From 691cc0e3a8716a2cdb7271765cd7d4c7465066eb Mon Sep 17 00:00:00 2001 From: Bryan Cain Date: Wed, 17 Aug 2011 14:35:35 -0500 Subject: glsl_to_tgsi: implement ir_binop_logic_or using an add w/saturate or add w/SLT Logical-or is implemented using addition (followed by clamping to [0,1]) on values of 0.0 and 1.0. Replacing the logical-or operators with addition gives a + b which has a result on the range [0, 2]. Previously a SNE instruction was used to clamp the resulting logic value to [0,1]. In a fragment shader, using a saturate on the add has the same effect. Adding the saturate to the add is free, so (at least) one instruction is saved. In a vertex shader, using an SLT on the negation of the add result has the same effect. Many older shader architectures do not support the SNE instruction. It must be emulated using two SLT instructions and an ADD. On these architectures, the single SLT saves two instructions. Note that SNE is still used when integers are used for boolean values, since there is no such thing as an integer saturate, and older shader architectures without SNE don't support integers. This is a port of commit 41f8ffe5e07c to glsl_to_tgsi with integer support added. --- src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 31 ++++++++++++++++++++++++++---- 1 file changed, 27 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 73a647efe34..5f4aef16b66 100644 --- a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp +++ b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp @@ -1493,11 +1493,34 @@ glsl_to_tgsi_visitor::visit(ir_expression *ir) emit(ir, TGSI_OPCODE_SNE, result_dst, op[0], op[1]); break; - case ir_binop_logic_or: - /* This could be a saturated add and skip the SNE. */ - emit(ir, TGSI_OPCODE_ADD, result_dst, op[0], op[1]); - emit(ir, TGSI_OPCODE_SNE, result_dst, result_src, st_src_reg_for_float(0.0)); + case ir_binop_logic_or: { + /* After the addition, the value will be an integer on the + * range [0,2]. Zero stays zero, and positive values become 1.0. + */ + glsl_to_tgsi_instruction *add = + emit(ir, TGSI_OPCODE_ADD, result_dst, op[0], op[1]); + 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 if floats are being used as boolean values. + */ + add->saturate = true; + } else if (result_dst.type == GLSL_TYPE_FLOAT) { + /* Negating the result of the addition gives values on the range + * [-2, 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 an SNE on the result of the addition. Zero stays zero, + * 1 stays 1, and 2 becomes 1. + */ + emit(ir, TGSI_OPCODE_SNE, result_dst, result_src, st_src_reg_for_int(0)); + } break; + } case ir_binop_logic_and: /* the bool args are stored as float 0.0 or 1.0, so "mul" gives us "and". */ -- cgit v1.2.3