* config/i386/sse.md

	(<mask_codefor>avx512vl_shuf_<shuffletype>32x4_1<mask_name>): Rename
	to ...
	(avx512vl_shuf_<shuffletype>32x4_1<mask_name>): ... this.
	(*avx_vperm_broadcast_v4sf): Use v constraint instead of x.  Use
	maybe_evex prefix instead of vex.
	(*avx_vperm_broadcast_<mode>): Use v constraint instead of x.  Handle
	EXT_REX_SSE_REG_P (op0) case in the splitter.

	* gcc.target/i386/avx512vl-vbroadcast-3.c: New test.

From-SVN: r236763

4 files changed, 200 insertions, 6 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index a3c4d90..0bdd47e 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,14 @@
+2016-05-26  Jakub Jelinek  <jakub@redhat.com>
+
+	* config/i386/sse.md
+	(<mask_codefor>avx512vl_shuf_<shuffletype>32x4_1<mask_name>): Rename
+	to ...
+	(avx512vl_shuf_<shuffletype>32x4_1<mask_name>): ... this.
+	(*avx_vperm_broadcast_v4sf): Use v constraint instead of x.  Use
+	maybe_evex prefix instead of vex.
+	(*avx_vperm_broadcast_<mode>): Use v constraint instead of x.  Handle
+	EXT_REX_SSE_REG_P (op0) case in the splitter.
+
 2016-05-25  Jeff Law  <law@redhat.com>
 
 	PR tree-optimization/71272
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 2297ca2..c681098 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -12399,7 +12399,7 @@
   DONE;
 })
 
-(define_insn "<mask_codefor>avx512vl_shuf_<shuffletype>32x4_1<mask_name>"
+(define_insn "avx512vl_shuf_<shuffletype>32x4_1<mask_name>"
   [(set (match_operand:VI4F_256 0 "register_operand" "=v")
 	(vec_select:VI4F_256
 	  (vec_concat:<ssedoublemode>
@@ -17283,9 +17283,9 @@
 ;; If it so happens that the input is in memory, use vbroadcast.
 ;; Otherwise use vpermilp (and in the case of 256-bit modes, vperm2f128).
 (define_insn "*avx_vperm_broadcast_v4sf"
-  [(set (match_operand:V4SF 0 "register_operand" "=x,x,x")
+  [(set (match_operand:V4SF 0 "register_operand" "=v,v,v")
 	(vec_select:V4SF
-	  (match_operand:V4SF 1 "nonimmediate_operand" "m,o,x")
+	  (match_operand:V4SF 1 "nonimmediate_operand" "m,o,v")
 	  (match_parallel 2 "avx_vbroadcast_operand"
 	    [(match_operand 3 "const_int_operand" "C,n,n")])))]
   "TARGET_AVX"
@@ -17307,13 +17307,13 @@
   [(set_attr "type" "ssemov,ssemov,sselog1")
    (set_attr "prefix_extra" "1")
    (set_attr "length_immediate" "0,0,1")
-   (set_attr "prefix" "vex")
+   (set_attr "prefix" "maybe_evex")
    (set_attr "mode" "SF,SF,V4SF")])
 
 (define_insn_and_split "*avx_vperm_broadcast_<mode>"
-  [(set (match_operand:VF_256 0 "register_operand" "=x,x,x")
+  [(set (match_operand:VF_256 0 "register_operand" "=v,v,v")
 	(vec_select:VF_256
-	  (match_operand:VF_256 1 "nonimmediate_operand" "m,o,?x")
+	  (match_operand:VF_256 1 "nonimmediate_operand" "m,o,?v")
 	  (match_parallel 2 "avx_vbroadcast_operand"
 	    [(match_operand 3 "const_int_operand" "C,n,n")])))]
   "TARGET_AVX"
@@ -17345,6 +17345,23 @@
 
