From 3f5cf8c488bfc401d1d5503c1ec61874d7c1477d Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Wed, 20 Jul 2016 20:07:35 +0200 Subject: nv50/ir: allow to swap sources for OP_SUB This allows the load-propagation pass to swap the sources in presence of immediate values. Maxwell (GM107): total instructions in shared programs :1928187 -> 1927634 (-0.03%) total gprs used in shared programs :330741 -> 330154 (-0.18%) total local used in shared programs :28032 -> 28032 (0.00%) local gpr inst bytes helped 0 271 425 425 hurt 0 0 194 194 Fermi (GF114): total instructions in shared programs :2334474 -> 2333829 (-0.03%) total gprs used in shared programs :380934 -> 380215 (-0.19%) total local used in shared programs :33304 -> 33264 (-0.12%) local gpr inst bytes helped 5 314 521 521 hurt 0 4 195 195 No regressions on GM107 and GF114 with full piglit. Signed-off-by: Samuel Pitoiset Reviewed-by: Ilia Mirkin --- src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'src/gallium/drivers') diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp index 3fc1abf18cd..a9172f834b2 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp @@ -192,7 +192,7 @@ LoadPropagation::checkSwapSrc01(Instruction *insn) { const Target *targ = prog->getTarget(); if (!targ->getOpInfo(insn).commutative) - if (insn->op != OP_SET && insn->op != OP_SLCT) + if (insn->op != OP_SET && insn->op != OP_SLCT && insn->op != OP_SUB) return; if (insn->src(1).getFile() != FILE_GPR) return; @@ -232,6 +232,11 @@ LoadPropagation::checkSwapSrc01(Instruction *insn) else if (insn->op == OP_SLCT) insn->asCmp()->setCond = inverseCondCode(insn->asCmp()->setCond); + else + if (insn->op == OP_SUB) { + insn->src(0).mod = insn->src(0).mod ^ Modifier(NV50_IR_MOD_NEG); + insn->src(1).mod = insn->src(1).mod ^ Modifier(NV50_IR_MOD_NEG); + } } bool -- cgit v1.2.3