[compiler-rt] Add missing carry to 128x128->256 wide multiply

Author: beetrees

compiler-rt/lib/builtins/fp_lib.h

@@ -180,8 +180,11 @@ static __inline void wideMultiply(rep_t a, rep_t b, rep_t *hi, rep_t *lo) {
                          (sum2 & Word_FullMask) + ((sum3 << 32) & Word_HiMask);
 
   *lo = r0 + (r1 << 64);
+  // The addition above can overflow, in which case `*lo` will be less than
+  // `r0`. Carry any overflow into `hi`.
+  const bool carry = *lo < r0;
   *hi = (r1 >> 64) + (sum1 >> 96) + (sum2 >> 64) + (sum3 >> 32) + sum4 +
-        (sum5 << 32) + (sum6 << 64);
+        (sum5 << 32) + (sum6 << 64) + carry;
 }
 #undef Word_1
 #undef Word_2

compiler-rt/test/builtins/Unit/multf3_test.c

@@ -77,6 +77,12 @@ int main()
                      UINT64_C(0x0),
                      UINT64_C(0x0)))
         return 1;
+    // test carry between lo and hi in widening multiply
+    if (test__multf3(0x0.7fffffffffffffffffffffffffffp-16382L,
+                     0x1.7fffffffffffffffffffffffffffp+1L,
+                     UINT64_C(0x00017fffffffffff),
+                     UINT64_C(0xfffffffffffffffc)))
+        return 1;
 
 #else
     printf("skipped\n");