x86: Add tests for piecewise move and store

* gcc.target/i386/pieces-memcpy-10.c: New test.
	* gcc.target/i386/pieces-memcpy-11.c: Likewise.
	* gcc.target/i386/pieces-memcpy-12.c: Likewise.
	* gcc.target/i386/pieces-memcpy-13.c: Likewise.
	* gcc.target/i386/pieces-memcpy-14.c: Likewise.
	* gcc.target/i386/pieces-memcpy-15.c: Likewise.
	* gcc.target/i386/pieces-memcpy-16.c: Likewise.
	* gcc.target/i386/pieces-memset-1.c: Likewise.
	* gcc.target/i386/pieces-memset-2.c: Likewise.
	* gcc.target/i386/pieces-memset-3.c: Likewise.
	* gcc.target/i386/pieces-memset-4.c: Likewise.
	* gcc.target/i386/pieces-memset-5.c: Likewise.
	* gcc.target/i386/pieces-memset-6.c: Likewise.
	* gcc.target/i386/pieces-memset-7.c: Likewise.
	* gcc.target/i386/pieces-memset-8.c: Likewise.
	* gcc.target/i386/pieces-memset-9.c: Likewise.
	* gcc.target/i386/pieces-memset-10.c: Likewise.
	* gcc.target/i386/pieces-memset-11.c: Likewise.
	* gcc.target/i386/pieces-memset-12.c: Likewise.
	* gcc.target/i386/pieces-memset-13.c: Likewise.
	* gcc.target/i386/pieces-memset-14.c: Likewise.
	* gcc.target/i386/pieces-memset-15.c: Likewise.
	* gcc.target/i386/pieces-memset-16.c: Likewise.
	* gcc.target/i386/pieces-memset-17.c: Likewise.
	* gcc.target/i386/pieces-memset-18.c: Likewise.
	* gcc.target/i386/pieces-memset-19.c: Likewise.
	* gcc.target/i386/pieces-memset-20.c: Likewise.
	* gcc.target/i386/pieces-memset-21.c: Likewise.
	* gcc.target/i386/pieces-memset-22.c: Likewise.
	* gcc.target/i386/pieces-memset-23.c: Likewise.
	* gcc.target/i386/pieces-memset-24.c: Likewise.
	* gcc.target/i386/pieces-memset-25.c: Likewise.
	* gcc.target/i386/pieces-memset-26.c: Likewise.
	* gcc.target/i386/pieces-memset-27.c: Likewise.
	* gcc.target/i386/pieces-memset-28.c: Likewise.
	* gcc.target/i386/pieces-memset-29.c: Likewise.
	* gcc.target/i386/pieces-memset-30.c: Likewise.
	* gcc.target/i386/pieces-memset-31.c: Likewise.
	* gcc.target/i386/pieces-memset-32.c: Likewise.
	* gcc.target/i386/pieces-memset-33.c: Likewise.
	* gcc.target/i386/pieces-memset-34.c: Likewise.
	* gcc.target/i386/pieces-memset-35.c: Likewise.
	* gcc.target/i386/pieces-memset-36.c: Likewise.
	* gcc.target/i386/pieces-memset-37.c: Likewise.
	* gcc.target/i386/pieces-memset-38.c: Likewise.
	* gcc.target/i386/pieces-memset-39.c: Likewise.
	* gcc.target/i386/pieces-memset-40.c: Likewise.
	* gcc.target/i386/pieces-memset-41.c: Likewise.
	* gcc.target/i386/pieces-memset-42.c: Likewise.
	* gcc.target/i386/pieces-memset-43.c: Likewise.
	* gcc.target/i386/pieces-memset-44.c: Likewise.

gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-11.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 64);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 64);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-13.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -mtune=generic" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 66);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu64\[ \\t\]+\[^\n\]*%zmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-14.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 33);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-16.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 34);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-7.c

@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+void
+foo (int a1, int a2, int a3, int a4, int a5, int a6, char *dst, char *src)
+{
+  __builtin_memcpy (dst, src, 17);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-8.c

@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
+
+void
+foo (int a1, int a2, int a3, int a4, int a5, int a6, char *dst, char *src)
+{
+  __builtin_memcpy (dst, src, 18);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memcpy-9.c

