Merge from trunk revision 99b1021d21e5812ed01221d8fca8e8a32488a934.

36 files changed, 595 insertions, 324 deletions

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-warn-23.c b/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-warn-23.c
index 7fb9651..112b08a 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-warn-23.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-warn-23.c
@@ -214,12 +214,14 @@ void test_struct_member_array (struct S3 *s3, int i)
   T (d, "%s", d);       /* { dg-warning "overlaps" } */
   T (d, "%s", d + 0);   /* { dg-warning "overlaps" } */
   T (d, "%s", d + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", d + 2);   /* { dg-warning "may overlap" } */
+  /* Since d below points to char[4], strlen(d + 2) must be at most 1
+     and so the call cannot overlap. */
+  T (d, "%s", d + 2);
   T (d, "%s", d + i);   /* { dg-warning "may overlap" } */
 
   T (d, "%s", &d[0]);   /* { dg-warning "overlaps" } */
   T (d, "%s", &d[1]);   /* { dg-warning "may overlap" } */
-  T (d, "%s", &d[2]);   /* { dg-warning "may overlap" } */
+  T (d, "%s", &d[2]);
   T (d, "%s", &d[i]);   /* { dg-warning "may overlap" } */
 
   T (d + 0, "%s", d);   /* { dg-warning "overlaps" } */
@@ -236,7 +238,7 @@ void test_struct_member_array (struct S3 *s3, int i)
 
   T (d, "%s", s);       /* { dg-warning "overlaps" } */
   T (d, "%s", s + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", s + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", s + 2);
   T (d, "%s", s + i);   /* { dg-warning "may overlap" } */
 
   s = s3->s2_1.s_1.b;
@@ -324,7 +326,7 @@ void test_struct_member_array (struct S3 *s3, int i)
 
   T (d, "%s", s);       /* { dg-warning "overlaps" } */
   T (d, "%s", s + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", s + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", s + 2);
   T (d, "%s", s + i);   /* { dg-warning "may overlap" } */
 
   s = s3->s2_2.s_2.a;
@@ -368,7 +370,7 @@ void test_struct_member_array (struct S3 *s3, int i)
 
   T (d, "%s", s);       /* { dg-warning "overlaps" } */
   T (d, "%s", s + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", s + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", s + 2);
   T (d, "%s", s + i);   /* { dg-warning "may overlap" } */
 
   s = s3->s2_2.s_2.a;
@@ -394,12 +396,12 @@ void test_struct_member_array_array (struct S3 *s3, int i)
   T (d, "%s", s);       /* { dg-warning "overlaps" } */
   T (d, "%s", s + 0);   /* { dg-warning "overlaps" } */
   T (d, "%s", s + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", s + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", s + 2);
   T (d, "%s", s + i);   /* { dg-warning "may overlap" } */
 
   T (d, "%s", &s[0]);   /* { dg-warning "overlaps" } */
   T (d, "%s", &s[1]);   /* { dg-warning "may overlap" } */
-  T (d, "%s", &s[2]);   /* { dg-warning "may overlap" } */
+  T (d, "%s", &s[2]);
   T (d, "%s", &s[i]);   /* { dg-warning "may overlap" } */
 
   T (d + 0, "%s", s);   /* { dg-warning "overlaps" } */
@@ -566,12 +568,12 @@ void test_union_member_array (union U *un, int i)
   T (d, "%s", d);       /* { dg-warning "overlaps" } */
   T (d, "%s", d + 0);   /* { dg-warning "overlaps" } */
   T (d, "%s", d + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", d + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", d + 2);
   T (d, "%s", d + i);   /* { dg-warning "may overlap" } */
 
   T (d, "%s", &d[0]);   /* { dg-warning "overlaps" } */
   T (d, "%s", &d[1]);   /* { dg-warning "may overlap" } */
-  T (d, "%s", &d[2]);   /* { dg-warning "may overlap" } */
+  T (d, "%s", &d[2]);
   T (d, "%s", &d[i]);   /* { dg-warning "may overlap" } */
 
   T (d + 0, "%s", d);   /* { dg-warning "overlaps" } */
@@ -588,7 +590,7 @@ void test_union_member_array (union U *un, int i)
 
   T (d, "%s", s);       /* { dg-warning "overlaps" } */
   T (d, "%s", s + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", s + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", s + 2);
   T (d, "%s", s + i);   /* { dg-warning "may overlap" } */
 
   s = un->s2_1.s_1.b;
@@ -616,7 +618,7 @@ void test_union_member_array (union U *un, int i)
 
   T (d, "%s", s);       /* { dg-warning "overlaps" } */
   T (d, "%s", s + 1);   /* { dg-warning "may overlap" } */
-  T (d, "%s", s + 2);   /* { dg-warning "may overlap" } */
+  T (d, "%s", s + 2);
   T (d, "%s", s + i);   /* { dg-warning "may overlap" } */
 
