From a43f68810a347f3e952a0bc401be6edb91e1baea Mon Sep 17 00:00:00 2001 From: Bryan Cain Date: Sat, 20 Aug 2011 13:26:12 -0500 Subject: [PATCH] glsl_to_tgsi: implement ir_unop_any using DP4 w/saturate or DP4 w/SLT This is a port of commit 92ca560d68e8 to glsl_to_tgsi, with integer support added. --- src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 32 +++++++++++++++++++--- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp index 62127afadde..f7d79e9f50c 100644 --- a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp +++ b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp @@ -1482,12 +1482,36 @@ glsl_to_tgsi_visitor::visit(ir_expression *ir) } break; - case ir_unop_any: + case ir_unop_any: { assert(ir->operands[0]->type->is_vector()); - emit_dp(ir, result_dst, op[0], op[0], - ir->operands[0]->type->vector_elements); - emit(ir, TGSI_OPCODE_SNE, result_dst, result_src, st_src_reg_for_float(0.0)); + + /* After the dot-product, the value will be an integer on the + * range [0,4]. Zero stays zero, and positive values become 1.0. + */ + glsl_to_tgsi_instruction *const dp = + emit_dp(ir, result_dst, op[0], op[0], + ir->operands[0]->type->vector_elements); + if (this->prog->Target == GL_FRAGMENT_PROGRAM_ARB && + result_dst.type == GLSL_TYPE_FLOAT) { + /* The clamping to [0,1] can be done for free in the fragment + * shader with a saturate. + */ + dp->saturate = true; + } else if (result_dst.type == GLSL_TYPE_FLOAT) { + /* Negating the result of the dot-product gives values on the range + * [-4, 0]. Zero stays zero, and negative values become 1.0. This + * is achieved using SLT. + */ + st_src_reg slt_src = result_src; + slt_src.negate = ~slt_src.negate; + emit(ir, TGSI_OPCODE_SLT, result_dst, slt_src, st_src_reg_for_float(0.0)); + } + else { + /* Use SNE 0 if integers are being used as boolean values. */ + emit(ir, TGSI_OPCODE_SNE, result_dst, result_src, st_src_reg_for_int(0)); + } break; + } case ir_binop_logic_xor: emit(ir, TGSI_OPCODE_SNE, result_dst, op[0], op[1]); -- 2.30.2