Simplify (_Float16) ceil ((double) x) to .CEIL (x) when available.
gcc/ChangeLog:
PR target/102464
* config/i386/i386.c (ix86_optab_supported_p):
Return true for HFmode.
* match.pd: Simplify (_Float16) ceil ((double) x) to
__builtin_ceilf16 (a) when a is _Float16 type and
direct_internal_fn_supported_p.
gcc/testsuite/ChangeLog:
* gcc.target/i386/pr102464.c: New test.
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index a566d84..7bc1b05 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -23582,20 +23582,24 @@
return opt_type == OPTIMIZE_FOR_SPEED;
case rint_optab:
- if (SSE_FLOAT_MODE_P (mode1)
- && TARGET_SSE_MATH
- && !flag_trapping_math
- && !TARGET_SSE4_1)
+ if (mode1 == HFmode)
+ return true;
+ else if (SSE_FLOAT_MODE_P (mode1)
+ && TARGET_SSE_MATH
+ && !flag_trapping_math
+ && !TARGET_SSE4_1)
return opt_type == OPTIMIZE_FOR_SPEED;
return true;
case floor_optab:
case ceil_optab:
case btrunc_optab:
- if (SSE_FLOAT_MODE_P (mode1)
- && TARGET_SSE_MATH
- && !flag_trapping_math
- && TARGET_SSE4_1)
+ if (mode1 == HFmode)
+ return true;
+ else if (SSE_FLOAT_MODE_P (mode1)
+ && TARGET_SSE_MATH
+ && !flag_trapping_math
+ && TARGET_SSE4_1)
return true;
return opt_type == OPTIMIZE_FOR_SPEED;
diff --git a/gcc/match.pd b/gcc/match.pd
index a9791ce..9d7c1ac 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -6191,6 +6191,35 @@
(froms (convert float_value_p@0))
(convert (tos @0)))))
+#if GIMPLE
+(match float16_value_p
+ @0
+ (if (TYPE_MAIN_VARIANT (TREE_TYPE (@0)) == float16_type_node)))
+(for froms (BUILT_IN_TRUNCL BUILT_IN_TRUNC BUILT_IN_TRUNCF
+ BUILT_IN_FLOORL BUILT_IN_FLOOR BUILT_IN_FLOORF
+ BUILT_IN_CEILL BUILT_IN_CEIL BUILT_IN_CEILF
+ BUILT_IN_ROUNDEVENL BUILT_IN_ROUNDEVEN BUILT_IN_ROUNDEVENF
+ BUILT_IN_ROUNDL BUILT_IN_ROUND BUILT_IN_ROUNDF
+ BUILT_IN_NEARBYINTL BUILT_IN_NEARBYINT BUILT_IN_NEARBYINTF
+ BUILT_IN_RINTL BUILT_IN_RINT BUILT_IN_RINTF)
+ tos (IFN_TRUNC IFN_TRUNC IFN_TRUNC
+ IFN_FLOOR IFN_FLOOR IFN_FLOOR
+ IFN_CEIL IFN_CEIL IFN_CEIL
+ IFN_ROUNDEVEN IFN_ROUNDEVEN IFN_ROUNDEVEN
+ IFN_ROUND IFN_ROUND IFN_ROUND
+ IFN_NEARBYINT IFN_NEARBYINT IFN_NEARBYINT
+ IFN_RINT IFN_RINT IFN_RINT)
+ /* (_Float16) round ((doube) x) -> __built_in_roundf16 (x), etc.,
+ if x is a _Float16. */
+ (simplify
+ (convert (froms (convert float16_value_p@0)))
+ (if (optimize
+ && types_match (type, TREE_TYPE (@0))
+ && direct_internal_fn_supported_p (as_internal_fn (tos),
+ type, OPTIMIZE_FOR_BOTH))
+ (tos @0))))
+#endif
+
(for froms (XFLOORL XCEILL XROUNDL XRINTL)
tos (XFLOOR XCEIL XROUND XRINT)
/* llfloorl(extend(x)) -> llfloor(x), etc., if x is a double. */
diff --git a/gcc/testsuite/gcc.target/i386/pr102464.c b/gcc/testsuite/gcc.target/i386/pr102464.c
new file mode 100644
index 0000000..e3e060e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr102464.c
@@ -0,0 +1,39 @@
+/* PR target/102464. */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#define FOO(FUNC,SUFFIX) \
+ _Float16 \
+ foo_##FUNC##_##SUFFIX (_Float16 a) \
+ { \
+ return __builtin_##FUNC##SUFFIX (a); \
+ }
+
+FOO (roundeven, f16);
+FOO (roundeven, f);
+FOO (roundeven, );
+FOO (roundeven, l);
+FOO (trunc, f16);
+FOO (trunc, f);
+FOO (trunc, );
+FOO (trunc, l);
+FOO (ceil, f16);
+FOO (ceil, f);
+FOO (ceil, );
+FOO (ceil, l);
+FOO (floor, f16);
+FOO (floor, f);
+FOO (floor, );
+FOO (floor, l);
+FOO (nearbyint, f16);
+FOO (nearbyint, f);
+FOO (nearbyint, );
+FOO (nearbyint, l);
+FOO (rint, f16);
+FOO (rint, f);
+FOO (rint, );
+FOO (rint, l);
+
+/* { dg-final { scan-assembler-not "vcvtsh2s\[sd\]" } } */
+/* { dg-final { scan-assembler-not "extendhfxf" } } */
+/* { dg-final { scan-assembler-times "vrndscalesh\[^\n\r\]*xmm\[0-9\]" 24 } } */
