From ae7eb93e6caaf2a75fdaab071c0e5e9883376a82 Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Sat, 13 Aug 2016 11:54:52 +0200 Subject: [PATCH] nvc0/ir: allow min/max instructions to be dual-issued in pairs changes for GpuTest /test=pixmark_piano /benchmark /no_scorebox /msaa=0 /benchmark_duration_ms=60000 /width=1024 /height=640: inst_executed: 1.03G inst_issued1: 614M -> 580M inst_issued2: 213M -> 230M score: 1021 -> 1030 Signed-off-by: Karol Herbst Reviewed-by: Ilia Mirkin --- .../drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp index 0cb21e8..f5981de 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp @@ -625,9 +625,19 @@ bool TargetNVC0::canDualIssue(const Instruction *a, const Instruction *b) const if (a->op == OP_MOV || b->op == OP_MOV) return true; if (clA == clB) { - // only F32 arith or integer additions - if (clA != OPCLASS_ARITH) + switch (clA) { + // there might be more + case OPCLASS_COMPARE: + if ((a->op == OP_MIN || a->op == OP_MAX) && + (b->op == OP_MIN || b->op == OP_MAX)) + break; + return false; + case OPCLASS_ARITH: + break; + default: return false; + } + // only F32 arith or integer additions return (a->dType == TYPE_F32 || a->op == OP_ADD || b->dType == TYPE_F32 || b->op == OP_ADD); } -- 2.7.4