nv50/ir: Add support for MAD 4-byte opcode

Add emission rules for negative and saturate flags for MAD 4-byte opcodes,
and get rid of some of the constraints. Obviously tested with a wide variety
of shaders.

V2: Document MAD as supported short form
V3: Split up IMM from short-form modifiers

Signed-off-by: Roy Spliet <rspliet@eclipso.eu>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp
index 20773884ad395d417393d7685c8c4fb9ae9757d7..23e4babfed02dce8a8aba9ce20320823297dccfd 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp
@@ -941,7 +941,10 @@ CodeEmitterNV50::emitFMAD(const Instruction *i)
 
    if (i->encSize == 4) {
       emitForm_MUL(i);
-      assert(!neg_mul && !neg_add);
+      code[0] |= neg_mul << 15;
+      code[0] |= neg_add << 22;
+      if (i->saturate)
+         code[0] |= 1 << 8;
    } else {
       code[1]  = neg_mul << 26;
       code[1] |= neg_add << 27;
@@ -1931,11 +1934,6 @@ CodeEmitterNV50::getMinEncodingSize(const Instruction *i) const
 
    // check constraints on short MAD
    if (info.srcNr >= 2 && i->srcExists(2)) {
-      if (i->saturate || i->src(2).mod)
-         return 8;
-      if ((i->src(0).mod ^ i->src(1).mod) ||
-          (i->src(0).mod | i->src(1).mod).abs())
-         return 8;
       if (!i->defExists(0) ||
           i->def(0).rep()->reg.data.id != i->src(2).rep()->reg.data.id)
          return 8;

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
index 48f996b3d22a25735052a8ce1f39d116c187cfc1..178a1671c3f35213c2d5187391029059b3321c87 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
@@ -117,8 +117,8 @@ void TargetNV50::initOpInfo()
    };
    static const uint32_t shortForm[(OP_LAST + 31) / 32] =
    {
-      // MOV,ADD,SUB,MUL,SAD,L/PINTERP,RCP,TEX,TXF
-      0x00010e40, 0x00000040, 0x00000498, 0x00000000
+      // MOV,ADD,SUB,MUL,MAD,SAD,L/PINTERP,RCP,TEX,TXF
+      0x00014e40, 0x00000040, 0x00000498, 0x00000000
    };
    static const operation noDestList[] =
    {