With the following testcase, on AMDGCN with -Ofast:
void
foo (float* output, float* input)
{
for (int i = 0; i < 1024 * 1024; i++) {
output[i] = __builtin_sinf (input[i]) + __builtin_cosf (input[i]);
}
}
... the following ICE happens:
during GIMPLE pass: sincos
test.cpp: In function 'void foo(float*, float*)':
test.cpp:2:1: internal compiler error: Segmentation fault
2 | foo (float* output, float* input)
| ^~~
[... snipped ...]
0x17befb8 types_compatible_p(tree_node*, tree_node*)
gcc/gimple-expr.h:67
0x17befb8 execute_cse_sincos_1
gcc/tree-ssa-math-opts.cc:1299
0x17befb8 execute
gcc/tree-ssa-math-opts.cc:2248
This happens because the vect pass converted the testcase into:
vect__4.6_40 = MEM <vector(64) float> [(float *)vectp_input.4_38];
vect__6.8_42 = .COS (vect__4.6_40);
vect__5.7_41 = .SIN (vect__4.6_40);
vect__8.9_43 = vect__5.7_41 + vect__6.8_42;
Then, sincos attempts to find the type of the IFN_SIN/IFN_COS via
mathfn_built_in_type. This fails, so the compiler crashes.
For these IFNs, their input type is the same as their output type, so
we can fall back to that.
Note that, currently, GCC can't seem to handle vector sincos/cexpi
operations, so any attempt to CSE these will fail quickly after. This
patch does not fix that, only the ICE that happens in the attempt.
gcc/ChangeLog:
* tree-ssa-math-opts.cc (execute_cse_sincos_1): If
mathfn_built_in_type fails to determine a type for our
operation, presume that it is the same as the input type.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/sincos-ice-on-ifn_sin-call.c: New test.
* gcc.target/gcn/sincos-ice-on-ifn_sin-call-1.c: New test.
---
Reg-strapped on x86_64-linux-gnu and amdgcn-amdhsa (when that finishes
running; I suspect it'll be fine).
OK for trunk?
.../tree-ssa/sincos-ice-on-ifn_sin-call.c | 19 +++++++++++++++++++
.../gcn/sincos-ice-on-ifn_sin-call-1.c | 13 +++++++++++++
gcc/tree-ssa-math-opts.cc | 12 +++++++++++-
3 files changed, 43 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/sincos-ice-on-ifn_sin-call.c
create mode 100644 gcc/testsuite/gcc.target/gcn/sincos-ice-on-ifn_sin-call-1.c
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/sincos-ice-on-ifn_sin-call.c
b/gcc/testsuite/gcc.dg/tree-ssa/sincos-ice-on-ifn_sin-call.c
new file mode 100644
index 000000000000..3a8c047502e0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/sincos-ice-on-ifn_sin-call.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O -fgimple" } */
+typedef float V __attribute__ ((vector_size (16)));
+
+void __GIMPLE (ssa, startwith ("sincos"))
+foo (float * output, const float * input)
+{
+ V a;
+ V b;
+ V c;
+ V d;
+
+ __BB(2):
+ a = __MEM <const V> (input);
+ b = .COS (a);
+ c = .SIN (a);
+ d = a + b;
+ return;
+}
diff --git a/gcc/testsuite/gcc.target/gcn/sincos-ice-on-ifn_sin-call-1.c
b/gcc/testsuite/gcc.target/gcn/sincos-ice-on-ifn_sin-call-1.c
new file mode 100644
index 000000000000..b787a49fb0e8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/gcn/sincos-ice-on-ifn_sin-call-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-Ofast" } */
+#include <math.h>
+
+/* This test is the original, platform-specific, version of
+ gcc.dg/tree-ssa/sincos-ice-on-ifn_sin-call.c. */
+void
+foo (float output[1024 * 1024], const float input[1024 * 1024])
+{
+ for (int i = 0; i < 1024 * 1024; i++) {
+ output[i] = __builtin_sinf (input[i]) + __builtin_cosf (input[i]);
+ }
+}
diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
index 04c9f2c07e92..f4c6c64a5375 100644
--- a/gcc/tree-ssa-math-opts.cc
+++ b/gcc/tree-ssa-math-opts.cc
@@ -1287,7 +1287,17 @@ execute_cse_sincos_1 (tree name)
continue;
}
- tree t = mathfn_built_in_type (gimple_call_combined_fn (use_stmt));
+ auto stmt_cfn = gimple_call_combined_fn (use_stmt);
+ tree t = mathfn_built_in_type (stmt_cfn);
+ if (!t)
+ {
+ /* mathfn_built_in_type does not handle internal functions, which may
+ also be CSE'd. For them, the input type is the same as the
+ output type. */
+ gcc_checking_assert (internal_fn_p (stmt_cfn));
+ t = TREE_TYPE (name);
+ }
+
if (!type)
{
type = t;
--
2.52.0