   s = un->s2_2.s_1.b;
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ifc-20040816-1.c b/gcc/testsuite/gcc.dg/tree-ssa/ifc-20040816-1.c
index b55a533..f8a6495 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ifc-20040816-1.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ifc-20040816-1.c
@@ -39,4 +39,4 @@ int main1 ()
    which is folded by vectorizer.  Both outgoing edges must have probability
    100% so the resulting profile match after folding.  */
 /* { dg-final { scan-tree-dump-times "Invalid sum of outgoing probabilities 200.0" 1 "ifcvt" } } */
-/* { dg-final { scan-tree-dump-times "Invalid sum of incoming counts" 1 "ifcvt" } } */
+/* { dg-final { scan-tree-dump-times "Invalid sum of incoming counts" 2 "ifcvt" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ldist-rawmemchr-1.c b/gcc/testsuite/gcc.dg/tree-ssa/ldist-rawmemchr-1.c
new file mode 100644
index 0000000..6abfd27
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ldist-rawmemchr-1.c
@@ -0,0 +1,72 @@
+/* { dg-do run { target s390x-*-* } } */
+/* { dg-options "-O2 -ftree-loop-distribution -fdump-tree-ldist-details" } */
+/* { dg-final { scan-tree-dump-times "generated rawmemchrQI" 2 "ldist" { target s390x-*-* } } } */
+/* { dg-final { scan-tree-dump-times "generated rawmemchrHI" 2 "ldist" { target s390x-*-* } } } */
+/* { dg-final { scan-tree-dump-times "generated rawmemchrSI" 2 "ldist" { target s390x-*-* } } } */
+
+/* Rawmemchr pattern: reduction stmt and no store */
+
+#include <stdint.h>
+#include <assert.h>
+
+typedef __SIZE_TYPE__ size_t;
+extern void* malloc (size_t);
+extern void* memset (void*, int, size_t);
+
+#define test(T, pattern)   \
+__attribute__((noinline))  \
+T *test_##T (T *p)         \
+{                          \
+  while (*p != (T)pattern) \
+    ++p;                   \
+  return p;                \
+}
+
+test (uint8_t,  0xab)
+test (uint16_t, 0xabcd)
+test (uint32_t, 0xabcdef15)
+
+test (int8_t,  0xab)
+test (int16_t, 0xabcd)
+test (int32_t, 0xabcdef15)
+
+#define run(T, pattern, i)      \
+{                               \
+T *q = p;                       \
+q[i] = (T)pattern;              \
+assert (test_##T (p) == &q[i]); \
+q[i] = 0;                       \
+}
+
+int main(void)
+{
+  void *p = malloc (1024);
+  assert (p);
+  memset (p, 0, 1024);
+
+  run (uint8_t, 0xab, 0);
+  run (uint8_t, 0xab, 1);
+  run (uint8_t, 0xab, 13);
+
+  run (uint16_t, 0xabcd, 0);
+  run (uint16_t, 0xabcd, 1);
+  run (uint16_t, 0xabcd, 13);
+
+  run (uint32_t, 0xabcdef15, 0);
+  run (uint32_t, 0xabcdef15, 1);
+  run (uint32_t, 0xabcdef15, 13);
+
+  run (int8_t, 0xab, 0);
+  run (int8_t, 0xab, 1);
+  run (int8_t, 0xab, 13);
+
+  run (int16_t, 0xabcd, 0);
+  run (int16_t, 0xabcd, 1);
+  run (int16_t, 0xabcd, 13);
+
+  run (int32_t, 0xabcdef15, 0);
+  run (int32_t, 0xabcdef15, 1);
+  run (int32_t, 0xabcdef15, 13);
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ldist-rawmemchr-2.c b/gcc/testsuite/gcc.dg/tree-ssa/ldist-rawmemchr-2.c
new file mode 100644
index 0000000..00d6ea0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ldist-rawmemchr-2.c
@@ -0,0 +1,83 @@
+/* { dg-do run { target s390x-*-* } } */
+/* { dg-options "-O2 -ftree-loop-distribution -fdump-tree-ldist-details" } */
+/* { dg-final { scan-tree-dump-times "generated rawmemchrQI" 2 "ldist" { target s390x-*-* } } } */
+/* { dg-final { scan-tree-dump-times "generated rawmemchrHI" 2 "ldist" { target s390x-*-* } } } */
+/* { dg-final { scan-tree-dump-times "generated rawmemchrSI" 2 "ldist" { target s390x-*-* } } } */
+
+/* Rawmemchr pattern: reduction stmt and store */
+
+#include <stdint.h>
+#include <assert.h>
+
+typedef __SIZE_TYPE__ size_t;
+extern void* malloc (size_t);
+extern void* memset (void*, int, size_t);
+
+uint8_t *p_uint8_t;
+uint16_t *p_uint16_t;
+uint32_t *p_uint32_t;
+
+int8_t *p_int8_t;
+int16_t *p_int16_t;
+int32_t *p_int32_t;
+
+#define test(T, pattern)    \
+__attribute__((noinline))   \
+T *test_##T (void)          \
+{                           \
+  while (*p_##T != pattern) \
+    ++p_##T;                \
+  return p_##T;             \
+}
+
+test (uint8_t,  0xab)
+test (uint16_t, 0xabcd)
+test (uint32_t, 0xabcdef15)
+
+test (int8_t,  (int8_t)0xab)
+test (int16_t, (int16_t)0xabcd)
+test (int32_t, (int32_t)0xabcdef15)
+
+#define run(T, pattern, i) \
+{                          \
+T *q = p;                  \
+q[i] = pattern;            \
+p_##T = p;                 \
+T *r = test_##T ();        \
+assert (r == p_##T);       \
+assert (r == &q[i]);       \
+q[i] = 0;                  \
+}
+
+int main(void)
+{
+  void *p = malloc (1024);
+  assert (p);
+  memset (p, '\0', 1024);
+
+  run (uint8_t, 0xab, 0);
+  run (uint8_t, 0xab, 1);
+  run (uint8_t, 0xab, 13);
+
+  run (uint16_t, 0xabcd, 0);
+  run (uint16_t, 0xabcd, 1);
+  run (uint16_t, 0xabcd, 13);
+
+  run (uint32_t, 0xabcdef15, 0);
+  run (uint32_t, 0xabcdef15, 1);
+  run (uint32_t, 0xabcdef15, 13);
+
+  run (int8_t, (int8_t)0xab, 0);
+  run (int8_t, (int8_t)0xab, 1);
+  run (int8_t, (int8_t)0xab, 13);
+
+  run (int16_t, (int16_t)0xabcd, 0);
+  run (int16_t, (int16_t)0xabcd, 1);
+  run (int16_t, (int16_t)0xabcd, 13);
+
+  run (int32_t, (int32_t)0xabcdef15, 0);
+  run (int32_t, (int32_t)0xabcdef15, 1);
+  run (int32_t, (int32_t)0xabcdef15, 13);
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-1.c b/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-1.c
new file mode 100644