       /* Shuffle the lane we care about into both lanes of the dest.  */
       mask = (elt / (<ssescalarnum> / 2)) * 0x11;
+      if (EXT_REX_SSE_REG_P (op0))
+	{
+	  /* There is no EVEX VPERM2F128, but we can use either VBROADCASTSS
+	     or VSHUFF128.  */
+	  gcc_assert (<MODE>mode == V8SFmode);
+	  if ((mask & 1) == 0)
+	    emit_insn (gen_avx2_vec_dupv8sf (op0,
+					     gen_lowpart (V4SFmode, op0)));
+	  else
+	    emit_insn (gen_avx512vl_shuf_f32x4_1 (op0, op0, op0,
+						  GEN_INT (4), GEN_INT (5),
+						  GEN_INT (6), GEN_INT (7),
+						  GEN_INT (12), GEN_INT (13),
+						  GEN_INT (14), GEN_INT (15)));
+	  DONE;
+	}
+
       emit_insn (gen_avx_vperm2f128<mode>3 (op0, op0, op0, GEN_INT (mask)));
       DONE;
     }
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 8f1d5a7..fc925c3 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2016-05-26  Jakub Jelinek  <jakub@redhat.com>
+
+	* gcc.target/i386/avx512vl-vbroadcast-3.c: New test.
+
 2016-05-26  Jiong Wang  <jiong.wang@arm.com>
 
 	* gcc.target/aarch64/simd/vmul_elem_1.c: Force result variables to be
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c b/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c
new file mode 100644
index 0000000..d981fe4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c
@@ -0,0 +1,162 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx512vl -masm=att" } */
+
+typedef float V1 __attribute__((vector_size (16)));
+typedef float V2 __attribute__((vector_size (32)));
+typedef int V4 __attribute__((vector_size (16)));
+typedef int V5 __attribute__((vector_size (32)));
+
+void
+f1 (V1 x)
+{
+  register V1 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 0, 0, 0, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f2 (V1 x)
+{
+  register V1 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 1, 1, 1, 1 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f3 (V1 x)
+{
+  register V1 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 2, 2, 2, 2 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f4 (V1 x)
+{
+  register V1 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V4) { 3, 3, 3, 3 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f5 (V1 *x)
+{
+  register V1 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V4) { 0, 0, 0, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f6 (V1 *x)
+{
+  register V1 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V4) { 1, 1, 1, 1 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f7 (V1 *x)
+{
+  register V1 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V4) { 2, 2, 2, 2 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f8 (V1 *x)
+{
+  register V1 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V4) { 3, 3, 3, 3 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f9 (V2 x)
+{
+  register V2 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V5) { 0, 0, 0, 0, 0, 0, 0, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f10 (V2 x)
+{
+  register V2 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V5) { 1, 1, 1, 1, 1, 1, 1, 1 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f11 (V2 x)
+{
+  register V2 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V5) { 4, 4, 4, 4, 4, 4, 4, 4 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f12 (V2 x)
+{
+  register V2 a __asm ("xmm16");
+  a = x;
+  asm volatile ("" : "+v" (a));
+  a = __builtin_shuffle (a, (V5) { 5, 5, 5, 5, 5, 5, 5, 5 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f13 (V2 *x)
+{
+  register V2 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V5) { 0, 0, 0, 0, 0, 0, 0, 0 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f14 (V2 *x)
+{
+  register V2 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V5) { 1, 1, 1, 1, 1, 1, 1, 1 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f15 (V2 *x)
+{
+  register V2 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V5) { 4, 4, 4, 4, 4, 4, 4, 4 });
+  asm volatile ("" : "+v" (a));
+}
+
+void
+f16 (V2 *x)
+{
+  register V2 a __asm ("xmm16");
+  a = __builtin_shuffle (*x, (V5) { 5, 5, 5, 5, 5, 5, 5, 5 });
+  asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%rdi\[^\n\r]*%xmm16" 4 } } */
+/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%xmm16\[^\n\r]*%ymm16" 3 } } */
+/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%rdi\[^\n\r]*%ymm16" 3 } } */
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$0\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$85\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$170\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$255\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$0\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 1 } } */
+/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$85\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 2 } } */
+/* { dg-final { scan-assembler-times "vshuff32x4\[^\n\r]*\\\$3\[^\n\r]*%ymm16\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 2 } } */