tests: exercise wide 32-bit products and unsigned umul16

Add runtime markers for a full-width 32x32 multiply (0x12345678 * 0x9abcdef0
= 0x242d2080) and for a wide-dividend remainder, so a 16-bit-truncated MPYS or
a wrong FS1 cannot still produce the expected small results.  Compute the 16x16
unsigned product in unsigned arithmetic to remove the signed-overflow
annotation, and reject a regressed nuw nsw multiply in the optimized IR.

scripts/m4/mul-check.lua

@@ -14,6 +14,8 @@
 --   018A80E0  srem(-100,7)          == -2
 --   018A8100  sumto(10)             == 55
 --   018A8120  squares(5)            == 30
+--   018A8140  mul(0x12345678,0x9abcdef0) == 0x242d2080
+--   018A8160  urem(0xfffffffe,7)    == 2
 
 dofile(os.getenv("M4_LOADER_LUA"))
 
@@ -28,16 +30,17 @@ emu.register_frame_done(function()
 		checked = true
 		local prog = manager.machine.devices[':maincpu'].spaces['program']
 		local m = {}
-		for i = 0, 9 do
+		for i = 0, 11 do
 			m[i] = prog:read_u32(0x018A8000 + i * 0x20)
 		end
 		print(string.format(
-			"M4: mul=%d umul16=%d sdiv=%d udiv=%d srem=%d urem=%d sdivneg=%d sremneg=%d sumto=%d squares=%d",
-			m[0], m[1], m[2], m[3], m[4], m[5], m[6], m[7], m[8], m[9]))
+			"M4: mul=%d umul16=%d sdiv=%d udiv=%d srem=%d urem=%d sdivneg=%d sremneg=%d sumto=%d squares=%d widemul=%d widerem=%d",
+			m[0], m[1], m[2], m[3], m[4], m[5], m[6], m[7], m[8], m[9],
+			m[10], m[11]))
 		local want = {42, 0xfffe0001, 14, 613566756, 2, 2,
-			0xfffffff2, 0xfffffffe, 55, 30}
+			0xfffffff2, 0xfffffffe, 55, 30, 0x242d2080, 2}
 		local ok = true
-		for i = 0, 9 do
+		for i = 0, 11 do
 			if m[i] ~= want[i + 1] then
 				ok = false
 			end
@@ -45,7 +48,7 @@ emu.register_frame_done(function()
 		if ok then
 			print("M4 MAME: PASS")
 		else
-			print("M4 MAME: FAIL (want mul=42 umul16=4294836225 sdiv=14 udiv=613566756 srem=2 urem=2 sdivneg=-14 sremneg=-2 sumto=55 squares=30)")
+			print("M4 MAME: FAIL (want mul=42 umul16=4294836225 sdiv=14 udiv=613566756 srem=2 urem=2 sdivneg=-14 sremneg=-2 sumto=55 squares=30 widemul=606937216 widerem=2)")
 		end
 	end
 end, "mul-check")

scripts/m4/mul.c

@@ -9,15 +9,20 @@
  *   018A80A0  urem(100,7)              == 2
  *   018A80C0  sdiv(-100,7)             == -14
  *   018A80E0  srem(-100,7)             == -2
+ *   018A8140  mul(0x12345678,0x9ABCDEF0) == 0x242D2080 (wide 32x32 product)
+ *   018A8160  urem(0xfffffffe,7)       == 2   (wide quotient in the remainder)
  */
 #define MARK(n) (*(volatile unsigned int *)(0x018A8000u + (n)*0x20u))
 
 int mul(int a, int b) { return a * b; }
 
 /* A 16x16 unsigned product: both operands are masked to 16 bits, which is the
- * form the target selects to MPYU.  A plain unsigned short multiply promotes
- * to a signed int multiply and would use MPYS. */
-int umul16(int a, int b) { return (a & 0xffff) * (b & 0xffff); }
+ * form the target selects to MPYU.  The product must be computed in unsigned
+ * arithmetic: 0xffff * 0xffff does not fit in signed int, so `int * int` would
+ * be signed overflow and the optimizer could narrow or rename the result. */
+int umul16(int a, int b) {
+  return (int)((unsigned)(a & 0xffff) * (unsigned)(b & 0xffff));
+}
 
 int sdiv(int a, int b) { return a / b; }
 unsigned udiv(unsigned a, unsigned b) { return a / b; }
@@ -33,5 +38,7 @@ int mul_test(void) {
   MARK(5) = urem(100u, 7u);
   MARK(6) = (unsigned)sdiv(-100, 7);
   MARK(7) = (unsigned)srem(-100, 7);
+  MARK(10) = (unsigned)mul(0x12345678, 0x9ABCDEF0);
+  MARK(11) = urem(0xfffffffeu, 7u);
   return 0;
 }

scripts/tests/m4/mul.sh

@@ -34,6 +34,15 @@ if grep -Eq '\bmul i(33|64)\b' "$WORK/asm/loop.ll"; then
 fi
 echo "   ok driver -O2 loop IR has no i33/i64 multiply"
 
+# The 16x16 unsigned product must not carry the old signed-overflow
+# annotation.  With the multiply done in unsigned arithmetic the IR is
+# `mul nuw`, not `mul nuw nsw`; the latter contradicts the 0xfffe0001 result.
+if awk '/^define .*@umul16\(/{infn=1} infn{print} infn && /^}/{exit}' \
+        "$WORK/asm/mul.ll" | grep -q 'mul nuw nsw'; then
+    fail "umul16 still has a signed no-wrap multiply (the product is unsigned)"
+fi
+echo "   ok umul16 multiplies without signed no-wrap"
+
 # Stop at the next function label (a column-0 label that is not an LBB block
 # label), so a following local function cannot leak into this slice.
 body() { # body FILE FUNC
@@ -49,7 +58,7 @@ body() { # body FILE FUNC
 TMP=$(mktemp -d "${TMPDIR:-/tmp}/m4-mul.XXXXXX")
 trap 'rm -rf "$TMP"' EXIT HUP INT TERM
 
-EXPECTED="M4: mul=42 umul16=4294836225 sdiv=14 udiv=613566756 srem=2 urem=2 sdivneg=4294967282 sremneg=4294967294 sumto=55 squares=30"
+EXPECTED="M4: mul=42 umul16=4294836225 sdiv=14 udiv=613566756 srem=2 urem=2 sdivneg=4294967282 sremneg=4294967294 sumto=55 squares=30 widemul=606937216 widerem=2"
 grep -Fqx "$EXPECTED" "$WORK/mame.log" \
     || { grep -E '^M4: ' "$WORK/mame.log" >&2 || true; fail "runtime markers did not match: $EXPECTED"; }
 echo "   ok runtime markers: $EXPECTED"