index 0000000..918b600
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-1.c
@@ -0,0 +1,100 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -ftree-loop-distribution -fdump-tree-ldist-details" } */
+/* { dg-final { scan-tree-dump-times "generated strlenQI\n" 4 "ldist" } } */
+/* { dg-final { scan-tree-dump-times "generated strlenHI\n" 4 "ldist" { target s390x-*-* } } } */
+/* { dg-final { scan-tree-dump-times "generated strlenSI\n" 4 "ldist" { target s390x-*-* } } } */
+
+#include <stdint.h>
+#include <assert.h>
+
+typedef __SIZE_TYPE__ size_t;
+extern void* malloc (size_t);
+extern void* memset (void*, int, size_t);
+
+#define test(T, U)        \
+__attribute__((noinline)) \
+U test_##T##U (T *s)      \
+{                         \
+  U i;                    \
+  for (i=0; s[i]; ++i);   \
+  return i;               \
+}
+
+test (uint8_t,  size_t)
+test (uint16_t, size_t)
+test (uint32_t, size_t)
+test (uint8_t,  int)
+test (uint16_t, int)
+test (uint32_t, int)
+
+test (int8_t,  size_t)
+test (int16_t, size_t)
+test (int32_t, size_t)
+test (int8_t,  int)
+test (int16_t, int)
+test (int32_t, int)
+
+#define run(T, U, i)             \
+{                                \
+T *q = p;                        \
+q[i] = 0;                        \
+assert (test_##T##U (p) == i);   \
+memset (&q[i], 0xf, sizeof (T)); \
+}
+
+int main(void)
+{
+  void *p = malloc (1024);
+  assert (p);
+  memset (p, 0xf, 1024);
+
+  run (uint8_t, size_t, 0);
+  run (uint8_t, size_t, 1);
+  run (uint8_t, size_t, 13);
+
+  run (int8_t, size_t, 0);
+  run (int8_t, size_t, 1);
+  run (int8_t, size_t, 13);
+
+  run (uint8_t, int, 0);
+  run (uint8_t, int, 1);
+  run (uint8_t, int, 13);
+
+  run (int8_t, int, 0);
+  run (int8_t, int, 1);
+  run (int8_t, int, 13);
+
+  run (uint16_t, size_t, 0);
+  run (uint16_t, size_t, 1);
+  run (uint16_t, size_t, 13);
+
+  run (int16_t, size_t, 0);
+  run (int16_t, size_t, 1);
+  run (int16_t, size_t, 13);
+
+  run (uint16_t, int, 0);
+  run (uint16_t, int, 1);
+  run (uint16_t, int, 13);
+
+  run (int16_t, int, 0);
+  run (int16_t, int, 1);
+  run (int16_t, int, 13);
+
+  run (uint32_t, size_t, 0);
+  run (uint32_t, size_t, 1);
+  run (uint32_t, size_t, 13);
+
+  run (int32_t, size_t, 0);
+  run (int32_t, size_t, 1);
+  run (int32_t, size_t, 13);
+
+  run (uint32_t, int, 0);
+  run (uint32_t, int, 1);
+  run (uint32_t, int, 13);
+
+  run (int32_t, int, 0);
+  run (int32_t, int, 1);
+  run (int32_t, int, 13);
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-2.c b/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-2.c
new file mode 100644
index 0000000..e25d6ea
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-2.c
@@ -0,0 +1,58 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -ftree-loop-distribution -fdump-tree-ldist-details" } */
+/* { dg-final { scan-tree-dump-times "generated strlenQI\n" 3 "ldist" } } */
+
+#include <assert.h>
+
+typedef __SIZE_TYPE__ size_t;
+extern void* malloc (size_t);
+extern void* memset (void*, int, size_t);
+
+__attribute__((noinline))
+int test_pos (char *s)
+{
+  int i;
+  for (i=42; s[i]; ++i);
+  return i;
+}
+
+__attribute__((noinline))
+int test_neg (char *s)
+{
+  int i;
+  for (i=-42; s[i]; ++i);
+  return i;
+}
+
+__attribute__((noinline))
+int test_including_null_char (char *s)
+{
+  int i;
+  for (i=1; s[i-1]; ++i);
+  return i;
+}
+
+int main(void)
+{
+  void *p = malloc (1024);
+  assert (p);
+  memset (p, 0xf, 1024);
+  char *s = (char *)p + 100;
+
+  s[42+13] = 0;
+  assert (test_pos (s) == 42+13);
+  s[42+13] = 0xf;
+
+  s[13] = 0;
+  assert (test_neg (s) == 13);
+  s[13] = 0xf;
+
+  s[-13] = 0;
+  assert (test_neg (s) == -13);
+  s[-13] = 0xf;
+
+  s[13] = 0;
+  assert (test_including_null_char (s) == 13+1);
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-3.c b/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-3.c
new file mode 100644
index 0000000..370fd5e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ldist-strlen-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-loop-distribution -fdump-tree-ldist-details" } */
+/* { dg-final { scan-tree-dump-times "generated strlenSI\n" 1 "ldist" { target s390x-*-* } } } */
+
+extern int s[];
+
+int test ()
+{
+  int i = 0;
+  for (; s[i]; ++i);
+  return i;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr102736.c b/gcc/testsuite/gcc.dg/tree-ssa/pr102736.c
new file mode 100644
index 0000000..c693a71
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr102736.c
@@ -0,0 +1,21 @@
+// { dg-do run }
+// { dg-options "-O1 -ftree-vrp" }
+
+int a, b = -1, c;
+int d = 1;
+static inline signed char e(signed char f, int g) { return g ? f : 0; }
+static inline signed char h(signed char f) { return f < a ? f : f < a; }
+static inline unsigned char i(unsigned char f, int g) { return g ? f : f > g; }
+void j() {
+L:
+  c = e(1, i(h(b), d));
+  if (b)
+    return;
+  goto L;
+}
+int main() {
+  j();
+  if (c != 1)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr20701.c b/gcc/testsuite/gcc.dg/tree-ssa/pr20701.c
index 2f91458..496c425 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr20701.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr20701.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-vrp1 -fno-early-inlining -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fdump-tree-vrp1 -fno-early-inlining -fdelete-null-pointer-checks -fdisable-tree-thread1" } */
 
