gcc/gcc10-pr94308.patch

53 lines
1.5 KiB
Diff

2020-03-25 Jakub Jelinek <jakub@redhat.com>
PR target/94308
* config/i386/i386-features.c (ix86_add_reg_usage_to_vzeroupper): Set
INSN_CODE (insn) to -1 when changing the pattern.
* gcc.target/i386/pr94308.c: New test.
--- gcc/config/i386/i386-features.c.jj 2020-03-17 13:50:52.955933209 +0100
+++ gcc/config/i386/i386-features.c 2020-03-24 19:19:17.801609289 +0100
@@ -1792,6 +1792,7 @@ ix86_add_reg_usage_to_vzeroupper (rtx_in
RTVEC_ELT (vec, j) = gen_rtx_SET (reg, reg);
}
XVEC (pattern, 0) = vec;
+ INSN_CODE (insn) = -1;
df_insn_rescan (insn);
}
--- gcc/testsuite/gcc.target/i386/pr94308.c.jj 2020-03-24 19:32:51.964436310 +0100
+++ gcc/testsuite/gcc.target/i386/pr94308.c 2020-03-24 19:32:39.848617482 +0100
@@ -0,0 +1,31 @@
+/* PR target/94308 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mfpmath=sse -mavx2 -mfma" } */
+
+#include <x86intrin.h>
+
+void
+foo (float *x, const float *y, const float *z, unsigned int w)
+{
+ unsigned int a;
+ const unsigned int b = w / 8;
+ const float *c = y;
+ const float *d = z;
+ __m256 e = _mm256_setzero_ps ();
+ __m256 f, g;
+ for (a = 0; a < b; a++)
+ {
+ f = _mm256_loadu_ps (c);
+ g = _mm256_loadu_ps (d);
+ c += 8;
+ d += 8;
+ e = _mm256_fmadd_ps (f, g, e);
+ }
+ __attribute__ ((aligned (32))) float h[8];
+ _mm256_storeu_ps (h, e);
+ _mm256_zeroupper ();
+ float i = h[0] + h[1] + h[2] + h[3] + h[4] + h[5] + h[6] + h[7];
+ for (a = b * 8; a < w; a++)
+ i += (*c++) * (*d++);
+ *x = i;
+}