Support vector float_extend from __bf16 to float.

It's supported by vector permutation with zero vector.

gcc/ChangeLog:

	* config/i386/i386-expand.cc
	(ix86_expand_vector_bf2sf_with_vec_perm): New function.
	* config/i386/i386-protos.h
	(ix86_expand_vector_bf2sf_with_vec_perm): New Declare.
	* config/i386/mmx.md (extendv2bfv2sf2): New expander.
	* config/i386/sse.md (extend<sf_cvt_bf16_lower><mode>2):
	Ditto.
	(VF1_AVX512BW): New mode iterator.
	(sf_cvt_bf16): Add V4SF.
	(sf_cvt_bf16_lower): New mode attr.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx512bw-extendbf2sf.c: New test.
	* gcc.target/i386/sse2-extendbf2sf.c: New test.

gcc/config/i386/i386-expand.cc

@@ -26879,5 +26879,44 @@ ix86_expand_vector_sf2bf_with_vec_perm (rtx dest, rtx src)
   emit_move_insn (dest, lowpart_subreg (GET_MODE (dest), target, vperm_mode));
 }
 
+/* Implement extendv8bf2v8sf2 with vector permutation.  */
+void
+ix86_expand_vector_bf2sf_with_vec_perm (rtx dest, rtx src)
+{
+  machine_mode vperm_mode, src_mode = GET_MODE (src);
+  switch (src_mode)
+    {
+    case V16BFmode:
+      vperm_mode = V32BFmode;
+      break;
+    case V8BFmode:
+      vperm_mode = V16BFmode;
+      break;
+    case V4BFmode:
+      vperm_mode = V8BFmode;
+      break;
+    default:
+      gcc_unreachable ();
+    }
+
+  int nelt = GET_MODE_NUNITS (vperm_mode);
+  vec_perm_builder sel (nelt, nelt, 1);
+  sel.quick_grow (nelt);
+  for (int i = 0, k = 0, j = nelt; i != nelt; i++)
+    sel[i] = i & 1 ? j++ : k++;
+
+  vec_perm_indices indices (sel, 2, nelt);
+
+  rtx target = gen_reg_rtx (vperm_mode);
+  rtx op1 = lowpart_subreg (vperm_mode,
+			    force_reg (src_mode, src),
+			    src_mode);
+  rtx op0 = CONST0_RTX (vperm_mode);
+  bool ok = targetm.vectorize.vec_perm_const (vperm_mode, vperm_mode,
+					      target, op0, op1, indices);
+  gcc_assert (ok);
+  emit_move_insn (dest, lowpart_subreg (GET_MODE (dest), target, vperm_mode));
+}
+
 
 #include "gt-i386-expand.h"

gcc/config/i386/i386-protos.h

@@ -259,6 +259,8 @@ extern bool ix86_ternlog_operand_p (rtx op);
 extern rtx ix86_expand_ternlog (machine_mode mode, rtx op0, rtx op1, rtx op2,
 				int idx, rtx target);
 extern void ix86_expand_vector_sf2bf_with_vec_perm (rtx, rtx);
+extern void ix86_expand_vector_bf2sf_with_vec_perm (rtx, rtx);
+
 
 #ifdef TREE_CODE
 extern void init_cumulative_args (CUMULATIVE_ARGS *, tree, rtx, tree, int);

gcc/config/i386/mmx.md

@@ -3012,6 +3012,24 @@
   DONE;
 })
 
+(define_expand "extendv2bfv2sf2"
+  [(set (match_operand:V2SF 0 "register_operand")
+	(float_extend:V2SF
+	  (match_operand:V2BF 1 "nonimmediate_operand")))]
+  "TARGET_SSE2 && TARGET_MMX_WITH_SSE"
+{
+  rtx op0 = gen_reg_rtx (V4SFmode);
+  rtx op1 = gen_reg_rtx (V4BFmode);
+
+  emit_move_insn (op1, lowpart_subreg (V4BFmode,
+				       force_reg (V2BFmode, operands[1]),
+				       V2BFmode));
+  emit_insn (gen_extendv4bfv4sf2 (op0, op1));
+
+  emit_move_insn (operands[0], lowpart_subreg (V2SFmode, op0, V4SFmode));
+  DONE;
+})
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
 ;; Parallel integral arithmetic

gcc/config/i386/sse.md

@@ -539,6 +539,9 @@
 (define_mode_iterator VF1_AVX512VL
   [(V16SF "TARGET_EVEX512") (V8SF "TARGET_AVX512VL") (V4SF "TARGET_AVX512VL")])
 