 typedef struct {
   int code;
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr20702.c b/gcc/testsuite/gcc.dg/tree-ssa/pr20702.c
index c8968577..8112967 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr20702.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr20702.c
@@ -4,7 +4,7 @@
    immediate successors of the basic block.  */
 
 /* { dg-do compile } */
-/* { dg-options "-O2 -fno-tree-dominator-opts -fdisable-tree-evrp -fdump-tree-vrp1-details -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fno-thread-jumps -fdisable-tree-evrp -fdump-tree-vrp1-details -fdelete-null-pointer-checks" } */
 
 extern void bar (int);
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21086.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21086.c
index aadd53e..9b93d39 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21086.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21086.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-vrp1 -fdump-tree-dce2 -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fno-thread-jumps -fdisable-tree-evrp -fdump-tree-vrp1 -fdump-tree-dce2 -fdelete-null-pointer-checks" } */
 
 int
 foo (int *p)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21090.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21090.c
index 3909adb..92a8768 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21090.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21090.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-vrp1 -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fno-thread-jumps -fdisable-tree-evrp -fdump-tree-vrp1 -fdelete-null-pointer-checks" } */
 
 int g, h;
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21559.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21559.c
index 51b3b7a..43f046e 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21559.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21559.c
@@ -35,10 +35,7 @@ void foo (void)
 /* First, we should simplify the bits < 0 test within the loop.  */
 /* { dg-final { scan-tree-dump-times "Simplified relational" 1 "evrp" } } */
 
-/* Second, we should thread the edge out of the loop via the break
-   statement.  We also realize that the final bytes == 0 test is useless,
-   and thread over it.  We also know that toread != 0 is useless when
-   entering while loop and thread over it.  */
-/* { dg-final { scan-tree-dump-times "Threaded jump" 3 "vrp-thread1" } } */
+/* We used to check for 3 threaded jumps here, but they all would
+   rotate the loop.  */
 
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr25382.c b/gcc/testsuite/gcc.dg/tree-ssa/pr25382.c
index d747655..8634c0a 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr25382.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr25382.c
@@ -3,7 +3,7 @@
    Check that VRP now gets ranges from BIT_AND_EXPRs.  */
 
 /* { dg-do compile } */
-/* { dg-options "-O2 -fno-tree-ccp -fdisable-tree-evrp -fdump-tree-vrp1" } */
+/* { dg-options "-O2 -fno-thread-jumps -fno-tree-ccp -fdisable-tree-evrp -fdump-tree-vrp1" } */
 
 int
 foo (int a)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr58480.c b/gcc/testsuite/gcc.dg/tree-ssa/pr58480.c
index 42898e7..f11623b 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr58480.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr58480.c
@@ -1,5 +1,5 @@
 /* { dg-do compile { target { ! keeps_null_pointer_checks } } } */
-/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-vrp1 -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fno-thread-jumps -fdisable-tree-evrp -fdump-tree-vrp1 -fdelete-null-pointer-checks" } */
 
 extern void eliminate (void);
 extern void* f1 (void *a, void *b) __attribute__((nonnull));
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr59597.c b/gcc/testsuite/gcc.dg/tree-ssa/pr59597.c
index 2caa1f5..764b3fe 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr59597.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr59597.c
@@ -56,11 +56,7 @@ main (int argc, char argv[])
   return crc;
 }
 
-/* Previously we had 3 jump threads, but one of them crossed loops.
-   The reason the old threader was allowing it, was because there was
-   an ASSERT_EXPR getting in the way.  Without the ASSERT_EXPR, we
-   have an empty pre-header block as the final block in the thread,
-   which the threader will simply join with the next block which *is*
-   in a different loop.  */
-/* { dg-final { scan-tree-dump-times "Registering jump thread" 2 "vrp-thread1" } } */
+/* None of the threads we can get in vrp-thread1 are valid.  They all
+   cross or rotate loops.  */
+/* { dg-final { scan-tree-dump-not "Registering jump thread" "vrp-thread1" } } */
 /* { dg-final { scan-tree-dump-not "joiner" "vrp-thread1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr71437.c b/gcc/testsuite/gcc.dg/tree-ssa/pr71437.c
index a2386ba..eab3a25 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr71437.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr71437.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-ffast-math -O3 -fdump-tree-vrp-thread1-details" } */
+/* { dg-options "-ffast-math -O3 -fdump-tree-dom3-details" } */
 
