[2/2] Support 32/64-bit vectorization for conversion between _Float16 and integer/float.

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 8375100d4bf..be2a9026c44 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -60,6 +60,7 @@  (define_mode_iterator MMXMODE248 [V4HI V2SI V1DI])
 ;; All 4-byte integer/float16 vector modes
 (define_mode_iterator V_32 [V4QI V2HI V1SI V2HF V2BF])
 
+(define_mode_iterator V2FI_32 [V2HF V2BF V2HI])
 ;; 4-byte integer vector modes
 (define_mode_iterator VI_32 [V4QI V2HI])
 
@@ -79,7 +80,7 @@  (define_mode_iterator V_16_32_64
 ;; V2S* modes
 (define_mode_iterator V2FI [V2SF V2SI])
 
-(define_mode_iterator V2FI_V4HF [V2SF V2SI V4HF])
+(define_mode_iterator V24FI [V2SF V2SI V4HF V4HI])
 ;; Mapping from integer vector mode to mnemonic suffix
 (define_mode_attr mmxvecsize
   [(V8QI "b") (V4QI "b") (V2QI "b")
@@ -100,7 +101,7 @@  (define_mode_attr mmxdoublemode
 ;; Mapping of vector float modes to an integer mode of the same size
 (define_mode_attr mmxintvecmode
   [(V2SF "V2SI") (V2SI "V2SI") (V4HI "V4HI") (V8QI "V8QI")
-   (V4HF "V4HF") (V2HF "V2HI")])
+   (V4HF "V4HI") (V2HF "V2HI")])
 
 (define_mode_attr mmxintvecmodelower
   [(V2SF "v2si") (V2SI "v2si") (V4HI "v4hi") (V8QI "v8qi")
@@ -108,7 +109,7 @@  (define_mode_attr mmxintvecmodelower
 
 ;; Mapping of vector modes to a vector mode of double size
 (define_mode_attr mmxdoublevecmode
-  [(V2SF "V4SF") (V2SI "V4SI") (V4HF "V8HF")])
+  [(V2SF "V4SF") (V2SI "V4SI") (V4HF "V8HF") (V4HI "V8HI")])
 
 ;; Mapping of vector modes back to the scalar modes
 (define_mode_attr mmxscalarmode
@@ -600,7 +601,7 @@  (define_insn "sse_movntq"
 (define_expand "movq_<mode>_to_sse"
   [(set (match_operand:<mmxdoublevecmode> 0 "register_operand")
 	(vec_concat:<mmxdoublevecmode>
-	  (match_operand:V2FI_V4HF 1 "nonimmediate_operand")
+	  (match_operand:V24FI 1 "nonimmediate_operand")
 	  (match_dup 2)))]
   "TARGET_SSE2"
 {
@@ -1967,31 +1968,40 @@  (define_expand "divv4hf3"
   DONE;
 })
 
-(define_mode_attr mov_to_sse_suffix [(V2HF "d") (V4HF "q")])
-(define_expand "movd_v2hf_to_sse"
-  [(set (match_operand:V8HF 0 "register_operand")
-	(vec_merge:V8HF
-	  (vec_duplicate:V8HF
-	    (match_operand:V2HF 1 "nonimmediate_operand"))
+(define_mode_attr mov_to_sse_suffix
+  [(V2HF "d") (V4HF "q") (V2HI "d") (V4HI "q")])
+
+(define_mode_attr mmxxmmmode
+  [(V2HF "V8HF") (V2HI "V8HI") (V2BF "V8BF")])
+
+(define_mode_attr mmxxmmmodelower
+  [(V2HF "v8hf") (V2HI "v8hi") (V2BF "v8bf")])
+
+(define_expand "movd_<mode>_to_sse"
+  [(set (match_operand:<mmxxmmmode> 0 "register_operand")
+	(vec_merge:<mmxxmmmode>
+	  (vec_duplicate:<mmxxmmmode>
+	    (match_operand:V2FI_32 1 "nonimmediate_operand"))
 	  (match_dup 2)
 	  (const_int 3)))]
   "TARGET_SSE"
 {
   if (!flag_trapping_math)
   {
-    rtx op1 = force_reg (V2HFmode, operands[1]);
-    emit_move_insn (operands[0], lowpart_subreg (V8HFmode, op1, V2HFmode));
+    rtx op1 = force_reg (<MODE>mode, operands[1]);
+    emit_move_insn (operands[0],
+		   lowpart_subreg (<mmxxmmmode>mode, op1, <MODE>mode));
     DONE;
   }
-  operands[2] = CONST0_RTX (V8HFmode);
+  operands[2] = CONST0_RTX (<mmxxmmmode>mode);
 })
 
