libgcc: Add support for HF mode (aka _Float16) in libbid

This patch adds support for trunc and extend operations between HF
mode (_Float16) and Decimal Floating Point formats (_Decimal32,
_Decimal64 and _Decimal128).

For simplicity we rely on the implicit conversions inserted by the
compiler between HF and SD/DF/TF modes.  The existing bid*_to_binary*
and binary*_to_bid* functions are non-trivial and at this stage it is
not clear if there is a performance-critical use case involving _Float16
and _Decimal* formats.

The patch also adds two executable tests, to make sure the right
functions are called, available (link phase) and functional.

Tested on aarch64 and x86_64. The number of symbol matches in the
testcases includes the .global XXX to avoid having to match different
call instructions for different targets.

2022-05-04  Christophe Lyon  <christophe.lyon@arm.com>

libgcc/ChangeLog:

	* Makefile.in (D32PBIT_FUNCS): Add _hf_to_sd and _sd_to_hf.
	(D64PBIT_FUNCS): Add _hf_to_dd and _dd_to_hf.
	(D128PBIT_FUNCS): Add _hf_to_td _td_to_hf.

libgcc/config/libbid/ChangeLog:

	* bid_gcc_intrinsics.h (LIBGCC2_HAS_HF_MODE): Define according to
	__LIBGCC_HAS_HF_MODE__.
	(BID_HAS_HF_MODE): Define.
	(HFtype): Define.
	(__bid_extendhfsd): New prototype.
	(__bid_extendhfdd): Likewise.
	(__bid_extendhftd): Likewise.
	(__bid_truncsdhf): Likewise.
	(__bid_truncddhf): Likewise.
	(__bid_trunctdhf): Likewise.
	* _dd_to_hf.c: New file.
	* _hf_to_dd.c: New file.
	* _hf_to_sd.c: New file.
	* _hf_to_td.c: New file.
	* _sd_to_hf.c: New file.
	* _td_to_hf.c: New file.

gcc/testsuite/ChangeLog:

	* gcc.dg/torture/convert-dfp-2.c: New test.
	* gcc.dg/torture/convert-dfp.c: New test.

2 files changed, 108 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.dg/torture/convert-dfp-2.c b/gcc/testsuite/gcc.dg/torture/convert-dfp-2.c
new file mode 100644
index 0000000..3e4ecb5
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/convert-dfp-2.c
@@ -0,0 +1,45 @@
+/* { dg-do run } */
+/* { dg-require-effective-target float16_runtime } */
+/* { dg-require-effective-target dfprt } */
+/* { dg-options "-save-temps" } */
+/* { dg-add-options float16 } */
+
+/* Test conversions from DFP to smaller types.  */
+
+_Decimal32 var32;
+_Decimal64 var64;
+_Decimal128 var128;
+_Float16 var16;
+
+void __attribute__ ((__noinline__)) foo32 (_Decimal32 param32)
+{
+  var16 = param32;
+}
+
+void __attribute__ ((__noinline__)) foo64 (_Decimal64 param64)
+{
+  var16 = param64;
+  var32 = param64;
+}
+
+void __attribute__ ((__noinline__)) foo128 (_Decimal128 param128)
+{
+  var16 = param128;
+  var32 = param128;
+  var64 = param128;
+}
+
+int main ()
+{
+  foo32 (var32);
+  foo64 (var64);
+  foo128 (var128);
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {\t__bid_truncsdhf} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_truncddhf} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_truncddsd2} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_trunctdhf} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_trunctdsd2} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_trunctddd2} 2 { target { dfp_bid } } } } */
diff --git a/gcc/testsuite/gcc.dg/torture/convert-dfp.c b/gcc/testsuite/gcc.dg/torture/convert-dfp.c
new file mode 100644
index 0000000..ec13689
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/convert-dfp.c
@@ -0,0 +1,63 @@
+/* { dg-do run } */
+/* { dg-require-effective-target float16_runtime } */
+/* { dg-require-effective-target dfprt } */
+/* { dg-options "-save-temps" } */
+/* { dg-add-options float16 } */
+
+/* Test conversions to/from DFP values.  */
+
+extern void abort ();
+
+_Decimal32 var32 = 1.2df;
+
+int __attribute__ ((__noinline__)) foo32 (_Decimal32 param32, _Decimal64 param64, _Decimal128 param128, _Float16 param16)
+{
+  return (param32 == var32)
+    + (param64 == var32)
+    + (param128 == var32)
+    /* Small enough relative difference?  */
+    + ((((_Decimal32)param16 - var32) / var32) < 0.002df);
+}
+
+_Decimal64 var64 = 1.2dd;
+
+int __attribute__ ((__noinline__)) foo64 (_Decimal32 param32, _Decimal64 param64, _Decimal128 param128, _Float16 param16)
+{
+  return (param32 == var64)
+    + (param64 == var64)
+    + (param128 == var64)
+    /* Small enough relative difference?  */
+    + ((((_Decimal64)param16 - var64) / var64) < 0.002dd);
+}
+
+_Decimal128 var128 = 1.2dl;
+
+int __attribute__ ((__noinline__)) foo128 (_Decimal32 param32, _Decimal64 param64, _Decimal128 param128, _Float16 param16)
+{
+  return (param32 == var128)
+    + (param64 == var128)
+    + (param128 == var128)
+    /* Small enough relative difference?  */
+    + ((((_Decimal128)param16 - var128) / var128) < 0.002dl);
+}
+
+int main()
+{
+  if (foo32 (1.2df, 1.2dd, 1.2dl, (_Float16)1.2) != 4)
+    abort ();
+
+  if (foo64 (1.2df, 1.2dd, 1.2dl, (_Float16)1.2) != 4)
+    abort ();
+
+  if (foo128 (1.2df, 1.2dd, 1.2dl, (_Float16)1.2) != 4)
+    abort ();
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {\t__bid_extendsddd2} 3 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_extendsdtd2} 3 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_extendddtd2} 3 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_extendhfsd} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_extendhfdd} 2 { target { dfp_bid } } } } */
+/* { dg-final { scan-assembler-times {\t__bid_extendhftd} 2 { target { dfp_bid } } } } */