[Mesa-dev] [PATCH 1/6] nv50/ir: add LIMM form of mad to gk110

[Karol Herbst]

2016-10-08 18:54 GMT+02:00 Samuel Pitoiset <samuel.pitoiset at gmail.com>:
> Please, update the prefix.
>
> Also the same comment applies here, and I think the best way is to enable
> that PostRAConstantFoldingPass for nvc0+ in a separate patch at the end of
> that series. That way you won't break things and mupuf will appreciate. :)
>

I think you read the patches in the wrong order. The two first patches
are the changes in the emiter.

> On 10/08/2016 05:43 PM, Karol Herbst wrote:
>>
>> Signed-off-by: Karol Herbst <karolherbst at gmail.com>
>> ---
>>  .../drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp | 49
>> ++++++++++++++--------
>>  1 file changed, 32 insertions(+), 17 deletions(-)
>>
>> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
>> b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
>> index ce20ed3..5c28fd4 100644
>> --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
>> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
>> @@ -47,7 +47,7 @@ private:
>>  private:
>>     void emitForm_21(const Instruction *, uint32_t opc2, uint32_t opc1);
>>     void emitForm_C(const Instruction *, uint32_t opc, uint8_t ctg);
>> -   void emitForm_L(const Instruction *, uint32_t opc, uint8_t ctg,
>> Modifier);
>> +   void emitForm_L(const Instruction *, uint32_t opc, uint8_t ctg,
>> Modifier, int sCount = 3);
>>
>>     void emitPredicate(const Instruction *);
>>
>> @@ -364,7 +364,7 @@ CodeEmitterGK110::setImmediate32(const Instruction *i,
>> const int s,
>>
>>  void
>>  CodeEmitterGK110::emitForm_L(const Instruction *i, uint32_t opc, uint8_t
>> ctg,
>> -                             Modifier mod)
>> +                             Modifier mod, int sCount)
>>  {
>>     code[0] = ctg;
>>     code[1] = opc << 20;
>> @@ -373,7 +373,7 @@ CodeEmitterGK110::emitForm_L(const Instruction *i,
>> uint32_t opc, uint8_t ctg,
>>
>>     defId(i->def(0), 2);
>>
>> -   for (int s = 0; s < 3 && i->srcExists(s); ++s) {
>> +   for (int s = 0; s < sCount && i->srcExists(s); ++s) {
>>        switch (i->src(s).getFile()) {
>>        case FILE_GPR:
>>           srcId(i->src(s), s ? 42 : 10);
>> @@ -486,25 +486,40 @@ CodeEmitterGK110::emitNOP(const Instruction *i)
>>  void
>>  CodeEmitterGK110::emitFMAD(const Instruction *i)
>>  {
>> -   assert(!isLIMM(i->src(1), TYPE_F32));
>> +   bool neg1 = (i->src(0).mod ^ i->src(1).mod).neg();
>>
>> -   emitForm_21(i, 0x0c0, 0x940);
>> +   if (isLIMM(i->src(1), TYPE_F32)) {
>> +      // last source is dst, so force 2 sources
>> +      emitForm_L(i, 0x600, 0x0, Modifier(0), 2);
>>
>> -   NEG_(34, 2);
>> -   SAT_(35);
>> -   RND_(36, F);
>> -   FTZ_(38);
>> -   DNZ_(39);
>> +      SAT_(3a);
>> +      NEG_(3b, 0);
>> +      NEG_(3c, 2);
>>
>> -   bool neg1 = (i->src(0).mod ^ i->src(1).mod).neg();
>> +      // neg 1
>> +      if (neg1) {
>> +         code[1] |= 1 << 27;
>> +      }
>> +   } else {
>> +      emitForm_21(i, 0x0c0, 0x940);
>>
>> -   if (code[0] & 0x1) {
>> -      if (neg1)
>> -         code[1] ^= 1 << 27;
>> -   } else
>> -   if (neg1) {
>> -      code[1] |= 1 << 19;
>> +      NEG_(33, 0);
>> +      NEG_(34, 2);
>> +      SAT_(35);
>> +      RND_(36, F);
>> +
>> +      // neg 1
>> +      if (code[0] & 0x1) {
>> +         if (neg1)
>> +            code[1] ^= 1 << 27;
>> +      } else
>> +      if (neg1) {
>> +         code[1] |= 1 << 19;
>> +      }
>>     }
>> +
>> +   FTZ_(38);
>> +   DNZ_(39);
>>  }
>>
>>  void
>>
>