re PR target/77476 ([AVX-512] illegal kmovb instruction on KNL)

PR target/77476
	* config/i386/i386.md (isa): Add x64_avx512bw.
	(*zero_extendsidi2): For alternative 11 use x64_avx512bw isa.
	(kmov_isa): New mode attr.
	(zero_extend<mode>di2): Use <kmov_isa> isa for the last alternative.
	(*zero_extend<mode>si2): Likewise.
	(*zero_extendqihi2): Use avx512dq isa for the last alternative.

	* gcc.target/i386/avx512f-pr77476.c: New test.
	* gcc.target/i386/avx512bw-pr77476.c: New test.
	* gcc.target/i386/avx512dq-pr77476.c: New test.

From-SVN: r240000

gcc/ChangeLog

@@ -1,3 +1,13 @@
+2016-09-05  Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/77476
+	* config/i386/i386.md (isa): Add x64_avx512bw.
+	(*zero_extendsidi2): For alternative 11 use x64_avx512bw isa.
+	(kmov_isa): New mode attr.
+	(zero_extend<mode>di2): Use <kmov_isa> isa for the last alternative.
+	(*zero_extend<mode>si2): Likewise.
+	(*zero_extendqihi2): Use avx512dq isa for the last alternative.
+
 2016-09-05  Gerald Pfeifer  <gerald@pfeifer.com>
 
 	* doc/invoke.texi (SPU Options): nops -> NOPs.

gcc/config/i386/i386.md

@@ -799,7 +799,7 @@
 		    sse2,sse2_noavx,sse3,sse4,sse4_noavx,avx,noavx,
 		    avx2,noavx2,bmi,bmi2,fma4,fma,avx512f,noavx512f,
 		    fma_avx512f,avx512bw,noavx512bw,avx512dq,noavx512dq,
-		    avx512vl,noavx512vl,x64_avx512dq"
+		    avx512vl,noavx512vl,x64_avx512dq,x64_avx512bw"
   (const_string "base"))
 
 (define_attr "enabled" ""
@@ -812,6 +812,8 @@
 	   (symbol_ref "TARGET_64BIT && TARGET_AVX")
 	 (eq_attr "isa" "x64_avx512dq")
 	   (symbol_ref "TARGET_64BIT && TARGET_AVX512DQ")
+	 (eq_attr "isa" "x64_avx512bw")
+	   (symbol_ref "TARGET_64BIT && TARGET_AVX512BW")
 	 (eq_attr "isa" "nox64") (symbol_ref "!TARGET_64BIT")
 	 (eq_attr "isa" "sse2") (symbol_ref "TARGET_SSE2")
 	 (eq_attr "isa" "sse2_noavx")
@@ -3735,12 +3737,14 @@
   [(set (attr "isa")
      (cond [(eq_attr "alternative" "0,1,2")
 	      (const_string "nox64")
-	    (eq_attr "alternative" "3,7,11")
+	    (eq_attr "alternative" "3,7")
 	      (const_string "x64")
 	    (eq_attr "alternative" "8")
 	      (const_string "x64_sse4")
 	    (eq_attr "alternative" "10")
 	      (const_string "sse2")
+	    (eq_attr "alternative" "11")
+	      (const_string "x64_avx512bw")
 	   ]
 	   (const_string "*")))
    (set (attr "type")
@@ -3804,6 +3808,9 @@
    (set (match_dup 4) (const_int 0))]
   "split_double_mode (DImode, &operands[0], 1, &operands[3], &operands[4]);")
 
+(define_mode_attr kmov_isa
+  [(QI "avx512dq") (HI "avx512f") (SI "avx512bw") (DI "avx512bw")])
+
 (define_insn "zero_extend<mode>di2"
   [(set (match_operand:DI 0 "register_operand" "=r,*r")
 	(zero_extend:DI
@@ -3812,7 +3819,8 @@
   "@
    movz{<imodesuffix>l|x}\t{%1, %k0|%k0, %1}
    kmov<mskmodesuffix>\t{%1, %k0|%k0, %1}"
-  [(set_attr "type" "imovx,mskmov")
+  [(set_attr "isa" "*,<kmov_isa>")
+   (set_attr "type" "imovx,mskmov")
    (set_attr "mode" "SI")])
 