@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -mtune=generic" } */
+
+void
+foo (int a1, int a2, int a3, int a4, int a5, int a6, char *dst, char *src)
+{
+  __builtin_memcpy (dst, src, 19);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-1.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 64);
+}
+
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-10.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 64);
+}
+
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-11.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 64);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-12.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 66);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu64\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-13.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 33);
+}
+
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-14.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-15.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-16.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 17);
+}
+
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-17.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 17);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-18.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 3, 18);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-19.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 64);
+}
+
+/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-2.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 64);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */

gcc/testsuite/gcc.target/i386/pieces-memset-20.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 64);
+}
+
+/* { dg-final { scan-assembler-times "vpxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-21.c

@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512vl -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 66);
+}
+
+/* { dg-final { scan-assembler-times "vpxor(?:d|)\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu(?:64|8)\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* { dg-final { scan-assembler-not "vzeroupper" } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-22.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 33);
+}
+
+/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-23.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 33);
+}
+
+/* { dg-final { scan-assembler-times "vpxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-24.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 33);
+}
+
+/* { dg-final { scan-assembler-times "vpxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-25.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 17);
+}
+
+/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-26.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 17);
+}
+
+/* { dg-final { scan-assembler-times "pxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-27.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 17);
+}
+
+/* { dg-final { scan-assembler-times "vpxor(?:d|)\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu(?:64|8|)\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-28.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 64);
+}
+
+/* { dg-final { scan-assembler-times "pcmpeqd\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-29.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 64);
+}
+
+/* { dg-final { scan-assembler-not "vpcmpeqd\[ \\t\]+\[^\n\]*%ymm" } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-3.c

@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512bw -mno-avx512vl -mavx512f -mtune=intel" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 66);
+}
+
+/* { dg-final { scan-assembler-times "vpbroadcastb\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* { dg-final { scan-assembler-times "vinserti64x4\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu64\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" { target { ! ia32 } } } } */

gcc/testsuite/gcc.target/i386/pieces-memset-30.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 64);
+}
+
+/* { dg-final { scan-assembler-times "vpcmpeqd\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-31.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 66);
+}
+
+/* { dg-final { scan-assembler-times "vpternlogd\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu64\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-32.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 33);
+}
+
+/* { dg-final { scan-assembler-times "pcmpeqd\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-33.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 33);
+}
+
+/* { dg-final { scan-assembler-not "vpcmpeqd\[ \\t\]+\[^\n\]*%ymm" } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-34.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 33);
+}
+
+/* { dg-final { scan-assembler-times "vpcmpeqd\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-35.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 34);
+}
+
+/* { dg-final { scan-assembler-times "vpcmpeqd\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-36.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 17);
+}
+
+/* { dg-final { scan-assembler-times "vpbroadcastb\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-37.c

@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=generic" } */
+
+void
+foo (int a1, int a2, int a3, int a4, int a5, int a6, int x, char *dst)
+{
+  __builtin_memset (dst, x, 66);
+}
+
+/* { dg-final { scan-assembler-times "vpbroadcastb\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-38.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=sandybridge" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 33);
+}
+
+/* { dg-final { scan-assembler-times "vpcmpeqd\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-39.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512bw -mtune=generic" } */
+
+void
+foo (int a1, int a2, int a3, int a4, int a5, int a6, int x, char *dst)
+{
+  __builtin_memset (dst, x, 66);
+}
+
+/* { dg-final { scan-assembler-times "vpbroadcastb\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* { dg-final { scan-assembler-not "vinserti64x4" } } */
+/* { dg-final { scan-assembler-times "vmovdqu8\[ \\t\]+\[^\n\]*%zmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-4.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 33);
+}
+
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-40.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx512f -mavx2 -mtune=sandybridge" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 66);
+}
+
+/* { dg-final { scan-assembler-times "vpbroadcastb\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-41.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-42.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 33);
+}
+
+/* { dg-final { scan-assembler-times "vpxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-43.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=sandybridge" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, -1, 33);
+}
+
+/* { dg-final { scan-assembler-times "vpcmpeqd\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 2 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-44.c

@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 48);
+}
+
+/* { dg-final { scan-assembler-times "vpxor\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-5.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=haswell" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */

gcc/testsuite/gcc.target/i386/pieces-memset-6.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=intel" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 33);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" { target { ! ia32 } } } } */

gcc/testsuite/gcc.target/i386/pieces-memset-7.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 17);
+}
+
+/* { dg-final { scan-assembler-times "movups\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-8.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-avx2 -mavx -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 17);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */

gcc/testsuite/gcc.target/i386/pieces-memset-9.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx512f -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int x)
+{
+  __builtin_memset (dst, x, 17);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%xmm" 1 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
+/* Nor use a frame pointer.  */
+/* { dg-final { scan-assembler-not "%\[re\]bp" } } */