diff mbox series

RISC-V: Nan-box the result of movbf on soft-bf16

Message ID 20240507064139.26230-1-zengxiao@eswincomputing.com
State New
Headers show
Series RISC-V: Nan-box the result of movbf on soft-bf16 | expand

Commit Message

Xiao Zeng May 7, 2024, 6:41 a.m. UTC 
1 This patch implements the Nan-box of bf16.

2 Please refer to the Nan-box implementation of hf16 in:
<https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=057dc349021660c40699fb5c98fd9cac8e168653>

3 The discussion about Nan-box can be found on the website:
<https://www.mail-archive.com/search?q=Nan-box+the+result+of+movhf+on+soft-fp16&l=gcc-patches%40gcc.gnu.org>

4 Below test are passed for this patch
        * The riscv fully regression test.

gcc/ChangeLog:

	* config/riscv/riscv.cc (riscv_legitimize_move): Expand movbf
	with Nan-boxing value.
	* config/riscv/riscv.md (*movbf_softfloat_boxing): New pattern.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/_Bfloat16-nanboxing.c: New test.
---
 gcc/config/riscv/riscv.cc                     | 51 ++++++++++---------
 gcc/config/riscv/riscv.md                     | 11 +++-
 .../gcc.target/riscv/_Bfloat16-nanboxing.c    | 38 ++++++++++++++
 3 files changed, 75 insertions(+), 25 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/_Bfloat16-nanboxing.c
diff mbox series

Patch

diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 545e68566dc..6976064b88b 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -3120,35 +3120,38 @@  riscv_legitimize_move (machine_mode mode, rtx dest, rtx src)
     }
 
   /* In order to fit NaN boxing, expand
-     (set FP_REG (reg:HF src))
+     (set FP_REG (reg:HF/BF src))
      to
      (set (reg:SI/DI mask) (const_int -65536)
-     (set (reg:SI/DI temp) (zero_extend:SI/DI (subreg:HI (reg:HF src) 0)))
+     (set (reg:SI/DI temp) (zero_extend:SI/DI (subreg:HI (reg:HF/BF src) 0)))
      (set (reg:SI/DI temp) (ior:SI/DI (reg:SI/DI mask) (reg:SI/DI temp)))
-     (set (reg:HF dest) (unspec:HF [ (reg:SI/DI temp) ] UNSPEC_FMV_SFP16_X))
+     (set (reg:HF/BF dest) (unspec:HF/BF [ (reg:SI/DI temp) ]
+			    UNSPEC_FMV_SFP16_X/UNSPEC_FMV_SBF16_X))
      */
 
- if (TARGET_HARD_FLOAT
-     && !TARGET_ZFHMIN && mode == HFmode
-     && REG_P (dest) && FP_REG_P (REGNO (dest))
-     && REG_P (src) && !FP_REG_P (REGNO (src))
-     && can_create_pseudo_p ())
-   {
-     rtx mask = force_reg (word_mode, gen_int_mode (-65536, word_mode));
-     rtx temp = gen_reg_rtx (word_mode);
-     emit_insn (gen_extend_insn (temp,
-				 simplify_gen_subreg (HImode, src, mode, 0),
-				 word_mode, HImode, 1));
-     if (word_mode == SImode)
-       emit_insn (gen_iorsi3 (temp, mask, temp));
-     else
-       emit_insn (gen_iordi3 (temp, mask, temp));
-
-     riscv_emit_move (dest, gen_rtx_UNSPEC (HFmode, gen_rtvec (1, temp),
-					    UNSPEC_FMV_SFP16_X));
-
-     return true;
-   }
+  if (TARGET_HARD_FLOAT
+      && ((!TARGET_ZFHMIN && mode == HFmode)
+	  || (!TARGET_ZFBFMIN && mode == BFmode))
+      && REG_P (dest) && FP_REG_P (REGNO (dest)) && REG_P (src)
+      && !FP_REG_P (REGNO (src)) && can_create_pseudo_p ())
+    {
+      rtx mask = force_reg (word_mode, gen_int_mode (-65536, word_mode));
+      rtx temp = gen_reg_rtx (word_mode);
+      emit_insn (gen_extend_insn (temp,
+				  simplify_gen_subreg (HImode, src, mode, 0),
+				  word_mode, HImode, 1));
+      if (word_mode == SImode)
+	emit_insn (gen_iorsi3 (temp, mask, temp));
+      else
+	emit_insn (gen_iordi3 (temp, mask, temp));
+
+      riscv_emit_move (dest,
+		       gen_rtx_UNSPEC (mode, gen_rtvec (1, temp),
+				       mode == HFmode ? UNSPEC_FMV_SFP16_X
+						      : UNSPEC_FMV_SBF16_X));
+
+      return true;
+    }
 
   /* We need to deal with constants that would be legitimate
      immediate_operands but aren't legitimate move_operands.  */
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 24558682eb8..b34043bc6b8 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -86,8 +86,9 @@ 
   ;; String unspecs
   UNSPEC_STRLEN
 
-  ;; Workaround for HFmode without hardware extension
+  ;; Workaround for HFmode and BFmode without hardware extension
   UNSPEC_FMV_SFP16_X
+  UNSPEC_FMV_SBF16_X
 
   ;; XTheadFmv moves
   UNSPEC_XTHEADFMV
@@ -1926,6 +1927,14 @@ 
   [(set_attr "type" "fmove")
    (set_attr "mode" "SF")])
 
+(define_insn "*movbf_softfloat_boxing"
+  [(set (match_operand:BF 0 "register_operand"		  "=f")
+	(unspec:BF [(match_operand:X 1 "register_operand" " r")] UNSPEC_FMV_SBF16_X))]
+  "!TARGET_ZFBFMIN"
+  "fmv.w.x\t%0,%1"
+  [(set_attr "type" "fmove")
+   (set_attr "mode" "SF")])
+
 ;;
 ;;  ....................
 ;;
diff --git a/gcc/testsuite/gcc.target/riscv/_Bfloat16-nanboxing.c b/gcc/testsuite/gcc.target/riscv/_Bfloat16-nanboxing.c
new file mode 100644
index 00000000000..11a73d22234
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/_Bfloat16-nanboxing.c
@@ -0,0 +1,38 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64ifd -mabi=lp64d -mcmodel=medlow -O" } */
+
+_Bfloat16 gvar = 9.87654;
+union U
+{
+  unsigned short i16;
+  _Bfloat16 f16;
+};
+
+_Bfloat16
+test1 (unsigned short input)
+{
+  union U tmp;
+  tmp.i16 = input;
+  return tmp.f16;
+}
+
+_Bfloat16
+test2 ()
+{
+  return 1.234f;
+}
+
+_Bfloat16
+test3 ()
+{
+  return gvar;
+}
+
+_Bfloat16
+test ()
+{
+  return 0.0f;
+}
+
+/* { dg-final { scan-assembler-times "li\[ \t\]" 4 } } */
+/* { dg-final { scan-assembler-times "fmv\.w\.x\[ \t\]" 4 } } */