diff mbox series

[2/2] rs6000: Add test for _mm_minpos_epu16

Message ID 20210602221316.202627-3-pc@us.ibm.com
State New
Headers show
Series rs6000: Add support for _mm_minpos_epu16 | expand

Commit Message

Paul A. Clarke June 2, 2021, 10:13 p.m. UTC 
Copy the test for _mm_minpos_epu16 from
gcc/testsuite/gcc.target/i386/sse4_1-phminposuw.c, with
a few adjustments:

- Adjust the dejagnu directives for powerpc platform.
- Make the data not be monotonically increasing,
  such that some of the returned values are not
  always the first value (index 0).
- Fix a masking issue where the index was being truncated
  to 2 bits instead of 3 bits, which wasn't found because
  all of the returned indicies were 0 with the original
  generated data.
- Support big-endian.

2021-06-02  Paul A. Clarke  <pc@us.ibm.com>

gcc/testsuite/ChangeLog:
        * gcc.target/powerpc/sse4_1-phminposuw.c: Copy from
        gcc/testsuite/gcc.target/i386, make more robust.
---
 .../gcc.target/powerpc/sse4_1-phminposuw.c    | 63 +++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-phminposuw.c

Comments

Segher Boessenkool June 3, 2021, 1:50 a.m. UTC | #1 
On Wed, Jun 02, 2021 at 05:13:16PM -0500, Paul A. Clarke wrote:
> +  for (i = 0; i < NUM; i++)
> +    src.s[i] = i * i - 68 * i + 1200;

Could you do tests with some identical elements as well?  Because that
is where I think it fails on BE currently.


Segher
Paul A. Clarke June 3, 2021, 6:01 p.m. UTC | #2 
On Wed, Jun 02, 2021 at 08:50:56PM -0500, Segher Boessenkool wrote:
> On Wed, Jun 02, 2021 at 05:13:16PM -0500, Paul A. Clarke wrote:
> > +  for (i = 0; i < NUM; i++)
> > +    src.s[i] = i * i - 68 * i + 1200;
> 
> Could you do tests with some identical elements as well?  Because that
> is where I think it fails on BE currently.

Let me re-do the test case a bit more to provide a better set of
input data, rather than this computational attempt which misses a
bunch of interesting cases.

I'll send a v2 in a bit.

PC
diff mbox series

Patch

diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-phminposuw.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-phminposuw.c
new file mode 100644
index 000000000000..0b6318500b1e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-phminposuw.c
@@ -0,0 +1,63 @@ 
+/* { dg-do run } */
+/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+#ifndef CHECK_H
+#define CHECK_H "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK_H
+
+#include <smmintrin.h>
+
+#define NUM 64
+
+static void
+TEST (void)
+{
+  union
+    {
+      __m128i x[NUM/8];
+      unsigned short s[NUM];
+    } src;
+  unsigned short minVal[NUM/8];
+  int minInd[NUM/8];
+  unsigned short minValScalar, minIndScalar;
+  int i, j;
+  union
+    {
+      int i;
+      unsigned short s[2];
+    } res;
+
+  for (i = 0; i < NUM; i++)
+    src.s[i] = i * i - 68 * i + 1200;
+
+  for (i = 0, j = 0; i < NUM; i += 8, j++)
+    {
+      res.i = _mm_cvtsi128_si32 (_mm_minpos_epu16 (src.x [i/8]));
+      minVal[j] = res.s[0];
+      minInd[j] = res.s[1] & 0b111;
+    }
+
+  for (i = 0; i < NUM; i += 8)
+    {
+      minValScalar = src.s[i];
+      minIndScalar = 0;
+
+      for (j = i + 1; j < i + 8; j++)
+	if (minValScalar > src.s[j])
+	  {
+	    minValScalar = src.s[j];
+	    minIndScalar = j - i;
+	  }
+
+      if (minValScalar != minVal[i/8] && minIndScalar != minInd[i/8])
+	abort ();
+    }
+}