 int I = 50, J = 50;
 int S, L;
@@ -39,4 +39,8 @@ void foo (int K)
 	bar (LD, SD);
     }
 }
-/* { dg-final { scan-tree-dump-times "Threaded jump " 2 "vrp-thread1" } } */
+
+/* We used to get 1 vrp-thread1 candidates here, but they now get
+   deferred until after loop opts are done, because they were rotating
+   loops.  */
+/* { dg-final { scan-tree-dump-times "Threaded jump " 2 "dom3" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c b/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
index 18f7aab..f2a5e78 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
@@ -123,8 +123,7 @@ enum STATES FMS( u8 **in , u32 *transitions) {
    aarch64 has the highest CASE_VALUES_THRESHOLD in GCC.  It's high enough
    to change decisions in switch expansion which in turn can expose new
    jump threading opportunities.  Skip the later tests on aarch64.  */
-/* { dg-final { scan-tree-dump "Jumps threaded: \[7-9\]" "thread1" } } */
-/* { dg-final { scan-tree-dump-times "Invalid sum" 1 "thread1" } } */
+/* { dg-final { scan-tree-dump "Jumps threaded: \[7-9\]" "thread2" } } */
 /* { dg-final { scan-tree-dump-not "optimizing for size" "thread1" } } */
 /* { dg-final { scan-tree-dump-not "optimizing for size" "thread2" } } */
 /* { dg-final { scan-tree-dump-not "optimizing for size" "thread3" { target { ! aarch64*-*-* } } } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/predcom-3.c b/gcc/testsuite/gcc.dg/tree-ssa/predcom-3.c
index 1174cd1..9abbe6c 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/predcom-3.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/predcom-3.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -funroll-loops --param max-unroll-times=8 -fpredictive-commoning -fdump-tree-pcom-details -fno-tree-pre" } */
+/* { dg-options "-O2 -funroll-loops --param max-unroll-times=8 -fpredictive-commoning -fdump-tree-pcom-details -fno-tree-pre -fno-tree-loop-vectorize" } */
 
 int a[1000], b[1000];
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pta-callused.c b/gcc/testsuite/gcc.dg/tree-ssa/pta-callused.c
index cb85ec1..aa639b4 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pta-callused.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pta-callused.c
@@ -22,5 +22,5 @@ int bar (int b)
   return *foo (&q);
 }
 
-/* { dg-final { scan-tree-dump "CALLUSED\\(\[0-9\]+\\) = { f.* i q }" "alias" } } */
+/* { dg-final { scan-tree-dump "CALLUSED\\(\[0-9\]+\\) = { NONLOCAL f.* i q }" "alias" } } */
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dce-9.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dce-9.c
new file mode 100644
index 0000000..e1ffa7f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dce-9.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-cddce1" } */
+
+int main()
+{
+  while(1)
+    for(int i=0; i<9000000; i++){}
+}
+
+/* { dg-final { scan-tree-dump-not "if" "cddce1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c
deleted file mode 100644
index 0246ebf..0000000
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c
+++ /dev/null
@@ -1,27 +0,0 @@
-/* { dg-do compile } */ 
-/* { dg-options "-O2 -fdump-tree-vrp-thread1-details -std=gnu89 --param logical-op-non-short-circuit=0" } */
-
-#include "ssa-dom-thread-4.c"
-
-/* On targets that define LOGICAL_OP_NON_SHORT_CIRCUIT to 0, we split both
-   "a_elt || b_elt" and "b_elt && kill_elt" into two conditions each,
-   rather than using "(var1 != 0) op (var2 != 0)".  Also, as on other targets,
-   we duplicate the header of the inner "while" loop.  There are then
-   4 threading opportunities:
-
-   1x "!a_elt && b_elt" in the outer "while" loop
-      -> the start of the inner "while" loop,
-	 skipping the known-true "b_elt" in the first condition.
-   1x "!b_elt" in the first condition
-      -> the outer "while" loop's continuation point,
-	 skipping the known-false "b_elt" in the second condition.
-   2x "kill_elt->indx >= b_elt->indx" in the first "while" loop
-      -> "kill_elt->indx == b_elt->indx" in the second condition,
-	 skipping the known-true "b_elt && kill_elt" in the second
-	 condition.
-
-   All the cases are picked up by VRP1 as jump threads.  */
-
-/* There used to be 6 jump threads found by thread1, but they all
-   depended on threading through distinct loops in ethread.  */
-/* { dg-final { scan-tree-dump-times "Threaded" 2 "vrp-thread1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2a.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2a.c
deleted file mode 100644
index 8f0a12c..0000000
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-2a.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/* { dg-do compile } */ 
-/* { dg-options "-O2 -fdump-tree-vrp-thread1-stats -fdump-tree-dom2-stats" } */
-
-void bla();
-
-/* In the following case, we should be able to thread edge through
-   the loop header.  */
-
-void thread_entry_through_header (void)
-{
-  int i;
-
-  for (i = 0; i < 170; i++)
-    bla ();
-}
-
-/* There's a single jump thread that should be handled by the VRP
-   jump threading pass.  */
-/* { dg-final { scan-tree-dump-times "Jumps threaded: 1" 1 "vrp-thread1"} } */
-/* { dg-final { scan-tree-dump-times "Jumps threaded: 2" 0 "vrp-thread1"} } */
-/* { dg-final { scan-tree-dump-not "Jumps threaded" "dom2"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-4.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-4.c
deleted file mode 100644
index 46e464f..0000000
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-4.c
+++ /dev/null
@@ -1,62 +0,0 @@
-/* { dg-do compile } */ 
-/* { dg-options "-O2 -fdump-tree-vrp-thread1-details -fdump-tree-dom2-details -std=gnu89 --param logical-op-non-short-circuit=1" } */
-struct bitmap_head_def;
-typedef struct bitmap_head_def *bitmap;
-typedef const struct bitmap_head_def *const_bitmap;
-typedef unsigned long BITMAP_WORD;
-typedef struct bitmap_element_def
-{
-  struct bitmap_element_def *next;
-  unsigned int indx;
-} bitmap_element;
-
-
-
-
-
-
-
-
-
-unsigned char
-bitmap_ior_and_compl (bitmap dst, const_bitmap a, const_bitmap b,
-		      const_bitmap kill)
-{
-  unsigned char changed = 0;
-
-  bitmap_element *dst_elt;
-  const bitmap_element *a_elt, *b_elt, *kill_elt, *dst_prev;
-
-  while (a_elt || b_elt)
-    {
-      unsigned char new_element = 0;
-
-      if (b_elt)
-	while (kill_elt && kill_elt->indx < b_elt->indx)
-	  kill_elt = kill_elt->next;
-
-      if (b_elt && kill_elt && kill_elt->indx == b_elt->indx
-	  && (!a_elt || a_elt->indx >= b_elt->indx))
-	{
-	  bitmap_element tmp_elt;
-	  unsigned ix;
-
-	  BITMAP_WORD ior = 0;
-
-	      changed = bitmap_elt_ior (dst, dst_elt, dst_prev,
-					a_elt, &tmp_elt, changed);
-
-	}
-
-    }
-
-
-  return changed;
-}
-/* The block starting the second conditional has  3 incoming edges,
-   we should thread all three, but due to a bug in the threading
-   code we missed the edge when the first conditional is false
-   (b_elt is zero, which means the second conditional is always
-   zero.  VRP1 catches all three.  */
-/* { dg-final { scan-tree-dump-times "Registering jump thread" 2 "vrp-thread1" } } */
-/* { dg-final { scan-tree-dump-times "Path crosses loops" 1 "vrp-thread1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
deleted file mode 100644
index b0a7d42..0000000
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
+++ /dev/null
@@ -1,44 +0,0 @@
-/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread1-details -fdump-tree-thread3-details" } */
-
-/* { dg-final { scan-tree-dump-times "Registering jump" 6 "thread1" } } */
-/* { dg-final { scan-tree-dump-times "Registering jump" 1 "thread3" } } */
-
-int sum0, sum1, sum2, sum3;
-int foo (char *s, char **ret)
-{
-  int state=0;
-  char c;
-
-  for (; *s && state != 4; s++)
-    {
-      c = *s;
-      if (c == '*')
-	{
-	  s++;
-	  break;
-	}
-      switch (state)
-	{
-	case 0:
-	  if (c == '+')
-	    state = 1;
-	  else if (c != '-')
-	    sum0+=c;
-	  break;
-	case 1:
-	  if (c == '+')
-	    state = 2;
-	  else if (c == '-')
-	    state = 0;
-	  else
-	    sum1+=c;
-	  break;
-	default:
-	  break;
-	}
-
-    }
-  *ret = s;
-  return state;
-}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
index 16abcde..ee17edd 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
@@ -1,15 +1,15 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread1-stats -fdump-tree-thread2-stats -fdump-tree-dom2-stats -fdump-tree-thread3-stats -fdump-tree-dom3-stats -fdump-tree-vrp2-stats -fno-guess-branch-probability" } */
+/* { dg-options "-O2 -fdump-tree-dom2-stats -fdump-tree-thread3-stats -fdump-tree-dom3-stats -fdump-tree-vrp-thread2-stats -fno-guess-branch-probability" } */
 
