AVX512FP16: Support cond_op for HFmode

gcc/ChangeLog:

	* config/i386/sse.md (cond_<insn><mode>): Extend to support
	vector HFmodes.
	(cond_mul<mode>): Likewise.
	(cond_div<mode>): Likewise.
	(cond_<code><mode>): Likewise.
	(cond_fma<mode>): Likewise.
	(cond_fms<mode>): Likewise.
	(cond_fnma<mode>): Likewise.
	(cond_fnms<mode>): Likewise.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/cond_op_addsubmuldiv__Float16-1.c: New test.
	* gcc.target/i386/cond_op_addsubmuldiv__Float16-2.c: Ditto.
	* gcc.target/i386/cond_op_fma__Float16-1.c: Ditto.
	* gcc.target/i386/cond_op_fma__Float16-2.c: Ditto.
	* gcc.target/i386/cond_op_maxmin__Float16-1.c: Ditto.
	* gcc.target/i386/cond_op_maxmin__Float16-2.c: Ditto.

7 files changed, 114 insertions, 56 deletions

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 084fc7f..a446ded 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2125,12 +2125,12 @@
   [(set_attr "isa" "noavx,noavx,avx,avx")])
 
 (define_expand "cond_<insn><mode>"
-  [(set (match_operand:VF 0 "register_operand")
-	(vec_merge:VF
-	  (plusminus:VF
-	    (match_operand:VF 2 "vector_operand")
-	    (match_operand:VF 3 "vector_operand"))
-	  (match_operand:VF 4 "nonimm_or_0_operand")
+  [(set (match_operand:VFH 0 "register_operand")
+	(vec_merge:VFH
+	  (plusminus:VFH
+	    (match_operand:VFH 2 "vector_operand")
+	    (match_operand:VFH 3 "vector_operand"))
+	  (match_operand:VFH 4 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "<MODE_SIZE> == 64 || TARGET_AVX512VL"
 {
@@ -2214,12 +2214,12 @@
    (set_attr "mode" "<ssescalarmode>")])
 
 (define_expand "cond_mul<mode>"
-  [(set (match_operand:VF 0 "register_operand")
-	(vec_merge:VF
-	  (mult:VF
-	    (match_operand:VF 2 "vector_operand")
-	    (match_operand:VF 3 "vector_operand"))
-	  (match_operand:VF 4 "nonimm_or_0_operand")
+  [(set (match_operand:VFH 0 "register_operand")
+	(vec_merge:VFH
+	  (mult:VFH
+	    (match_operand:VFH 2 "vector_operand")
+	    (match_operand:VFH 3 "vector_operand"))
+	  (match_operand:VFH 4 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "<MODE_SIZE> == 64 || TARGET_AVX512VL"
 {
@@ -2329,12 +2329,12 @@
 })
 
 (define_expand "cond_div<mode>"
-  [(set (match_operand:VF 0 "register_operand")
-	(vec_merge:VF
-	  (div:VF
-	    (match_operand:VF 2 "register_operand")
-	    (match_operand:VF 3 "vector_operand"))
-	  (match_operand:VF 4 "nonimm_or_0_operand")
+  [(set (match_operand:VFH 0 "register_operand")
+	(vec_merge:VFH
+	  (div:VFH
+	    (match_operand:VFH 2 "register_operand")
+	    (match_operand:VFH 3 "vector_operand"))
+	  (match_operand:VFH 4 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "<MODE_SIZE> == 64 || TARGET_AVX512VL"
 {
@@ -2667,12 +2667,12 @@
    (set_attr "mode" "HF")])
 
 (define_expand "cond_<code><mode>"
-  [(set (match_operand:VF 0 "register_operand")
-	(vec_merge:VF
-	  (smaxmin:VF
-	    (match_operand:VF 2 "vector_operand")
-	    (match_operand:VF 3 "vector_operand"))
-	  (match_operand:VF 4 "nonimm_or_0_operand")
+  [(set (match_operand:VFH 0 "register_operand")
+	(vec_merge:VFH
+	  (smaxmin:VFH
+	    (match_operand:VFH 2 "vector_operand")
+	    (match_operand:VFH 3 "vector_operand"))
+	  (match_operand:VFH 4 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "<MODE_SIZE> == 64 || TARGET_AVX512VL"
 {
@@ -4837,13 +4837,13 @@
    (set_attr "mode" "<MODE>")])
 
