diff mbox series

[v2,3/5] LoongArch: Redefine pattern for xvfrecip/vfrecip instructions.

Message ID 20231205070147.53352-4-xujiahao@loongson.cn
State New
Headers show
Series Add support for approximate instructions and optimize divf/sqrtf/rsqrt operations. | expand

Commit Message

Jiahao Xu Dec. 5, 2023, 7:01 a.m. UTC 
Redefine pattern for [x]vfrecip instructions use rtx code instead of unspec, and enable
[x]vfrecip instructions to be generated during auto-vectorization.

gcc/ChangeLog:

	* config/loongarch/lasx.md (lasx_xvfrecip_<flasxfmt>): Renamed to ..
	(recip<mode>3): .. this.
	* config/loongarch/loongarch-builtins.cc (CODE_FOR_lsx_vfrecip_d): Redefine
	to new pattern name.
	(CODE_FOR_lsx_vfrecip_s): Ditto.
	(CODE_FOR_lasx_xvfrecip_d): Ditto.
	(CODE_FOR_lasx_xvfrecip_s): Ditto.
	(loongarch_expand_builtin_direct): For the vector recip instructions, construct a
	temporary parameter const1_vector.
	* config/loongarch/lsx.md (lsx_vfrecip_<flsxfmt>): Renamed to ..
	(recip<mode>3): .. this.
	* config/loongarch/predicates.md (const_vector_1_operand): New predicate.
diff mbox series

Patch

diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md
index c8edc1bfd76..e4310c4523d 100644
--- a/gcc/config/loongarch/lasx.md
+++ b/gcc/config/loongarch/lasx.md
@@ -1626,12 +1626,12 @@  (define_insn "lasx_xvfmina_<flasxfmt>"
   [(set_attr "type" "simd_fminmax")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "lasx_xvfrecip_<flasxfmt>"
+(define_insn "recip<mode>3"
   [(set (match_operand:FLASX 0 "register_operand" "=f")
-	(unspec:FLASX [(match_operand:FLASX 1 "register_operand" "f")]
-		      UNSPEC_LASX_XVFRECIP))]
+       (div:FLASX (match_operand:FLASX 1 "const_vector_1_operand" "")
+		  (match_operand:FLASX 2 "register_operand" "f")))]
   "ISA_HAS_LASX"
-  "xvfrecip.<flasxfmt>\t%u0,%u1"
+  "xvfrecip.<flasxfmt>\t%u0,%u2"
   [(set_attr "type" "simd_fdiv")
    (set_attr "mode" "<MODE>")])
 
diff --git a/gcc/config/loongarch/loongarch-builtins.cc b/gcc/config/loongarch/loongarch-builtins.cc
index b196e142d61..e0933537166 100644
--- a/gcc/config/loongarch/loongarch-builtins.cc
+++ b/gcc/config/loongarch/loongarch-builtins.cc
@@ -502,6 +502,8 @@  AVAIL_ALL (lasx_frecipe, ISA_HAS_LASX && TARGET_FRECIPE)
 #define CODE_FOR_lsx_vssrlrn_wu_d CODE_FOR_lsx_vssrlrn_u_wu_d
 #define CODE_FOR_lsx_vfrsqrt_d CODE_FOR_rsqrtv2df2
 #define CODE_FOR_lsx_vfrsqrt_s CODE_FOR_rsqrtv4sf2
+#define CODE_FOR_lsx_vfrecip_d CODE_FOR_recipv2df3
+#define CODE_FOR_lsx_vfrecip_s CODE_FOR_recipv4sf3
 
 /* LoongArch ASX define CODE_FOR_lasx_mxxx */
 #define CODE_FOR_lasx_xvsadd_b CODE_FOR_ssaddv32qi3
@@ -780,6 +782,8 @@  AVAIL_ALL (lasx_frecipe, ISA_HAS_LASX && TARGET_FRECIPE)
 #define CODE_FOR_lasx_xvsat_du CODE_FOR_lasx_xvsat_u_du
 #define CODE_FOR_lasx_xvfrsqrt_d CODE_FOR_rsqrtv4df2
 #define CODE_FOR_lasx_xvfrsqrt_s CODE_FOR_rsqrtv8sf2
+#define CODE_FOR_lasx_xvfrecip_d CODE_FOR_recipv4df3
+#define CODE_FOR_lasx_xvfrecip_s CODE_FOR_recipv8sf3
 
 static const struct loongarch_builtin_description loongarch_builtins[] = {
 #define LARCH_MOVFCSR2GR 0
@@ -3024,6 +3028,22 @@  loongarch_expand_builtin_direct (enum insn_code icode, rtx target, tree exp,
   if (has_target_p)
     create_output_operand (&ops[opno++], target, TYPE_MODE (TREE_TYPE (exp)));
 
+  /* For the vector reciprocal instructions, we need to construct a temporary
+     parameter const1_vector.  */
+  switch (icode)
+    {
+    case CODE_FOR_recipv8sf3:
+    case CODE_FOR_recipv4df3:
+    case CODE_FOR_recipv4sf3:
+    case CODE_FOR_recipv2df3:
+      loongarch_prepare_builtin_arg (&ops[2], exp, 0);
+      create_input_operand (&ops[1], CONST1_RTX (ops[0].mode), ops[0].mode);
+      return loongarch_expand_builtin_insn (icode, 3, ops, has_target_p);
+
+    default:
+      break;
+    }
+
   /* Map the arguments to the other operands.  */
   gcc_assert (opno + call_expr_nargs (exp)
 	      == insn_data[icode].n_generator_args);
diff --git a/gcc/config/loongarch/lsx.md b/gcc/config/loongarch/lsx.md
index aeae1b1a622..06402e3b353 100644
--- a/gcc/config/loongarch/lsx.md
+++ b/gcc/config/loongarch/lsx.md
@@ -1539,12 +1539,12 @@  (define_insn "lsx_vfmina_<flsxfmt>"
   [(set_attr "type" "simd_fminmax")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "lsx_vfrecip_<flsxfmt>"
+(define_insn "recip<mode>3"
   [(set (match_operand:FLSX 0 "register_operand" "=f")
-	(unspec:FLSX [(match_operand:FLSX 1 "register_operand" "f")]
-		     UNSPEC_LSX_VFRECIP))]
+       (div:FLSX (match_operand:FLSX 1 "const_vector_1_operand" "")
+		 (match_operand:FLSX 2 "register_operand" "f")))]
   "ISA_HAS_LSX"
-  "vfrecip.<flsxfmt>\t%w0,%w1"
+  "vfrecip.<flsxfmt>\t%w0,%w2"
   [(set_attr "type" "simd_fdiv")
    (set_attr "mode" "<MODE>")])
 
diff --git a/gcc/config/loongarch/predicates.md b/gcc/config/loongarch/predicates.md
index d02e846cb12..f7796da10b2 100644
--- a/gcc/config/loongarch/predicates.md
+++ b/gcc/config/loongarch/predicates.md
@@ -227,6 +227,10 @@  (define_predicate "const_1_operand"
   (and (match_code "const_int,const_wide_int,const_double,const_vector")
        (match_test "op == CONST1_RTX (GET_MODE (op))")))
 
+(define_predicate "const_vector_1_operand"
+  (and (match_code "const_vector")
+       (match_test "op == CONST1_RTX (GET_MODE (op))")))
+
 (define_predicate "reg_or_1_operand"
   (ior (match_operand 0 "const_1_operand")
        (match_operand 0 "register_operand")))