Signed-off-by: Rhys Perry <pendingchao...@gmail.com>
---
src/gallium/drivers/nouveau/codegen/nv50_ir.cpp | 3 ++-
src/gallium/drivers/nouveau/codegen/nv50_ir.h | 14 ++++++++++++
.../drivers/nouveau/codegen/nv50_ir_peephole.cpp | 12 +++++++++--
.../drivers/nouveau/codegen/nv50_ir_print.cpp | 20 +++++++++++++++++
.../drivers/nouveau/codegen/nv50_ir_target.cpp | 7 +++---
.../nouveau/codegen/nv50_ir_target_gm107.cpp | 1 +
.../nouveau/codegen/nv50_ir_target_nv50.cpp | 5 +++--
.../nouveau/codegen/nv50_ir_target_nvc0.cpp | 25 ++++++++++++++++++++--
8 files changed, 77 insertions(+), 10 deletions(-)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir.cpp
index 49425b98b9..99bf8de370 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir.cpp
@@ -53,7 +53,8 @@ Modifier Modifier::operator*(const Modifier m) const
b &= ~NV50_IR_MOD_NEG;
a = (this->bits ^ b) & (NV50_IR_MOD_NOT | NV50_IR_MOD_NEG);
- c = (this->bits | m.bits) & (NV50_IR_MOD_ABS | NV50_IR_MOD_SAT);
+ c = (this->bits | m.bits) & (NV50_IR_MOD_ABS | NV50_IR_MOD_SAT |
+ NV50_IR_MOD_H1 | NV50_IR_MOD_SEXT);
return Modifier(a | c);
}
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir.h
b/src/gallium/drivers/nouveau/codegen/nv50_ir.h
index f4f3c70888..4deaf09989 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir.h
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir.h
@@ -58,6 +58,7 @@ enum operation
OP_FMA,
OP_SAD, // abs(src0 - src1) + src2
OP_SHLADD,
+ OP_XMAD, // extended multiply-add (GM107+), does a lot of things
OP_ABS,
OP_NEG,
OP_NOT,
@@ -251,6 +252,13 @@ enum operation
#define NV50_IR_SUBOP_VOTE_ALL 0
#define NV50_IR_SUBOP_VOTE_ANY 1
#define NV50_IR_SUBOP_VOTE_UNI 2
+#define NV50_IR_SUBOP_XMAD_PSL (1 << 0)
+#define NV50_IR_SUBOP_XMAD_MRG (1 << 1)
+#define NV50_IR_SUBOP_XMAD_CLO (1 << 2)
+#define NV50_IR_SUBOP_XMAD_CHI (2 << 2)
+#define NV50_IR_SUBOP_XMAD_CSFU (3 << 2)
+#define NV50_IR_SUBOP_XMAD_CBCC (4 << 2)
+#define NV50_IR_SUBOP_XMAD_CMODE_MASK (0x7 << 2)
#define NV50_IR_SUBOP_MINMAX_LOW 1
#define NV50_IR_SUBOP_MINMAX_MED 2
@@ -527,6 +535,9 @@ struct Storage
#define NV50_IR_MOD_SAT (1 << 2)
#define NV50_IR_MOD_NOT (1 << 3)
#define NV50_IR_MOD_NEG_ABS (NV50_IR_MOD_NEG | NV50_IR_MOD_ABS)
+// modifiers only for XMAD
+#define NV50_IR_MOD_H1 (1 << 4)
+#define NV50_IR_MOD_SEXT (1 << 5)
#define NV50_IR_INTERP_MODE_MASK 0x3
#define NV50_IR_INTERP_LINEAR (0 << 0)
@@ -556,11 +567,14 @@ public:
inline Modifier operator&(const Modifier m) const { return bits & m.bits; }
inline Modifier operator|(const Modifier m) const { return bits | m.bits; }
inline Modifier operator^(const Modifier m) const { return bits ^ m.bits; }
+ inline Modifier operator~() const { return ~bits; }
operation getOp() const;
inline int neg() const { return (bits & NV50_IR_MOD_NEG) ? 1 : 0; }
inline int abs() const { return (bits & NV50_IR_MOD_ABS) ? 1 : 0; }
+ inline int h1() const { return (bits & NV50_IR_MOD_H1) ? 1 : 0; }
+ inline int sext() const { return (bits & NV50_IR_MOD_SEXT) ? 1 : 0; }
inline operator bool() const { return bits ? true : false; }
