[X86] Ensure the _mm_test_all_ones macro does not reuse argument (PR60006)

[RKSimon]

Summary

The macro _mm_test_all_ones(V) was defined as _mm_testc_si128((V), _mm_cmpeq_epi32((V), (V))) - which could cause side effects depending on the source of the V value.

The _mm_cmpeq_epi32((V), (V)) trick was just to materialize an all-ones value, which can be more safely generated with _mm_set1_epi32(-1) .

Fixes #60006

[craig.topper]

LGTM

clang/lib/Headers/smmintrin.h

 /// \endcode
 ///
 /// This intrinsic corresponds to the <c> VPTEST / PTEST </c> instruction.
 ///
 /// \param V
 ///    A 128-bit integer vector containing the bits to be tested.
 /// \returns TRUE if the bits specified in the operand are all set to 1; FALSE
 ///    otherwise.
-#define _mm_test_all_ones(V) _mm_testc_si128((V), _mm_cmpeq_epi32((V), (V)))
+#define _mm_test_all_ones(V) _mm_testc_si128((V), _mm_set1_epi32(-1))
 
 /// Tests whether the specified bits in a 128-bit integer vector are
 ///    neither all zeros nor all ones.
 ///
 /// \headerfile <x86intrin.h>
 ///
 /// \code
 /// int _mm_test_mix_ones_zeros(__m128i M, __m128i V);

clang/test/CodeGen/X86/sse41-builtins.c

 
 // Make sure brackets work after macro intrinsics.
 float pr51324(__m128 a) {
   // CHECK-LABEL: pr51324
   // CHECK: call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %{{.*}}, i32 0)
   // CHECK: extractelement <4 x float> %{{.*}}, i32 0
   return _mm_round_ps(a, 0)[0];
 }
+
+// Ensure _mm_test_all_ones macro doesn't reuse argument
+__m128i expensive_call();
+int pr60006() {
+  // CHECK-LABEL: pr60006
+  // CHECK: call {{.*}} @expensive_call
+  // CHECK-NOT: call {{.*}} @expensive_call
+  // CHECK: call i32 @llvm.x86.sse41.ptestc(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
+  return _mm_test_all_ones(expensive_call());
+}