-(define_expand "movd_v2hf_to_sse_reg"
-  [(set (match_operand:V8HF 0 "register_operand")
-	(vec_merge:V8HF
-	  (vec_duplicate:V8HF
-	    (match_operand:V2HF 1 "nonimmediate_operand"))
-	  (match_operand:V8HF 2 "register_operand")
+(define_expand "movd_<mode>_to_sse_reg"
+  [(set (match_operand:<mmxxmmmode> 0 "register_operand")
+	(vec_merge:<mmxxmmmode>
+	  (vec_duplicate:<mmxxmmmode>
+	    (match_operand:V2FI_32 1 "nonimmediate_operand"))
+	  (match_operand:<mmxxmmmode> 2 "register_operand")
 	  (const_int 3)))]
   "TARGET_SSE")
 
@@ -2353,6 +2363,122 @@  (define_expand "signbit<mode>2"
   "TARGET_SSE2"
   "operands[2] = GEN_INT (GET_MODE_UNIT_BITSIZE (<MODE>mode)-1);")
 
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;
+;; Parallel single-precision floating point conversion operations
+;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_expand "fix<fixunssuffix>_trunc<mode><mmxintvecmodelower>2"
+  [(set (match_operand:<mmxintvecmode> 0 "register_operand")
+	(any_fix:<mmxintvecmode>
+	  (match_operand:VHF_32_64 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16 && TARGET_AVX512VL && ix86_partial_vec_fp_math"
+{
+  rtx op1 = gen_reg_rtx (V8HFmode);
+  rtx op0 = gen_reg_rtx (V8HImode);
+
+  emit_insn (gen_mov<mov_to_sse_suffix>_<mode>_to_sse (op1, operands[1]));
+
+  emit_insn (gen_fix<fixunssuffix>_truncv8hfv8hi2 (op0, op1));
+
+  emit_move_insn (operands[0],
+		 lowpart_subreg (<mmxintvecmode>mode, op0, V8HImode));
+  DONE;
+})
+
+(define_expand "fix<fixunssuffix>_truncv2hfv2si2"
+  [(set (match_operand:V2SI 0 "register_operand")
+	(any_fix:V2SI
+	  (match_operand:V2HF 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16 && TARGET_AVX512VL
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
+{
+  rtx op1 = gen_reg_rtx (V8HFmode);
+  rtx op0 = gen_reg_rtx (V4SImode);
+
+  emit_insn (gen_movd_v2hf_to_sse (op1, operands[1]));
+
+  emit_insn (gen_avx512fp16_fix<fixunssuffix>_truncv4si2 (op0, op1));
+
+  emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
+  DONE;
+})
+
+(define_expand "float<floatunssuffix><mmxintvecmodelower><mode>2"
+  [(set (match_operand:VHF_32_64 0 "register_operand")
+	(any_float:VHF_32_64
+	  (match_operand:<mmxintvecmode> 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16 && TARGET_AVX512VL && ix86_partial_vec_fp_math"
+{
+  rtx op1 = gen_reg_rtx (V8HImode);
+  rtx op0 = gen_reg_rtx (V8HFmode);
+
+  rtx (*gen_movd_sse) (rtx, rtx)
+    = gen_mov<mov_to_sse_suffix>_<mmxintvecmodelower>_to_sse;
+  emit_insn (gen_movd_sse (op1, operands[1]));
+
+  emit_insn (gen_float<floatunssuffix>v8hiv8hf2 (op0, op1));
+
+  emit_move_insn (operands[0],
+		 lowpart_subreg (<MODE>mode, op0, V8HFmode));
+  DONE;
+})
+
+(define_expand "float<floatunssuffix>v2siv2hf2"
+  [(set (match_operand:V2HF 0 "register_operand")
+	(any_float:V2HF
+	  (match_operand:V2SI 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16 && TARGET_AVX512VL
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
+{
+  rtx op1 = gen_reg_rtx (V4SImode);
+  rtx op0 = gen_reg_rtx (V8HFmode);
+
+  emit_insn (gen_movq_v2si_to_sse (op1, operands[1]));
+
+  emit_insn (gen_avx512fp16_float<floatunssuffix>v4siv4hf2 (op0, op1));
+
+  emit_move_insn (operands[0], lowpart_subreg (V2HFmode, op0, V8HFmode));
+  DONE;
+})
+
+(define_expand "extendv2hfv2sf2"
+  [(set (match_operand:V2SF 0 "register_operand")
+	(float_extend:V2SF
+	  (match_operand:V2HF 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16 && TARGET_AVX512VL
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
+{
+  rtx op1 = gen_reg_rtx (V8HFmode);
+  rtx op0 = gen_reg_rtx (V4SFmode);
+
+  emit_insn (gen_movd_v2hf_to_sse (op1, operands[1]));
+
+  emit_insn (gen_avx512fp16_float_extend_phv4sf2 (op0, op1));
+
+  emit_move_insn (operands[0], lowpart_subreg (V2SFmode, op0, V4SFmode));
+  DONE;
+})
+
+(define_expand "truncv2sfv2hf2"
+  [(set (match_operand:V2HF 0 "register_operand")
+	(float_truncate:V2HF
+	  (match_operand:V2SF 1 "nonimmediate_operand")))]
+  "TARGET_AVX512FP16 && TARGET_AVX512VL
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
+{
+  rtx op1 = gen_reg_rtx (V4SFmode);
+  rtx op0 = gen_reg_rtx (V8HFmode);
+
+  emit_insn (gen_movq_v2sf_to_sse (op1, operands[1]));
+
+  emit_insn (gen_avx512fp16_truncv4sfv4hf2 (op0, op1));
+
+  emit_move_insn (operands[0], lowpart_subreg (V2HFmode, op0, V8HFmode));
+  DONE;
+})
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
 ;; Parallel integral arithmetic
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 4602edf2374..e9f947291c1 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -10975,12 +10975,12 @@  (define_insn "*vec_concat<mode>_0"
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "DF")])
 