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 4d0589214d..a43b481a01 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -191,9 +191,16 @@ 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 & 0x1c) ==
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
@@ -488,6 +495,7 @@ Modifier::applyTo(ImmediateValue& imm) const
imm.reg.data.s32 = -imm.reg.data.s32;
if (bits & NV50_IR_MOD_NOT)
imm.reg.data.s32 = ~imm.reg.data.s32;
+ // NOTE: applying the h1 and sext modifiers is confusing and not very
useful
break;
case TYPE_F64:
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp
index cbb21f5f72..c4906c31a8 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp
@@ -86,6 +86,7 @@ const char *operationStr[OP_LAST + 1] =
"fma",
"sad",
"shladd",
+ "xmad",
"abs",
"neg",
"not",
@@ -239,6 +240,11 @@ static const char *barOpStr[] =
{
"sync", "arrive", "red and", "red or", "red popc"
};
+
+static const char *xmadOpCModeStr[] =
+{
+ "clo", "chi", "csfu", "cbcc"
+};
static const char *DataTypeStr[] =
{
@@ -387,6 +393,10 @@ int Modifier::print(char *buf, size_t size) const
SPACE_PRINT(pos > base && pos < size, "neg");
if (bits & NV50_IR_MOD_ABS)
SPACE_PRINT(pos > base && pos < size, "abs");
+ if (bits & NV50_IR_MOD_H1)
+ SPACE_PRINT(pos > base && pos < size, "h1");
+ if (bits & NV50_IR_MOD_SEXT)
+ SPACE_PRINT(pos > base && pos < size, "sext");
return pos;
}
@@ -624,6 +634,16 @@ void Instruction::print() const
if (subOp < ARRAY_SIZE(barOpStr))
PRINT("%s ", barOpStr[subOp]);
break;
+ case OP_XMAD: {
+ if (subOp & NV50_IR_SUBOP_XMAD_PSL)
+ PRINT("psl ");
+ if (subOp & NV50_IR_SUBOP_XMAD_MRG)
+ PRINT("mrg ");
+ unsigned cmode = (subOp >> 2) & 0x7;
+ if (cmode && cmode <= ARRAY_SIZE(xmadOpCModeStr))
+ PRINT("%s ", xmadOpCModeStr[cmode - 1]);
+ break;
+ }
default:
if (subOp)
PRINT("(SUBOP:%u) ", subOp);
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_target.cpp
index 298e7c6ef9..9193a01f18 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target.cpp
@@ -30,7 +30,8 @@ const uint8_t Target::operationSrcNr[] =
0, 0, // NOP, PHI
0, 0, 0, 0, // UNION, SPLIT, MERGE, CONSTRAINT
1, 1, 2, // MOV, LOAD, STORE
- 2, 2, 2, 2, 2, 3, 3, 3, 3, // ADD, SUB, MUL, DIV, MOD, MAD, FMA, SAD, SHLADD
+ 2, 2, 2, 2, 2, 3, 3, 3, // ADD, SUB, MUL, DIV, MOD, MAD, FMA, SAD
+ 3, 3, // SHLADD, XMAD
1, 1, 1, // ABS, NEG, NOT
2, 2, 2, 2, 2, // AND, OR, XOR, SHL, SHR
2, 2, 1, // MAX, MIN, SAT
@@ -70,10 +71,10 @@ const OpClass Target::operationClass[] =
OPCLASS_MOVE,
OPCLASS_LOAD,
OPCLASS_STORE,
- // ADD, SUB, MUL; DIV, MOD; MAD, FMA, SAD, SHLADD
+ // ADD, SUB, MUL; DIV, MOD; MAD, FMA, SAD, SHLADD, XMAD
OPCLASS_ARITH, OPCLASS_ARITH, OPCLASS_ARITH,
OPCLASS_ARITH, OPCLASS_ARITH,
- OPCLASS_ARITH, OPCLASS_ARITH, OPCLASS_ARITH, OPCLASS_ARITH,
+ OPCLASS_ARITH, OPCLASS_ARITH, OPCLASS_ARITH, OPCLASS_ARITH, OPCLASS_ARITH,
// ABS, NEG; NOT, AND, OR, XOR; SHL, SHR
OPCLASS_CONVERT, OPCLASS_CONVERT,
OPCLASS_LOGIC, OPCLASS_LOGIC, OPCLASS_LOGIC, OPCLASS_LOGIC,
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
index 04cbd402a1..24a1cbb8da 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_gm107.cpp
@@ -60,6 +60,7 @@ TargetGM107::isOpSupported(operation op, DataType ty) const
