diff options
| author | Ilia Mirkin <imirkin@alum.mit.edu> | 2015-12-08 18:46:34 -0500 |
|---|---|---|
| committer | Ilia Mirkin <imirkin@alum.mit.edu> | 2015-12-08 23:15:29 -0500 |
| commit | 44260d908062a4771c30ab635dd527f4266dbaec (patch) | |
| tree | a03c655882e1ecf95d42b54bf7a5c16647304a21 | |
| parent | c1c1248b94e17a1a4fa0e6f353377efa99efe602 (diff) | |
| download | external_mesa3d-44260d908062a4771c30ab635dd527f4266dbaec.zip external_mesa3d-44260d908062a4771c30ab635dd527f4266dbaec.tar.gz external_mesa3d-44260d908062a4771c30ab635dd527f4266dbaec.tar.bz2 | |
nv50/ir: prefer to color mad def and src2 with the same color
This allows us to use the short encoding, and potentially fold
immediates in later on.
total instructions in shared programs : 6379731 -> 6367861 (-0.19%)
total gprs used in shared programs : 728502 -> 728683 (0.02%)
total local used in shared programs : 9904 -> 9904 (0.00%)
total bytes used in shared programs : 44661008 -> 44154976 (-1.13%)
local gpr inst bytes
helped 0 51 7267 20306
hurt 0 232 125 274
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
| -rw-r--r-- | src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp index a7d8177..b32bc13 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp @@ -1465,6 +1465,20 @@ GCRA::allocateRegisters(ArrayList& insns) if (lval) { nodes[i].init(regs, lval); RIG.insert(&nodes[i]); + + if (lval->inFile(FILE_GPR) && lval->defs.size() > 0 && + prog->getTarget()->getChipset() < 0xc0) { + Instruction *insn = lval->getInsn(); + if (insn->op == OP_MAD || insn->op == OP_SAD) + // Short encoding only possible if they're all GPRs, no need to + // affect them otherwise. + if (insn->flagsDef < 0 && + isFloatType(insn->dType) && + insn->src(0).getFile() == FILE_GPR && + insn->src(1).getFile() == FILE_GPR && + insn->src(2).getFile() == FILE_GPR) + nodes[i].addRegPreference(getNode(insn->getSrc(2)->asLValue())); + } } } |