 (define_expand "zero_extend<mode>si2"
@@ -3863,7 +3871,8 @@
   "@
    movz{<imodesuffix>l|x}\t{%1, %0|%0, %1}
    kmov<mskmodesuffix>\t{%1, %0|%0, %1}"
-  [(set_attr "type" "imovx,mskmov")
+  [(set_attr "isa" "*,<kmov_isa>")
+   (set_attr "type" "imovx,mskmov")
    (set_attr "mode" "SI,<MODE>")])
 
 (define_expand "zero_extendqihi2"
@@ -3914,6 +3923,7 @@
    movz{bl|x}\t{%1, %k0|%k0, %1}
    kmovb\t{%1, %k0|%k0, %1}"
   [(set_attr "type" "imovx,mskmov")
+   (set_attr "isa" "*,avx512dq")
    (set_attr "mode" "SI,QI")])
 
 (define_insn_and_split "*zext<mode>_doubleword_and"

gcc/testsuite/ChangeLog

@@ -1,5 +1,10 @@
 2016-09-05  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/77476
+	* gcc.target/i386/avx512f-pr77476.c: New test.
+	* gcc.target/i386/avx512bw-pr77476.c: New test.
+	* gcc.target/i386/avx512dq-pr77476.c: New test.
+
 	* lib/target-supports.exp (check_effective_target_vect_simd_clones):
 	Update comment to mention also avx512f.
 

gcc/testsuite/gcc.target/i386/avx512bw-pr77476.c

@@ -0,0 +1,9 @@
+/* PR target/77476 */
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw" } */
+/* { dg-require-effective-target avx512bw } */
+
+#include "avx512bw-check.h"
+#define PR77476_TEST avx512bw_test
+
+#include "avx512f-pr77476.c"

gcc/testsuite/gcc.target/i386/avx512dq-pr77476.c

@@ -0,0 +1,9 @@
+/* PR target/77476 */
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512dq" } */
+/* { dg-require-effective-target avx512dq } */
+
+#include "avx512dq-check.h"
+#define PR77476_TEST avx512dq_test
+
+#include "avx512f-pr77476.c"

gcc/testsuite/gcc.target/i386/avx512f-pr77476.c

@@ -0,0 +1,76 @@
+/* PR target/77476 */
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512f" } */
+/* { dg-require-effective-target avx512f } */
+
+#ifndef PR77476_TEST
+#include "avx512f-check.h"
+#define PR77476_TEST avx512f_test
+#endif
+
+unsigned short s;
+unsigned int i;
+unsigned long long l;
+
+void
+f1 (void)
+{
+  unsigned char a = 0xff;
+  asm volatile ("" : "+Yk" (a));
+  s = a;
+}
+
+void
+f2 (void)
+{
+  unsigned char a = 0xff;
+  asm volatile ("" : "+Yk" (a));
+  i = a;
+}
+
+void
+f3 (void)
+{
+  unsigned char a = 0xff;
+  asm volatile ("" : "+Yk" (a));
+  l = a;
+}
+
+void
+f4 (void)
+{
+  unsigned short a = 0xffff;
+  asm volatile ("" : "+Yk" (a));
+  i = a;
+}
+
+void
+f5 (void)
+{
+  unsigned short a = 0xffff;
+  asm volatile ("" : "+Yk" (a));
+  l = a;
+}
+
+#ifdef __AVX512BW__
+void
+f6 (void)
+{
+  unsigned int a = 0xffffffff;
+  asm volatile ("" : "+Yk" (a));
+  l = a;
+}
+#endif
+
+static void
+PR77476_TEST ()
+{
+  f1 (); if (s != 0xff) __builtin_abort (); s = 0;
+  f2 (); if (i != 0xff) __builtin_abort (); i = 0;
+  f3 (); if (l != 0xff) __builtin_abort (); l = 0;
+  f4 (); if (i != 0xffff) __builtin_abort (); i = 0;
+  f5 (); if (l != 0xffff) __builtin_abort (); l = 0;
+#ifdef __AVX512BW__
+  f6 (); if (l != 0xffffffff) __builtin_abort (); l = 0;
+#endif
+}