-(define_insn "*vec_concatv8hf_movss"
-  [(set (match_operand:V8HF 0 "register_operand"       "=x,v,v")
-	(vec_merge:V8HF
-	  (vec_duplicate:V8HF
-	    (match_operand:V2HF 2 "nonimmediate_operand" "x,m,v"))
-	  (match_operand:V8HF 1 "reg_or_0_operand"	 "0,C,v" )
+(define_insn "*vec_concat<mmxxmmmodelower>_movss"
+  [(set (match_operand:<mmxxmmmode> 0 "register_operand"       "=x,v,v")
+	(vec_merge:<mmxxmmmode>
+	  (vec_duplicate:<mmxxmmmode>
+	    (match_operand:V2FI_32 2 "nonimmediate_operand" "x,m,v"))
+	  (match_operand:<mmxxmmmode> 1 "reg_or_0_operand"	 "0,C,v" )
 	  (const_int 3)))]
   "TARGET_SSE"
   "@
diff --git a/gcc/testsuite/gcc.target/i386/part-vect-hf-convert-1.c b/gcc/testsuite/gcc.target/i386/part-vect-hf-convert-1.c
new file mode 100644
index 00000000000..95426015b58
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/part-vect-hf-convert-1.c
@@ -0,0 +1,111 @@ 
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-mavx512fp16 -mavx512vl -O2" } */
+/* { dg-final { scan-assembler-times {(?n)vcvttph2w[ \t]} 2 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvttph2uw[ \t]} 2 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvttph2dq[ \t]} 1 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvttph2udq[ \t]} 1 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvtw2ph[ \t]} 2 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvtuw2ph[ \t]} 2 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvtdq2phx[ \t]} 1 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvtudq2phx[ \t]} 1 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvtph2psx[ \t]} 1 } } */
+/* { dg-final { scan-assembler-times {(?n)vcvtps2phxx[ \t]} 1 } } */
+
+
+void
+fix_32 (short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pa[i] =  pb[i];
+}
+
+void
+fix_64 (short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 4; i++)
+    pa[i] =  pb[i];
+}
+
+void
+fixuns_32 (unsigned short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pa[i] =  pb[i];
+}
+
+void
+fixuns_64 (unsigned short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 4; i++)
+    pa[i] =  pb[i];
+}
+
+void
+float_32 (short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pb[i] =  pa[i];
+}
+
+void
+float_64 (short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 4; i++)
+    pb[i] =  pa[i];
+}
+
+void
+floatuns_32 (unsigned short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pb[i] =  pa[i];
+}
+
+void
+floatuns_64 (unsigned short* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 4; i++)
+    pb[i] =  pa[i];
+}
+
+void
+fix_32si (int* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pa[i] =  pb[i];
+}
+
+void
+fix_32usi (unsigned int* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pa[i] =  pb[i];
+}
+
+void
+float_32si (int* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pb[i] =  pa[i];
+}
+
+void
+float_32usi (unsigned int* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pb[i] =  pa[i];
+}
+
+void
+float_extend (float* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pa[i] =  pb[i];
+}
+
+void
+float_truncate (float* __restrict pa, _Float16* pb)
+{
+  for (int i = 0; i != 2; i++)
+    pb[i] =  pa[i];
+}