-/* { dg-final { scan-tree-dump "Jumps threaded: 12"  "thread1" } } */
-/* { dg-final { scan-tree-dump "Jumps threaded: 5" "thread3" { target { ! aarch64*-*-* } } } } */
 /* { dg-final { scan-tree-dump-not "Jumps threaded"  "dom2" } } */
 
 /* aarch64 has the highest CASE_VALUES_THRESHOLD in GCC.  It's high enough
    to change decisions in switch expansion which in turn can expose new
    jump threading opportunities.  Skip the later tests on aarch64.  */
 /* { dg-final { scan-tree-dump-not "Jumps threaded"  "dom3" { target { ! aarch64*-*-* } } } } */
-/* { dg-final { scan-tree-dump-not "Jumps threaded"  "vrp2" { target { ! aarch64*-*-* } } } } */
+/* { dg-final { scan-tree-dump-not "Jumps threaded"  "vrp-thread2" { target { ! aarch64*-*-* } } } } */
+/* { dg-final { scan-tree-dump "Jumps threaded: 11"  "thread3" { target { ! aarch64*-*-* } } } } */
+/* { dg-final { scan-tree-dump "Jumps threaded: 18"  "thread3" { target { aarch64*-*-* } } } } */
 
 enum STATE {
   S0=0,
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-97.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-97.c
new file mode 100644
index 0000000..2f09c8b
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-97.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* ethread threading does not yet catch this but it might at some point.  */
+/* { dg-options "-O -fdump-tree-fre1-details -fno-thread-jumps" } */
+
+int foo (int b, int x)
+{
+  int i, j;
+  if (b)
+    i = x;
+  if (b)
+    j = x;
+  return j == i;
+}
+
+/* Even with different undefs we should CSE a PHI node with the
+   same controlling condition.  */
+
+/* { dg-final { scan-tree-dump "Replaced redundant PHI node" "fre1" } } */
+/* { dg-final { scan-tree-dump "return 1;" "fre1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c
deleted file mode 100644
index 672a54e..0000000
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-vrp2-details --param logical-op-non-short-circuit=1" } */
-/* { dg-additional-options "-fdisable-tree-ethread -fdisable-tree-thread1 -fdisable-tree-thread2" } */
-/* { dg-final { scan-tree-dump-not "IRREDUCIBLE_LOOP" "vrp2" } } */
-
-void abort (void);
-typedef struct bitmap_head_def *bitmap;
-typedef const struct bitmap_head_def *const_bitmap;
-typedef struct bitmap_obstack
-{
-  struct bitmap_obstack *next;
-  unsigned int indx;
-}
-bitmap_element;
-typedef struct bitmap_head_def
-{
-  bitmap_element *first;
-}
-bitmap_head;
-static __inline__ unsigned char
-bitmap_elt_ior (bitmap dst, bitmap_element * dst_elt,
-		bitmap_element * dst_prev, const bitmap_element * a_elt,
-		const bitmap_element * b_elt)
-{
-  ((void) (!(a_elt || b_elt) ? abort (), 0 : 0));
-}
-
-unsigned char
-bitmap_ior_and_compl (bitmap dst, const_bitmap a, const_bitmap b,
-		      const_bitmap kill)
-{
-  bitmap_element *dst_elt = dst->first;
-  const bitmap_element *a_elt = a->first;
-  const bitmap_element *b_elt = b->first;
-  const bitmap_element *kill_elt = kill->first;
-  bitmap_element *dst_prev = ((void *) 0);
-  while (a_elt || b_elt)
-    {
-      if (b_elt && kill_elt && kill_elt->indx == b_elt->indx
-	  && (!a_elt || a_elt->indx >= b_elt->indx));
-      else
-	{
-	  bitmap_elt_ior (dst, dst_elt, dst_prev, a_elt, b_elt);
-	  if (a_elt && b_elt && a_elt->indx == b_elt->indx)
-	    ;
-	  else if (a_elt && (!b_elt || a_elt->indx <= b_elt->indx))
-	    a_elt = a_elt->next;
-	}
-    }
-}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
deleted file mode 100644
index 08c0b8d..0000000
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
+++ /dev/null
@@ -1,73 +0,0 @@
-/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread3-details -fdump-tree-thread4-details -fno-finite-loops --param early-inlining-insns=14 -fno-inline-functions" } */
-/* { dg-final { scan-tree-dump "Registering jump thread" "thread3" } } */
-/* { dg-final { scan-tree-dump "Registering jump thread" "thread4" } } */
-
-typedef struct bitmap_head_def *bitmap;
-typedef const struct bitmap_head_def *const_bitmap;
-typedef struct VEC_int_base
-{
-}
-VEC_int_base;
-typedef struct VEC_int_heap
-{
-  VEC_int_base base;
-}
-VEC_int_heap;
-typedef unsigned long BITMAP_WORD;
-typedef struct bitmap_element_def
-{
-  struct bitmap_element_def *next;
-  unsigned int indx;
-}
-bitmap_element;
-typedef struct bitmap_head_def
-{
-}
-bitmap_head;
-typedef struct
-{
-  bitmap_element *elt1;
-  bitmap_element *elt2;