 (define_expand "cond_fma<mode>"
-  [(set (match_operand:VF_AVX512VL 0 "register_operand")
-	(vec_merge:VF_AVX512VL
-	  (fma:VF_AVX512VL
-	    (match_operand:VF_AVX512VL 2 "vector_operand")
-	    (match_operand:VF_AVX512VL 3 "vector_operand")
-	    (match_operand:VF_AVX512VL 4 "vector_operand"))
-	  (match_operand:VF_AVX512VL 5 "nonimm_or_0_operand")
+  [(set (match_operand:VFH_AVX512VL 0 "register_operand")
+	(vec_merge:VFH_AVX512VL
+	  (fma:VFH_AVX512VL
+	    (match_operand:VFH_AVX512VL 2 "vector_operand")
+	    (match_operand:VFH_AVX512VL 3 "vector_operand")
+	    (match_operand:VFH_AVX512VL 4 "vector_operand"))
+	  (match_operand:VFH_AVX512VL 5 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "TARGET_AVX512F"
 {
@@ -4937,14 +4937,14 @@
    (set_attr "mode" "<MODE>")])
 
 (define_expand "cond_fms<mode>"
-  [(set (match_operand:VF_AVX512VL 0 "register_operand")
-	(vec_merge:VF_AVX512VL
-	  (fma:VF_AVX512VL
-	    (match_operand:VF_AVX512VL 2 "vector_operand")
-	    (match_operand:VF_AVX512VL 3 "vector_operand")
-	    (neg:VF_AVX512VL
-	      (match_operand:VF_AVX512VL 4 "vector_operand")))
-	  (match_operand:VF_AVX512VL 5 "nonimm_or_0_operand")
+  [(set (match_operand:VFH_AVX512VL 0 "register_operand")
+	(vec_merge:VFH_AVX512VL
+	  (fma:VFH_AVX512VL
+	    (match_operand:VFH_AVX512VL 2 "vector_operand")
+	    (match_operand:VFH_AVX512VL 3 "vector_operand")
+	    (neg:VFH_AVX512VL
+	      (match_operand:VFH_AVX512VL 4 "vector_operand")))
+	  (match_operand:VFH_AVX512VL 5 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "TARGET_AVX512F"
 {
@@ -5040,14 +5040,14 @@
    (set_attr "mode" "<MODE>")])
 
 (define_expand "cond_fnma<mode>"
-  [(set (match_operand:VF_AVX512VL 0 "register_operand")
-	(vec_merge:VF_AVX512VL
-	  (fma:VF_AVX512VL
-	    (neg:VF_AVX512VL
-	      (match_operand:VF_AVX512VL 2 "vector_operand"))
-	    (match_operand:VF_AVX512VL 3 "vector_operand")
-	    (match_operand:VF_AVX512VL 4 "vector_operand"))
-	  (match_operand:VF_AVX512VL 5 "nonimm_or_0_operand")
+  [(set (match_operand:VFH_AVX512VL 0 "register_operand")
+	(vec_merge:VFH_AVX512VL
+	  (fma:VFH_AVX512VL
+	    (neg:VFH_AVX512VL
+	      (match_operand:VFH_AVX512VL 2 "vector_operand"))
+	    (match_operand:VFH_AVX512VL 3 "vector_operand")
+	    (match_operand:VFH_AVX512VL 4 "vector_operand"))
+	  (match_operand:VFH_AVX512VL 5 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "TARGET_AVX512F"
 {
@@ -5145,15 +5145,15 @@
    (set_attr "mode" "<MODE>")])
 