+(define_mode_iterator VF1_AVX512BW
+  [(V16SF "TARGET_EVEX512 && TARGET_EVEX512") (V8SF "TARGET_AVX2") V4SF])
+
 (define_mode_iterator VF1_AVX10_2
   [(V16SF "TARGET_AVX10_2_512") V8SF V4SF])
 
@@ -30957,7 +30960,11 @@
   [(V32BF  "V16SF") (V16BF  "V8SF") (V8BF  "V4SF")])
 ;; Converting from SF to BF
 (define_mode_attr sf_cvt_bf16
-  [(V8SF  "V8BF") (V16SF  "V16BF")])
+  [(V4SF "V4BF") (V8SF  "V8BF") (V16SF  "V16BF")])
+
+(define_mode_attr sf_cvt_bf16_lower
+  [(V4SF "v4bf") (V8SF  "v8bf") (V16SF  "v16bf")])
+
 ;; Mapping from BF to SF
 (define_mode_attr sf_bf16
   [(V4SF  "V8BF") (V8SF  "V16BF") (V16SF  "V32BF")])
@@ -31116,6 +31123,17 @@
     }
 })
 
+(define_expand "extend<sf_cvt_bf16_lower><mode>2"
+  [(set (match_operand:VF1_AVX512BW 0 "register_operand")
+	(float_extend:VF1_AVX512BW
+	  (match_operand:<sf_cvt_bf16> 1 "nonimmediate_operand")))]
+  "TARGET_SSE2"
+{
+  ix86_expand_vector_bf2sf_with_vec_perm (operands[0], operands[1]);
+  DONE;
+})
+
+
 (define_insn "avx512f_cvtneps2bf16_<mode><mask_name>"
   [(set (match_operand:<sf_cvt_bf16> 0 "register_operand" "=v")
 	(float_truncate:<sf_cvt_bf16>

gcc/testsuite/gcc.target/i386/avx512bw-extendbf2sf.c

@@ -0,0 +1,46 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512bw -mavx512vl -O2" } */
+/* { dg-final { scan-assembler-times {(?n)(?:vpermi2w|vpunpcklwd)} 6 } } */
+
+typedef float v4sf __attribute__((vector_size(16)));
+typedef float v8sf __attribute__((vector_size(32)));
+typedef float v16sf __attribute__((vector_size(64)));
+typedef __bf16 v4bf __attribute__((vector_size(8)));
+typedef __bf16 v8bf __attribute__((vector_size(16)));
+typedef __bf16 v16bf __attribute__((vector_size(32)));
+
+v4sf
+foo (v4bf b, v4bf a)
+{
+  return __builtin_convertvector (a, v4sf);
+}
+
+v8sf
+foo2 (v8bf b, v8bf a)
+{
+  return __builtin_convertvector (a, v8sf);
+}
+
+v16sf
+foo3 (v16bf b, v16bf a)
+{
+  return __builtin_convertvector (a, v16sf);
+}
+
+v4sf
+foo_mem (v4bf* a)
+{
+  return __builtin_convertvector (*a, v4sf);
+}
+
+v8sf
+foo2_mem (v8bf* a)
+{
+  return __builtin_convertvector (*a, v8sf);
+}
+
+v16sf
+foo3_mem (v16bf* a)
+{
+  return __builtin_convertvector (*a, v16sf);
+}

gcc/testsuite/gcc.target/i386/sse2-extendbf2sf.c

@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-msse2 -O2" } */
+/* { dg-final { scan-assembler-times {(?n)(?:vpermi2w|punpcklwd)} 2 { target { ! ia32 } } } } */
+
+typedef float v2sf __attribute__((vector_size(8)));
+typedef __bf16 v2bf __attribute__((vector_size(4)));
+
+v2sf
+foo (v2bf b, v2bf a)
+{
+  return __builtin_convertvector (a, v2sf);
+}
+
+
+v2sf
+foo_mem (v2bf* a)
+{
+  return __builtin_convertvector (*a, v2sf);
+}
+