From f0b7a61d83534fc8f7aa593b1f0f0357a371a800 Mon Sep 17 00:00:00 2001
From: liuhongt <hongtao.liu@intel.com>
Date: Mon, 31 Jul 2023 16:03:45 +0800
Subject: [PATCH] Support vec_fmaddsub/vec_fmsubadd for vector HFmode.

AVX512FP16 supports vfmaddsubXXXph and vfmsubaddXXXph.
Also remove scalar mode from fmaddsub/fmsubadd pattern since there's
no scalar instruction for that.

gcc/ChangeLog:

	PR target/81904
	* config/i386/sse.md (vec_fmaddsub<mode>4): Extend to vector
	HFmode, use mode iterator VFH instead.
	(vec_fmsubadd<mode>4): Ditto.
	(<sd_mask_codefor>fma_fmaddsub_<mode><sd_maskz_name><round_name>):
	Remove scalar mode from iterator, use VFH_AVX512VL instead.
	(<sd_mask_codefor>fma_fmsubadd_<mode><sd_maskz_name><round_name>):
	Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr81904.c: New test.
---
 gcc/config/i386/sse.md                  | 44 ++++++++++++-------------
 gcc/testsuite/gcc.target/i386/pr81904.c | 22 +++++++++++++
 2 files changed, 44 insertions(+), 22 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr81904.c

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 8dea0570356..43afcfdc750 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -5803,21 +5803,21 @@
 ;; But this doesn't seem useful in practice.
 
 (define_expand "vec_fmaddsub<mode>4"
-  [(set (match_operand:VF 0 "register_operand")
-	(unspec:VF
-	  [(match_operand:VF 1 "nonimmediate_operand")
-	   (match_operand:VF 2 "nonimmediate_operand")
-	   (match_operand:VF 3 "nonimmediate_operand")]
+  [(set (match_operand:VFH 0 "register_operand")
+	(unspec:VFH
+	  [(match_operand:VFH 1 "nonimmediate_operand")
+	   (match_operand:VFH 2 "nonimmediate_operand")
+	   (match_operand:VFH 3 "nonimmediate_operand")]
 	  UNSPEC_FMADDSUB))]
   "TARGET_FMA || TARGET_FMA4 || (<MODE_SIZE> == 64 || TARGET_AVX512VL)")
 
 (define_expand "vec_fmsubadd<mode>4"
-  [(set (match_operand:VF 0 "register_operand")
-	(unspec:VF
-	  [(match_operand:VF 1 "nonimmediate_operand")
-	   (match_operand:VF 2 "nonimmediate_operand")
-	   (neg:VF
-	     (match_operand:VF 3 "nonimmediate_operand"))]
+  [(set (match_operand:VFH 0 "register_operand")
+	(unspec:VFH
+	  [(match_operand:VFH 1 "nonimmediate_operand")
+	   (match_operand:VFH 2 "nonimmediate_operand")
+	   (neg:VFH
+	     (match_operand:VFH 3 "nonimmediate_operand"))]
 	  UNSPEC_FMADDSUB))]
   "TARGET_FMA || TARGET_FMA4 || (<MODE_SIZE> == 64 || TARGET_AVX512VL)")
 
@@ -5877,11 +5877,11 @@
    (set_attr "mode" "<MODE>")])
 
 (define_insn "<sd_mask_codefor>fma_fmaddsub_<mode><sd_maskz_name><round_name>"
-  [(set (match_operand:VFH_SF_AVX512VL 0 "register_operand" "=v,v,v")
-	(unspec:VFH_SF_AVX512VL
-	  [(match_operand:VFH_SF_AVX512VL 1 "<round_nimm_predicate>" "%0,0,v")
-	   (match_operand:VFH_SF_AVX512VL 2 "<round_nimm_predicate>" "<round_constraint>,v,<round_constraint>")
-	   (match_operand:VFH_SF_AVX512VL 3 "<round_nimm_predicate>" "v,<round_constraint>,0")]
+  [(set (match_operand:VFH_AVX512VL 0 "register_operand" "=v,v,v")
+	(unspec:VFH_AVX512VL
+	  [(match_operand:VFH_AVX512VL 1 "<round_nimm_predicate>" "%0,0,v")
+	   (match_operand:VFH_AVX512VL 2 "<round_nimm_predicate>" "<round_constraint>,v,<round_constraint>")
+	   (match_operand:VFH_AVX512VL 3 "<round_nimm_predicate>" "v,<round_constraint>,0")]
 	  UNSPEC_FMADDSUB))]
   "TARGET_AVX512F && <sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
   "@
@@ -5943,12 +5943,12 @@
    (set_attr "mode" "<MODE>")])
 
 (define_insn "<sd_mask_codefor>fma_fmsubadd_<mode><sd_maskz_name><round_name>"
-  [(set (match_operand:VFH_SF_AVX512VL 0 "register_operand" "=v,v,v")
-	(unspec:VFH_SF_AVX512VL
-	  [(match_operand:VFH_SF_AVX512VL   1 "<round_nimm_predicate>" "%0,0,v")
-	   (match_operand:VFH_SF_AVX512VL   2 "<round_nimm_predicate>" "<round_constraint>,v,<round_constraint>")
-	   (neg:VFH_SF_AVX512VL
-	     (match_operand:VFH_SF_AVX512VL 3 "<round_nimm_predicate>" "v,<round_constraint>,0"))]
+  [(set (match_operand:VFH_AVX512VL 0 "register_operand" "=v,v,v")
+	(unspec:VFH_AVX512VL
+	  [(match_operand:VFH_AVX512VL   1 "<round_nimm_predicate>" "%0,0,v")
+	   (match_operand:VFH_AVX512VL   2 "<round_nimm_predicate>" "<round_constraint>,v,<round_constraint>")
+	   (neg:VFH_AVX512VL
+	     (match_operand:VFH_AVX512VL 3 "<round_nimm_predicate>" "v,<round_constraint>,0"))]
 	  UNSPEC_FMADDSUB))]
   "TARGET_AVX512F && <sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
   "@
diff --git a/gcc/testsuite/gcc.target/i386/pr81904.c b/gcc/testsuite/gcc.target/i386/pr81904.c
new file mode 100644
index 00000000000..9f5ad0bd952
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81904.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512fp16 -mavx512vl -O2 -mprefer-vector-width=512" } */
+/* { dg-final { scan-assembler-times "vfmaddsub...ph\[ \t\]+\[^\n\]*%zmm\[0-9\]" 1 } } */
+/* { dg-final { scan-assembler-times "vfmsubadd...ph\[ \t\]+\[^\n\]*%zmm\[0-9\]" 1 } } */
+
+void vec_fmaddsub_fp16(int n, _Float16 da_r, _Float16 *x, _Float16* y, _Float16* __restrict z)
+{
+  for (int i = 0; i < 32; i += 2)
+    {
+      z[i] =  da_r * x[i] - y[i];
+      z[i+1]  =  da_r * x[i+1] + y[i+1];
+    }
+}
+
+void vec_fmasubadd_fp16(int n, _Float16 da_r, _Float16 *x, _Float16* y, _Float16* __restrict z)
+{
+  for (int i = 0; i < 32; i += 2)
+    {
+      z[i] =  da_r * x[i] + y[i];
+      z[i+1]  =  da_r * x[i+1] - y[i+1];
+    }
+}