-  BITMAP_WORD bits;
-}
-bitmap_iterator;
-static __inline__ void
-bmp_iter_and_compl_init (bitmap_iterator * bi, const_bitmap map1,
-			 const_bitmap map2, unsigned start_bit,
-			 unsigned *bit_no)
-{
-}
-
-static __inline__ void
-bmp_iter_next (bitmap_iterator * bi, unsigned *bit_no)
-{
-}
-
-static __inline__ unsigned char
-bmp_iter_and_compl (bitmap_iterator * bi, unsigned *bit_no)
-{
-  if (bi->bits)
-    {
-      while (bi->elt2 && bi->elt2->indx < bi->elt1->indx)
-	bi->elt2 = bi->elt2->next;
-    }
-}
-
-extern int VEC_int_base_length (VEC_int_base *);
-bitmap
-compute_idf (bitmap def_blocks, bitmap_head * dfs)
-{
-  bitmap_iterator bi;
-  unsigned bb_index, i;
-  VEC_int_heap *work_stack;
-  bitmap phi_insertion_points;
-  while ((VEC_int_base_length (((work_stack) ? &(work_stack)->base : 0))) > 0)
-    {
-      for (bmp_iter_and_compl_init
-	   (&(bi), (&dfs[bb_index]), (phi_insertion_points), (0), &(i));
-	   bmp_iter_and_compl (&(bi), &(i)); bmp_iter_next (&(bi), &(i)))
-	{
-	}
-    }
-}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-backedge.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-backedge.c
new file mode 100644
index 0000000..890a0ee
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-backedge.c
@@ -0,0 +1,32 @@
+// { dg-do compile }
+// { dg-options "-O2 -fdisable-tree-ethread -fdisable-tree-thread1 -fdisable-tree-thread2 -fno-tree-dominator-opts -fdump-tree-thread3-details" }
+
+// Test that we can thread jumps across the backedge of a loop through
+// the switch statement to a particular case.
+//
+// Just in case, we disable all the jump threaders before loop
+// optimizations to make sure we get a clean stab at this.
+
+int foo (unsigned int x, int s)
+{
+  while (s != 999)
+    {
+      switch (s)
+	{
+	case 0:
+	  if (x)
+	    s = 1;
+	  break;
+	case 1:
+	  if (x)
+	    s = 999;
+	  break;
+	default:
+	  break;
+	}
+      x++;
+    }
+  return s;
+}
+
+// { dg-final { scan-tree-dump "Registering jump thread:.*normal \\(back\\)" "thread3" } }
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-invalid.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-invalid.c
new file mode 100644
index 0000000..bd56a62
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-invalid.c
@@ -0,0 +1,102 @@
+// { dg-do compile }
+// { dg-options "-O2 -fgimple -fdump-statistics" }
+//
+// This is a collection of seemingly threadble paths that should not be allowed.
+
+void foobar (int);
+
+// Possible thread from 2->4->3, but it would rotate the loop.
+void __GIMPLE (ssa)
+f1 ()
+{
+  int i;
+
+  // Pre-header.
+  __BB(2):
+  goto __BB4;
+
+  // Latch.
+  __BB(3):
+  foobar (i_1);
+  i_5 = i_1 + 1;
+  goto __BB4;
+
+  __BB(4,loop_header(1)):
+  i_1 = __PHI (__BB2: 0, __BB3: i_5);
+  if (i_1 != 101)
+    goto __BB3;
+  else
+    goto __BB5;
+
+  __BB(5):
+  return;
+
+}
+
+// Possible thread from 2->3->5 but threading through the empty latch
+// would create a non-empty latch.
+void __GIMPLE (ssa)
+f2 ()
+{
+  int i;
+
+  // Pre-header.
+  __BB(2):
+  goto __BB3;
+
+  __BB(3,loop_header(1)):
+  i_8 = __PHI (__BB5: i_5, __BB2: 0);
+  foobar (i_8);
+  i_5 = i_8 + 1;
+  if (i_5 != 256)
+    goto __BB5;
+  else
+    goto __BB4;
+
+  // Latch.
+  __BB(5):
+  goto __BB3;
+
+  __BB(4):
+  return;
+
+}
+
+// Possible thread from 3->5->6->3 but this would thread through the
+// header but not exit the loop.
+int __GIMPLE (ssa)
+f3 (int a)
+{
+  int i;
+
+  __BB(2):
+  goto __BB6;
+
+  __BB(3):
+  if (i_1 != 0)
+    goto __BB4;
+  else
+    goto __BB5;
+
+  __BB(4):
+  foobar (5);
+  goto __BB5;
+
+  // Latch.
+  __BB(5):
+  i_7 = i_1 + 1;
+  goto __BB6;
+
+  __BB(6,loop_header(1)):
+  i_1 = __PHI (__BB2: 1, __BB5: i_7);
+  if (i_1 <= 99)
+    goto __BB3;
+  else
+    goto __BB7;
+
+  __BB(7):
+  return;
+
+}
+
+// { dg-final { scan-tree-dump-not "Jumps threaded" "statistics" } }
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-vrp-thread-1.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-vrp-thread-1.c
index 86d07ef..f3ca140 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-vrp-thread-1.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-vrp-thread-1.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-vrp-thread1-details -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fdump-tree-thread1-details -fdelete-null-pointer-checks" } */
 /* { dg-skip-if "" keeps_null_pointer_checks } */
 
