Split notl + pbraodcast + pand to pbroadcast + pandn more modes.

r12-5595-gc39d77f252e895306ef88c1efb3eff04e4232554 adds 2 splitter to
transform notl + pbroadcast + pand to pbroadcast + pandn for
VI124_AVX2 which leaves out all DI-element-size ones as
well as all 512-bit ones.
This patch extend the splitter to VI_AVX2 which will handle DImode for
AVX2, and V64QImode,V32HImode,V16SImode,V8DImode for AVX512.

gcc/ChangeLog:

	PR target/100711
	* config/i386/sse.md (*andnot<mode>3): Extend below splitter
	to VI_AVX2 to cover more modes.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr100711-2.c: Add v4di/v2di testcases.
	* gcc.target/i386/pr100711-3.c: New test.

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 0656a5ce71795eeac27a143f5f3637de247ab8c4..a92f50e96b592232056d582bfbbacd97fa8e7036 100644 (file)
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -17116,17 +17116,17 @@
 
 ;; PR target/100711: Split notl; vpbroadcastd; vpand as vpbroadcastd; vpandn
 (define_split
-  [(set (match_operand:VI124_AVX2 0 "register_operand")
-       (and:VI124_AVX2
-         (vec_duplicate:VI124_AVX2
+  [(set (match_operand:VI_AVX2 0 "register_operand")
+       (and:VI_AVX2
+         (vec_duplicate:VI_AVX2
            (not:<ssescalarmode>
              (match_operand:<ssescalarmode> 1 "register_operand")))
-         (match_operand:VI124_AVX2 2 "vector_operand")))]
+         (match_operand:VI_AVX2 2 "vector_operand")))]
   "TARGET_AVX2"
   [(set (match_dup 3)
-       (vec_duplicate:VI124_AVX2 (match_dup 1)))
+       (vec_duplicate:VI_AVX2 (match_dup 1)))
    (set (match_dup 0)
-       (and:VI124_AVX2 (not:VI124_AVX2 (match_dup 3))
+       (and:VI_AVX2 (not:VI_AVX2 (match_dup 3))
                        (match_dup 2)))]
   "operands[3] = gen_reg_rtx (<MODE>mode);")
 

diff --git a/gcc/testsuite/gcc.target/i386/pr100711-2.c b/gcc/testsuite/gcc.target/i386/pr100711-2.c
index ccaf1688e1923503e96dfe528b2de4f60f3a8f73..f75914fb7fc1d94e024f5adc80346823c0ce885d 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr100711-2.c
+++ b/gcc/testsuite/gcc.target/i386/pr100711-2.c
@@ -4,10 +4,12 @@
 typedef char v16qi __attribute__ ((vector_size (16)));
 typedef short v8hi __attribute__ ((vector_size (16)));
 typedef int v4si __attribute__ ((vector_size (16)));
+typedef long long v2di __attribute__((vector_size (16)));
 
 typedef char v32qi __attribute__ ((vector_size (32)));
 typedef short v16hi __attribute__ ((vector_size (32)));
 typedef int v8si __attribute__ ((vector_size (32)));
+typedef long long v4di __attribute__((vector_size (32)));
 
 v16qi foo_v16qi (char a, v16qi b)
 {
@@ -25,6 +27,11 @@ v4si foo_v4si (int a, v4si b)
     return (__extension__ (v4si) {~a, ~a, ~a, ~a}) & b;
 }
 
+v2di foo_v2di (long long a, v2di b)
+{
+    return (__extension__ (v2di) {~a, ~a}) & b;
+}
+
 v32qi foo_v32qi (char a, v32qi b)
 {
     return (__extension__ (v32qi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
@@ -44,4 +51,9 @@ v8si foo_v8si (int a, v8si b)
     return (__extension__ (v8si) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,}) & b;
 }
 
-/* { dg-final { scan-assembler-times "vpandn" 6 } } */
+v4di foo_v4di (long long a, v4di b)
+{
+    return (__extension__ (v4di) {~a, ~a, ~a, ~a}) & b;
+}
+
+/* { dg-final { scan-assembler-times "vpandn" 8 } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr100711-3.c b/gcc/testsuite/gcc.target/i386/pr100711-3.c
new file mode 100644 (file)
index 0000000..e90f2a4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr100711-3.c
@@ -0,0 +1,40 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512bw" } */
+
+typedef char v64qi __attribute__ ((vector_size (64)));
+typedef short v32hi __attribute__ ((vector_size (64)));
+typedef int v16si __attribute__ ((vector_size (64)));
+typedef long long v8di __attribute__((vector_size (64)));
+
+v64qi foo_v64qi (char a, v64qi b)
+{
+    return (__extension__ (v64qi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                  ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                  ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                  ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                  ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) & b;
+}
+
+v32hi foo_v32hi (short a, v32hi b)
+{
+    return (__extension__ (v32hi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                  ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) & b;
+}
+
+v16si foo_v16si (int a, v16si b)
+{
+    return (__extension__ (v16si) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                  ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) & b;
+}
+
+v8di foo_v8di (long long a, v8di b)
+{
+    return (__extension__ (v8di) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) & b;
+}
+
+/* { dg-final { scan-assembler-times "vpandn" 4 } } */