From 6dc6e6e0d979aa666e2934ae40477195e4d37ceb Mon Sep 17 00:00:00 2001 From: Kenneth Graunke Date: Wed, 15 Oct 2014 18:57:07 -0700 Subject: [PATCH] i965/vec4: Generate better code for ir_triop_csel. Previously, we generated an extra CMP instruction: cmp.ge.f0(8) g6<1>D g1<0,4,1>F 0F cmp.nz.f0(8) null g6<4,4,1>D 0D (+f0) sel(8) g5<1>F g1.4<0,4,1>F g2<0,4,1>F The first operand is always a boolean, and we want to predicate the SEL on that. Rather than producing a boolean value and comparing it against zero, we can just produce a condition code in the flag register. Now we generate: cmp.ge.f0(8) null g1<0,4,1>F 0F (+f0) sel(8) g5<1>F g1.4<0,4,1>F g2<0,4,1>F No difference in shader-db. v2: Remember to delete the old code (thanks Matt). Signed-off-by: Kenneth Graunke Reviewed-by: Matt Turner --- src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp index d0587cd5f62..b46879b7beb 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp @@ -1277,6 +1277,20 @@ vec4_visitor::visit(ir_expression *ir) dst_reg result_dst(this, ir->type); src_reg result_src(result_dst); + if (ir->operation == ir_triop_csel) { + ir->operands[1]->accept(this); + op[1] = this->result; + ir->operands[2]->accept(this); + op[2] = this->result; + + enum brw_predicate predicate; + emit_bool_to_cond_code(ir->operands[0], &predicate); + inst = emit(BRW_OPCODE_SEL, result_dst, op[1], op[2]); + inst->predicate = predicate; + this->result = result_src; + return; + } + for (operand = 0; operand < ir->get_num_operands(); operand++) { this->result.file = BAD_FILE; ir->operands[operand]->accept(this); @@ -1780,9 +1794,7 @@ vec4_visitor::visit(ir_expression *ir) break; case ir_triop_csel: - emit(CMP(dst_null_d(), op[0], src_reg(0), BRW_CONDITIONAL_NZ)); - inst = emit(BRW_OPCODE_SEL, result_dst, op[1], op[2]); - inst->predicate = BRW_PREDICATE_NORMAL; + unreachable("already handled above"); break; case ir_triop_bfi: -- 2.30.2