[PATCH] LoongArch: Fix wrong LSX FP vector negation

[Xi Ruoyao]

We expanded (neg x) to (minus const0 x) for LSX FP vectors, this is
wrong because -0.0 is not 0 - 0.0.  This causes some Python tests to
fail when Python is built with LSX enabled.

Use the vbitrevi.{d/w} instructions to simply reverse the sign bit
instead.  We are already doing this for LASX and now we can unify them
into simd.md.

gcc/ChangeLog:

	* config/loongarch/lsx.md (neg<mode:FLSX>2): Remove the
	incorrect expand.
	* config/loongarch/simd.md (simdfmt_as_i): New define_mode_attr.
	(elmsgnbit): Likewise.
	(neg<mode:FVEC>2): New define_insn.
	* config/loongarch/lasx.md (negv4df2, negv8sf2): Remove as they
	are now instantiated in simd.md.
---

Bootstrapped and regtested on loongarch64-linux-gnu.  Ok for trunk?

 gcc/config/loongarch/lasx.md | 16 ----------------
 gcc/config/loongarch/lsx.md  | 11 -----------
 gcc/config/loongarch/simd.md | 18 ++++++++++++++++++
 3 files changed, 18 insertions(+), 27 deletions(-)

diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md
index e2115ffb884..ac84db7f0ce 100644
--- a/gcc/config/loongarch/lasx.md
+++ b/gcc/config/loongarch/lasx.md
@@ -3028,22 +3028,6 @@ (define_insn "absv8sf2"
   [(set_attr "type" "simd_logic")
    (set_attr "mode" "V8SF")])
 
-(define_insn "negv4df2"
-  [(set (match_operand:V4DF 0 "register_operand" "=f")
-	(neg:V4DF (match_operand:V4DF 1 "register_operand" "f")))]
-  "ISA_HAS_LASX"
-  "xvbitrevi.d\t%u0,%u1,63"
-  [(set_attr "type" "simd_logic")
-   (set_attr "mode" "V4DF")])
-
-(define_insn "negv8sf2"
-  [(set (match_operand:V8SF 0 "register_operand" "=f")
-	(neg:V8SF (match_operand:V8SF 1 "register_operand" "f")))]
-  "ISA_HAS_LASX"
-  "xvbitrevi.w\t%u0,%u1,31"
-  [(set_attr "type" "simd_logic")
-   (set_attr "mode" "V8SF")])
-
 (define_insn "xvfmadd<mode>4"
   [(set (match_operand:FLASX 0 "register_operand" "=f")
 	(fma:FLASX (match_operand:FLASX 1 "register_operand" "f")
diff --git a/gcc/config/loongarch/lsx.md b/gcc/config/loongarch/lsx.md
index 7002edae4d4..b9b94b9079c 100644
--- a/gcc/config/loongarch/lsx.md
+++ b/gcc/config/loongarch/lsx.md
@@ -728,17 +728,6 @@ (define_expand "neg<mode>2"
   DONE;
 })
 
-(define_expand "neg<mode>2"
-  [(set (match_operand:FLSX 0 "register_operand")
-	(neg:FLSX (match_operand:FLSX 1 "register_operand")))]
-  "ISA_HAS_LSX"
-{
-  rtx reg = gen_reg_rtx (<MODE>mode);
-  emit_move_insn (reg, CONST0_RTX (<MODE>mode));
-  emit_insn (gen_sub<mode>3 (operands[0], reg, operands[1]));
-  DONE;
-})
-
 (define_expand "lsx_vrepli<mode>"
   [(match_operand:ILSX 0 "register_operand")
    (match_operand 1 "const_imm10_operand")]
diff --git a/gcc/config/loongarch/simd.md b/gcc/config/loongarch/simd.md
index cb0a19447a1..00ff2823a4e 100644
--- a/gcc/config/loongarch/simd.md
+++ b/gcc/config/loongarch/simd.md
@@ -85,12 +85,21 @@ (define_mode_attr simdfmt [(V2DF "d") (V4DF "d")
 (define_mode_attr simdifmt_for_f [(V2DF "l") (V4DF "l")
 				  (V4SF "w") (V8SF "w")])
 
+;; Suffix for integer mode in LSX or LASX instructions to operating FP
+;; vectors using integer vector operations.
+(define_mode_attr simdfmt_as_i [(V2DF "d") (V4DF "d")
+				(V4SF "w") (V8SF "w")])
+
 ;; Size of vector elements in bits.
 (define_mode_attr elmbits [(V2DI "64") (V4DI "64")
 			   (V4SI "32") (V8SI "32")
 			   (V8HI "16") (V16HI "16")
 			   (V16QI "8") (V32QI "8")])
 
+;; The index of sign bit in FP vector elements.
+(define_mode_attr elmsgnbit [(V2DF "63") (V4DF "63")
+			     (V4SF "31") (V8SF "31")])
+
 ;; This attribute is used to form an immediate operand constraint using
 ;; "const_<bitimm>_operand".
 (define_mode_attr bitimm [(V16QI "uimm3") (V32QI "uimm3")
@@ -457,6 +466,15 @@ (define_expand "reduc_<fmaxmin>_scal_<mode>"
   DONE;
 })
 
+;; FP negation.
+(define_insn "neg<mode>2"
+  [(set (match_operand:FVEC 0 "register_operand" "=f")
+	(neg:FVEC (match_operand:FVEC 1 "register_operand" "f")))]
+  ""
+  "<x>vbitrevi.<simdfmt_as_i>\t%<wu>0,%<wu>1,<elmsgnbit>"
+  [(set_attr "type" "simd_logic")
+   (set_attr "mode" "<MODE>")])
+
 ; The LoongArch SX Instructions.
 (include "lsx.md")
 
-- 
2.43.0