_STENCIL_TEST_VAL_EXPORT_ENABLE(db_shader_control))
-               spi_shader_z_format = V_028710_SPI_SHADER_32_GR;
-       else if (G_02880C_Z_EXPORT_ENABLE(db_shader_control))
-               spi_shader_z_format = V_028710_SPI_SHADER_32_R;
-       else
-               spi_shader_z_format = 0;
-       si_pm4_set_reg(pm4, R_028710_SPI_SHADER_Z_FORMAT, spi_shader_z_format);
+       si_pm4_set_reg(pm4, R_028710_SPI_SHADER_Z_FORMAT, shader->spi_shader_z_format);
        si_pm4_set_reg(pm4, R_028714_SPI_SHADER_COL_FORMAT,
                       shader->spi_shader_col_format);
        si_pm4_set_reg(pm4, R_02823C_CB_SHADER_MASK, shader->cb_shader_mask);