 void oof (void);
@@ -29,5 +29,5 @@ build_omp_regions_1 (basic_block bb, struct omp_region *parent,
 
 /* ARM Cortex-M defined LOGICAL_OP_NON_SHORT_CIRCUIT to false,
    so skip below test.  */
-/* { dg-final { scan-tree-dump-times "Threaded" 1 "vrp-thread1" { target { ! arm_cortex_m } } } } */
+/* { dg-final { scan-tree-dump-times "Registering jump thread" 1 "thread1" { target { ! arm_cortex_m } } } } */
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/vrp08.c b/gcc/testsuite/gcc.dg/tree-ssa/vrp08.c
index c2da30b..2c6742b 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/vrp08.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/vrp08.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fno-tree-fre -fdisable-tree-evrp -fdump-tree-vrp1-details -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fno-tree-fre -fdisable-tree-evrp -fdump-tree-vrp1-details -fdisable-tree-thread1 -fdelete-null-pointer-checks" } */
 
 /* Compile with -fno-tree-fre -O2 to prevent CSEing *p.  */
 int
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/vrp55.c b/gcc/testsuite/gcc.dg/tree-ssa/vrp55.c
index a478a69..0ef57d9 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/vrp55.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/vrp55.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-vrp-thread1-blocks-vops-details -fdelete-null-pointer-checks" } */
+/* { dg-options "-O2 -fdump-tree-ethread-details -fdelete-null-pointer-checks" } */
 
 void arf (void);
 
@@ -12,6 +12,6 @@ fu (char *p, int x)
     arf ();
 }
 
-/* { dg-final { scan-tree-dump-times "Threaded jump" 1 "vrp-thread1" { target { ! keeps_null_pointer_checks } } } } */
-/* { dg-final { scan-tree-dump-times "Threaded jump" 0 "vrp-thread1" { target {   keeps_null_pointer_checks } } } } */
+/* { dg-final { scan-tree-dump-times "Registering jump thread" 1 "ethread" { target { ! keeps_null_pointer_checks } } } } */
+/* { dg-final { scan-tree-dump-times "Registering jump thread" 0 "ethread" { target {   keeps_null_pointer_checks } } } } */
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/vrp98-1.c b/gcc/testsuite/gcc.dg/tree-ssa/vrp98-1.c
new file mode 100644
index 0000000..daa3f07
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/vrp98-1.c
@@ -0,0 +1,41 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target int128 } */
+/* { dg-options "-Os -fdump-tree-evrp-details" } */
+
+#include <stdint.h>
+#include <limits.h>
+
+typedef unsigned int word __attribute__((mode(word)));
+typedef unsigned __int128 bigger_than_word;
+
+int
+foo (bigger_than_word a, word b, uint8_t c)
+{
+  /* Must fold use of t1 into use of b, as b is no wider than word_mode. */
+  const uint8_t t1 = b % UCHAR_MAX;
+
+  /* Must NOT fold use of t2 into use of a, as a is wider than word_mode. */
+  const uint8_t t2 = a % UCHAR_MAX;
+
+  /* Must fold use of t3 into use of c, as c is narrower than t3. */
+  const uint32_t t3 = (const uint32_t)(c >> 1);
+
+  uint16_t ret = 0;
+
+  if (t1 == 1)
+    ret = 20;
+  else if (t2 == 2)
+    ret = 30;
+  else if (t3 == 3)
+    ret = 40;
+  /* Th extra condition below is necessary to prevent a prior pass from
+     folding away the cast. Ignored in scan-tree-dump. */
+  else if (t3 == 4)
+    ret = 50;
+
+  return ret;
+}
+
+/* { dg-final { scan-tree-dump "Folded into: if \\(_\[0-9\]+ == 1\\)" "evrp" } } */
+/* { dg-final { scan-tree-dump-not "Folded into: if \\(_\[0-9\]+ == 2\\)" "evrp" } } */
+/* { dg-final { scan-tree-dump "Folded into: if \\(_\[0-9\]+ == 3\\)" "evrp" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/vrp98.c b/gcc/testsuite/gcc.dg/tree-ssa/vrp98.c
index 982f091..78d3bba 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/vrp98.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/vrp98.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target int128 } */
-/* { dg-options "-Os -fdump-tree-vrp1-details" } */
+/* { dg-options "-Os -fdisable-tree-evrp -fdump-tree-vrp1-details" } */
 
 #include <stdint.h>
 #include <limits.h>