diff options
Diffstat (limited to 'src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp')
| -rw-r--r-- | src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 18 |
1 files changed, 16 insertions, 2 deletions
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp index 2f7cc206b84..5b4a98d25cb 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp @@ -191,9 +191,17 @@ void LoadPropagation::checkSwapSrc01(Instruction *insn) { const Target *targ = prog->getTarget(); - if (!targ->getOpInfo(insn).commutative) - if (insn->op != OP_SET && insn->op != OP_SLCT && insn->op != OP_SUB) + if (!targ->getOpInfo(insn).commutative) { + if (insn->op != OP_SET && insn->op != OP_SLCT && + insn->op != OP_SUB && insn->op != OP_XMAD) return; + // XMAD is only commutative if both the CBCC and MRG flags are not set. + if (insn->op == OP_XMAD && + (insn->subOp & NV50_IR_SUBOP_XMAD_CMODE_MASK) == NV50_IR_SUBOP_XMAD_CBCC) + return; + if (insn->op == OP_XMAD && (insn->subOp & NV50_IR_SUBOP_XMAD_MRG)) + return; + } if (insn->src(1).getFile() != FILE_GPR) return; // This is the special OP_SET used for alphatesting, we can't reverse its @@ -236,6 +244,12 @@ LoadPropagation::checkSwapSrc01(Instruction *insn) 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); + } else + if (insn->op == OP_XMAD) { + // swap h1 flags + uint16_t h1 = (insn->subOp >> 1 & NV50_IR_SUBOP_XMAD_H1(0)) | + (insn->subOp << 1 & NV50_IR_SUBOP_XMAD_H1(1)); + insn->subOp = (insn->subOp & ~NV50_IR_SUBOP_XMAD_H1_MASK) | h1; } } |