 (define_expand "cond_fnms<mode>"
-  [(set (match_operand:VF_AVX512VL 0 "register_operand")
-	(vec_merge:VF_AVX512VL
-	  (fma:VF_AVX512VL
-	    (neg:VF_AVX512VL
-	      (match_operand:VF_AVX512VL 2 "vector_operand"))
-	    (match_operand:VF_AVX512VL 3 "vector_operand")
-	    (neg:VF_AVX512VL
-	      (match_operand:VF_AVX512VL 4 "vector_operand")))
-	  (match_operand:VF_AVX512VL 5 "nonimm_or_0_operand")
+  [(set (match_operand:VFH_AVX512VL 0 "register_operand")
+	(vec_merge:VFH_AVX512VL
+	  (fma:VFH_AVX512VL
+	    (neg:VFH_AVX512VL
+	      (match_operand:VFH_AVX512VL 2 "vector_operand"))
+	    (match_operand:VFH_AVX512VL 3 "vector_operand")
+	    (neg:VFH_AVX512VL
+	      (match_operand:VFH_AVX512VL 4 "vector_operand")))
+	  (match_operand:VFH_AVX512VL 5 "nonimm_or_0_operand")
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
   "TARGET_AVX512F"
 {
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_addsubmuldiv__Float16-1.c b/gcc/testsuite/gcc.target/i386/cond_op_addsubmuldiv__Float16-1.c
new file mode 100644
index 0000000..b503b75
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_addsubmuldiv__Float16-1.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=sapphirerapids -DTYPE=_Float16 -fdump-tree-vect" } */
+/* { dg-final { scan-tree-dump ".COND_ADD" "vect" } } */
+/* { dg-final { scan-tree-dump ".COND_SUB" "vect" } } */
+/* { dg-final { scan-tree-dump ".COND_MUL" "vect" } } */
+/* { dg-final { scan-tree-dump ".COND_RDIV" "vect" } } */
+
+#include "cond_op_addsubmuldiv_double-1.c"
+
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_addsubmuldiv__Float16-2.c b/gcc/testsuite/gcc.target/i386/cond_op_addsubmuldiv__Float16-2.c
new file mode 100644
index 0000000..e8397bb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_addsubmuldiv__Float16-2.c
@@ -0,0 +1,7 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512fp16 -mavx512vl -mprefer-vector-width=256 -DTYPE=_Float16" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512fp16 } */
+
+#define AVX512FP16
+#include "cond_op_addsubmuldiv_double-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_fma__Float16-1.c b/gcc/testsuite/gcc.target/i386/cond_op_fma__Float16-1.c
new file mode 100644
index 0000000..9ea45d6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_fma__Float16-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=sapphirerapids -DTYPE=_Float16 -fdump-tree-optimized -D__BUILTIN_FMA=__builtin_fmaf16" } */
+/* { dg-final { scan-tree-dump-times ".COND_FMA" 3 "optimized" } } */
+/* { dg-final { scan-tree-dump-times ".COND_FNMA" 3 "optimized" } } */
+/* { dg-final { scan-tree-dump-times ".COND_FMS" 3 "optimized" } } */
+/* { dg-final { scan-tree-dump-times ".COND_FNMS" 3 "optimized" } } */
+/* { dg-final { scan-assembler-times "vfmadd132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfmsub132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfmadd231ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfnmadd231ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfmsub231ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfnmsub231ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfmadd132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfmsub132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132ph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)"  1 } } */
+
+#include "cond_op_fma_double-1.c"
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_fma__Float16-2.c b/gcc/testsuite/gcc.target/i386/cond_op_fma__Float16-2.c
new file mode 100644
index 0000000..b384ab8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_fma__Float16-2.c
@@ -0,0 +1,7 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512fp16 -mavx512vl -mprefer-vector-width=256 -DTYPE=_Float16 -D__BUILTIN_FMA=__builtin_fmaf16 -DNUM=100" } */
+/* { dg-require-effective-target avx512fp16 } */
+/* { dg-require-effective-target avx512vl } */
+
+#define AVX512FP16
+#include "cond_op_fma_double-2.c"
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_maxmin__Float16-1.c b/gcc/testsuite/gcc.target/i386/cond_op_maxmin__Float16-1.c
new file mode 100644
index 0000000..b094102
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_maxmin__Float16-1.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=sapphirerapids -DTYPE=_Float16 -fdump-tree-optimized -DFN_MAX=__builtin_fmaxf16 -DFN_MIN=__builtin_fminf16" } */
+/* { dg-final { scan-tree-dump ".COND_MAX" "optimized" } } */
+/* { dg-final { scan-tree-dump ".COND_MIN" "optimized" } } */
+/* { dg-final { scan-assembler-times "vmaxph"  1 } } */
+/* { dg-final { scan-assembler-times "vminph"  1 } } */
+
+#include "cond_op_maxmin_double-1.c"
diff --git a/gcc/testsuite/gcc.target/i386/cond_op_maxmin__Float16-2.c b/gcc/testsuite/gcc.target/i386/cond_op_maxmin__Float16-2.c
new file mode 100644
index 0000000..b07d044
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/cond_op_maxmin__Float16-2.c
@@ -0,0 +1,7 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512fp16 -mavx512vl -mprefer-vector-width=256 -DTYPE=_Float16 -DFN_MAX=__builtin_fmaxf16 -DFN_MIN=__builtin_fminf16 -ffast-math" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512fp16 } */
+
+#define AVX512FP16
+#include "cond_op_maxmin_double-2.c"