case OP_SQRT:
case OP_DIV:
case OP_MOD:
+ case OP_XMAD:
return false;
default:
break;
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 83b4102b0a..ef5f06442e 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
@@ -115,12 +115,12 @@ void TargetNV50::initOpInfo()
{
// ADD, MUL, MAD, FMA, AND, OR, XOR, MAX, MIN, SET_AND, SET_OR, SET_XOR,
// SET, SELP, SLCT
- 0x0ce0ca00, 0x0000007e, 0x00000000, 0x00000000
+ 0x19c0ca00, 0x000000fc, 0x00000000, 0x00000000
};
static const uint32_t shortForm[(OP_LAST + 31) / 32] =
{
// MOV, ADD, SUB, MUL, MAD, SAD, RCP, L/PINTERP, TEX, TXF
- 0x00014e40, 0x00000080, 0x00001260, 0x00000000
+ 0x00014e40, 0x00000100, 0x000024c0, 0x00000000
};
static const operation noDestList[] =
{
@@ -439,6 +439,7 @@ TargetNV50::isOpSupported(operation op, DataType ty) const
case OP_EXIT: // want exit modifier instead (on NOP if required)
case OP_MEMBAR:
case OP_SHLADD:
+ case OP_XMAD:
return false;
case OP_SAD:
return ty == TYPE_S32;
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 954aec0a2f..66efa0135f 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp
@@ -195,13 +195,13 @@ void TargetNVC0::initOpInfo()
{
// ADD, MUL, MAD, FMA, AND, OR, XOR, MAX, MIN, SET_AND, SET_OR, SET_XOR,
// SET, SELP, SLCT
- 0x0ce0ca00, 0x0000007e, 0x00000000, 0x00000000
+ 0x19c0ca00, 0x000000fc, 0x00000000, 0x00000000
};
static const uint32_t shortForm[(OP_LAST + 31) / 32] =
{
// ADD, MUL, MAD, FMA, AND, OR, XOR, MAX, MIN
- 0x0ce0ca00, 0x00000000, 0x00000000, 0x00000000
+ 0x19c0ca00, 0x00000000, 0x00000000, 0x00000000
};
static const operation noDest[] =
@@ -354,6 +354,18 @@ TargetNVC0::insnCanLoad(const Instruction *i, int s,
if ((i->op == OP_SHL || i->op == OP_SHR) && typeSizeof(i->sType) == 8 &&
sf == FILE_MEMORY_CONST)
return false;
+ // constant buffer loads can't be used with cbcc xmads
+ if (i->op == OP_XMAD && (i->subOp & 0x1c) == NV50_IR_SUBOP_XMAD_CBCC &&
+ sf == FILE_MEMORY_CONST)
+ return false;
+ // constant buffer loads for the third operand can't be used with psl/mrg
xmads
+ if (i->op == OP_XMAD && sf == FILE_MEMORY_CONST && s == 2 &&
+ (i->subOp & (NV50_IR_SUBOP_XMAD_PSL | NV50_IR_SUBOP_XMAD_MRG)))
+ return false;
+ // for xmads, immediates can't have the h1 flag set
+ if (i->op == OP_XMAD && sf == FILE_IMMEDIATE &&
+ i->src(s).mod & Modifier(NV50_IR_MOD_H1))
+ return false;
for (int k = 0; i->srcExists(k); ++k) {
if (i->src(k).getFile() == FILE_IMMEDIATE) {
@@ -445,6 +457,8 @@ TargetNVC0::isOpSupported(operation op, DataType ty) const
return false;
if (op == OP_POW || op == OP_SQRT || op == OP_DIV || op == OP_MOD)
return false;
+ if (op == OP_XMAD)
+ return false;
return true;
}
@@ -485,6 +499,13 @@ TargetNVC0::isModSupported(const Instruction *insn, int s,
Modifier mod) const
if (insn->src(s ? 0 : 2).mod.neg())
return false;
break;
+ case OP_XMAD:
+ if (insn->getSrc(s)->inFile(FILE_IMMEDIATE) &&
+ mod & Modifier(NV50_IR_MOD_H1))
+ return false;
+ if (s < 2 && !(mod & ~Modifier(NV50_IR_MOD_H1 | NV50_IR_MOD_SEXT)))
+ return true;
+ break;
default:
return false;
}
--
2.14.4
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
