Merge branch 'linear-fma' into next

* add support for a new instruction: OP_FMA
* teach sparse to linearize __builtin_fma()

5 files changed, 57 insertions, 2 deletions

diff --git a/Documentation/IR.rst b/Documentation/IR.rst
index 97d4b2b2..ff5af1c5 100644
--- a/Documentation/IR.rst
+++ b/Documentation/IR.rst
@@ -309,6 +309,13 @@ Ternary ops
 	* .target: result of the operation
 	* .type: type of .target
 
+.. op:: OP_FMADD
+    Fused multiply-add.
+
+	* .src1, .src2, .src3: operands (types must be compatible with .target)
+	* .target: result of the operation (must be a floating-point type)
+	* .type: type of .target
+
 .. op:: OP_RANGE
 	Range/bounds checking (only used for an unused sparse extension).
 
diff --git a/builtin.c b/builtin.c
index 2e9be8be..26b612dc 100644
--- a/builtin.c
+++ b/builtin.c
@@ -490,6 +490,9 @@ static const struct builtin_fn builtins_common[] = {
 	{ "__builtin_ffs", &int_ctype, 0, { &int_ctype }, .op = &ffs_op },
 	{ "__builtin_ffsl", &int_ctype, 0, { &long_ctype }, .op = &ffs_op },
 	{ "__builtin_ffsll", &int_ctype, 0, { &llong_ctype }, .op = &ffs_op },
+	{ "__builtin_fma", &double_ctype, 0, { &double_ctype, &double_ctype, &double_ctype }},
+	{ "__builtin_fmaf", &float_ctype, 0, { &float_ctype, &float_ctype, &float_ctype }},
+	{ "__builtin_fmal", &ldouble_ctype, 0, { &ldouble_ctype, &ldouble_ctype, &ldouble_ctype }},
 	{ "__builtin_frame_address", &ptr_ctype, 0, { &uint_ctype }},
 	{ "__builtin_free", &void_ctype, 0, { &ptr_ctype }},
 	{ "__builtin_huge_val", &double_ctype, 0 },
diff --git a/linearize.c b/linearize.c
index 5a8e7497..1081bda8 100644
--- a/linearize.c
+++ b/linearize.c
@@ -244,6 +244,7 @@ static const char *opcodes[] = {
 
 	/* Special three-input */
 	[OP_SEL] = "select",
+	[OP_FMADD] = "fmadd",
 	
 	/* Memory */
 	[OP_LOAD] = "load",
@@ -461,6 +462,7 @@ const char *show_instruction(struct instruction *insn)
 		break;
 
 	case OP_SEL:
+	case OP_FMADD:
 		buf += sprintf(buf, "%s <- %s, %s, %s", show_pseudo(insn->target),
 			show_pseudo(insn->src1), show_pseudo(insn->src2), show_pseudo(insn->src3));
 		break;
@@ -1511,8 +1513,11 @@ static pseudo_t linearize_call_expression(struct entrypoint *ep, struct expressi
 	fntype = fn->ctype;
 
 	// handle builtins
-	if (fntype->op && fntype->op->linearize)
-		return fntype->op->linearize(ep, expr);
+	if (fntype->op && fntype->op->linearize) {
+		retval = fntype->op->linearize(ep, expr);
+		if (retval)
+			return retval;
+	}
 
 	ctype = &fntype->ctype;
 	if (fntype->type == SYM_NODE)
@@ -2580,6 +2585,23 @@ struct entrypoint *linearize_symbol(struct symbol *sym)
  * Builtin functions
  */
 
+static pseudo_t linearize_fma(struct entrypoint *ep, struct expression *expr)
+{
+	struct instruction *insn = alloc_typed_instruction(OP_FMADD, expr->ctype);
+	struct expression *arg;
+
+	PREPARE_PTR_LIST(expr->args, arg);
+		insn->src1 = linearize_expression(ep, arg);
+		NEXT_PTR_LIST(arg)
+		insn->src2 = linearize_expression(ep, arg);
+		NEXT_PTR_LIST(arg)
+		insn->src3 = linearize_expression(ep, arg);
+	FINISH_PTR_LIST(arg);
+
+	add_one_insn(ep, insn);
+	return insn->target = alloc_pseudo(insn);
+}
+
 static pseudo_t linearize_unreachable(struct entrypoint *ep, struct expression *exp)
 {
 	add_unreachable(ep);
@@ -2592,6 +2614,9 @@ static struct sym_init {
 	struct symbol_op op;
 } builtins_table[] = {
 	// must be declared in builtin.c:declare_builtins[]
+	{ "__builtin_fma", linearize_fma },
+	{ "__builtin_fmaf", linearize_fma },
+	{ "__builtin_fmal", linearize_fma },
 	{ "__builtin_unreachable", linearize_unreachable },
 	{ }
 };
diff --git a/opcode.def b/opcode.def
index 2583e2f4..7959efaf 100644
--- a/opcode.def
+++ b/opcode.def
@@ -91,6 +91,7 @@ OPCODE(SLICE,           BADOP,    BADOP,    BADOP, 1, OPF_TARGET)
 
 /* Select - three input values */
 OPCODE(SEL,             BADOP,    BADOP,    BADOP, 3, OPF_TARGET)
+OPCODE(FMADD,           BADOP,    BADOP,    BADOP, 3, OPF_TARGET)
 
 /* Memory */
 OPCODE(LOAD,            BADOP,    BADOP,    BADOP, 1, OPF_TARGET)
diff --git a/validation/linear/builtin-fma.c b/validation/linear/builtin-fma.c
new file mode 100644
index 00000000..b1024f39
--- /dev/null
+++ b/validation/linear/builtin-fma.c
@@ -0,0 +1,19 @@
+double fma(double a, double x, double y)
+{
+	return __builtin_fma(a, x, y);
+}
+
+/*
+ * check-name: builtin-fma
+ * check-command: test-linearize -Wno-decl $file
+ *
+ * check-output-start
+fma:
+.L0:
+	<entry-point>
+	fmadd.64    %r4 <- %r1, %r2, %r3
+	ret.64      %r4
+
+
+ * check-output-end
+ */