From: Jiahao Xu <xujiahao@loongson.cn>
To: gcc-patches@gcc.gnu.org
Cc: xry111@xry111.site, i@xen0n.name, chenglulu@loongson.cn,
xuchenghua@loongson.cn, Jiahao Xu <xujiahao@loongson.cn>
Subject: [PATCH v2 1/5] LoongArch: Add support for LoongArch V1.1 approximate instructions.
Date: Tue, 5 Dec 2023 15:01:43 +0800 [thread overview]
Message-ID: <20231205070147.53352-2-xujiahao@loongson.cn> (raw)
In-Reply-To: <20231205070147.53352-1-xujiahao@loongson.cn>
This patch adds define_insn/builtins/intrinsics for these instructions, and add option
-mfrecipe to control instruction generation.
gcc/ChangeLog:
* config/loongarch/genopts/isa-evolution.in (fecipe): Add.
* config/loongarch/larchintrin.h (__frecipe_s): New intrinsic.
(__frecipe_d): Ditto.
(__frsqrte_s): Ditto.
(__frsqrte_d): Ditto.
* config/loongarch/lasx.md (lasx_xvfrecipe_<flasxfmt>): New insn pattern.
(lasx_xvfrsqrte_<flasxfmt>): Ditto.
* config/loongarch/lasxintrin.h (__lasx_xvfrecipe_s): New intrinsic.
(__lasx_xvfrecipe_d): Ditto.
(__lasx_xvfrsqrte_s): Ditto.
(__lasx_xvfrsqrte_d): Ditto.
* config/loongarch/loongarch-builtins.cc (AVAIL_ALL): Add predicates.
(LSX_EXT_BUILTIN): New macro.
(LASX_EXT_BUILTIN): Ditto.
* config/loongarch/loongarch-cpucfg-map.h: Regenerate.
* config/loongarch/loongarch-str.h (OPTSTR_FRECIPE): Regenerate.
* config/loongarch/loongarch.cc (loongarch_asm_code_end): Dump status for TARGET_FRECIPE.
* config/loongarch/loongarch.md (loongarch_frecipe_<fmt>): New insn pattern.
(loongarch_frsqrte_<fmt>): Ditto.
* config/loongarch/loongarch.opt: Regenerate.
* config/loongarch/lsx.md (lsx_vfrecipe_<flsxfmt>): New insn pattern.
(lsx_vfrsqrte_<flsxfmt>): Ditto.
* config/loongarch/lsxintrin.h (__lsx_vfrecipe_s): New intrinsic.
(__lsx_vfrecipe_d): Ditto.
(__lsx_vfrsqrte_s): Ditto.
(__lsx_vfrsqrte_d): Ditto.
* doc/extend.texi: Add documentation for LoongArch new builtins and intrinsics.
gcc/testsuite/ChangeLog:
* gcc.target/loongarch/larch-frecipe-builtin.c: New test.
* gcc.target/loongarch/vector/lasx/lasx-frecipe-builtin.c: New test.
* gcc.target/loongarch/vector/lsx/lsx-frecipe-builtin.c: New test.
diff --git a/gcc/config/loongarch/genopts/isa-evolution.in b/gcc/config/loongarch/genopts/isa-evolution.in
index a6bc3f87f20..11a198b649f 100644
--- a/gcc/config/loongarch/genopts/isa-evolution.in
+++ b/gcc/config/loongarch/genopts/isa-evolution.in
@@ -1,3 +1,4 @@
+2 25 frecipe Support frecipe.{s/d} and frsqrte.{s/d} instructions.
2 26 div32 Support div.w[u] and mod.w[u] instructions with inputs not sign-extended.
2 27 lam-bh Support am{swap/add}[_db].{b/h} instructions.
2 28 lamcas Support amcas[_db].{b/h/w/d} instructions.
diff --git a/gcc/config/loongarch/larchintrin.h b/gcc/config/loongarch/larchintrin.h
index e571ed27b37..028081cccfb 100644
--- a/gcc/config/loongarch/larchintrin.h
+++ b/gcc/config/loongarch/larchintrin.h
@@ -333,6 +333,44 @@ __iocsrwr_d (unsigned long int _1, unsigned int _2)
}
#endif
+#if defined(__loongarch64) && defined(TARGET_FRECIPE)
+/* Assembly instruction format: fd, fj. */
+/* Data types in instruction templates: SF, SF. */
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__frecipe_s (float _1)
+{
+ __builtin_loongarch_frecipe_s ((float) _1);
+}
+
+/* Assembly instruction format: fd, fj. */
+/* Data types in instruction templates: DF, DF. */
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__frecipe_d (double _1)
+{
+ __builtin_loongarch_frecipe_d ((double) _1);
+}
+
+/* Assembly instruction format: fd, fj. */
+/* Data types in instruction templates: SF, SF. */
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__frsqrte_s (float _1)
+{
+ __builtin_loongarch_frsqrte_s ((float) _1);
+}
+
+/* Assembly instruction format: fd, fj. */
+/* Data types in instruction templates: DF, DF. */
+extern __inline void
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__frsqrte_d (double _1)
+{
+ __builtin_loongarch_frsqrte_d ((double) _1);
+}
+#endif
+
/* Assembly instruction format: ui15. */
/* Data types in instruction templates: USI. */
#define __dbar(/*ui15*/ _1) __builtin_loongarch_dbar ((_1))
diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md
index 116b30c0774..f6e5208a6f1 100644
--- a/gcc/config/loongarch/lasx.md
+++ b/gcc/config/loongarch/lasx.md
@@ -40,8 +40,10 @@ (define_c_enum "unspec" [
UNSPEC_LASX_XVFCVTL
UNSPEC_LASX_XVFLOGB
UNSPEC_LASX_XVFRECIP
+ UNSPEC_LASX_XVFRECIPE
UNSPEC_LASX_XVFRINT
UNSPEC_LASX_XVFRSQRT
+ UNSPEC_LASX_XVFRSQRTE
UNSPEC_LASX_XVFCMP_SAF
UNSPEC_LASX_XVFCMP_SEQ
UNSPEC_LASX_XVFCMP_SLE
@@ -1633,6 +1635,17 @@ (define_insn "lasx_xvfrecip_<flasxfmt>"
[(set_attr "type" "simd_fdiv")
(set_attr "mode" "<MODE>")])
+;; Approximate Reciprocal Instructions.
+
+(define_insn "lasx_xvfrecipe_<flasxfmt>"
+ [(set (match_operand:FLASX 0 "register_operand" "=f")
+ (unspec:FLASX [(match_operand:FLASX 1 "register_operand" "f")]
+ UNSPEC_LASX_XVFRECIPE))]
+ "ISA_HAS_LASX && TARGET_FRECIPE"
+ "xvfrecipe.<flasxfmt>\t%u0,%u1"
+ [(set_attr "type" "simd_fdiv")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "lasx_xvfrsqrt_<flasxfmt>"
[(set (match_operand:FLASX 0 "register_operand" "=f")
(unspec:FLASX [(match_operand:FLASX 1 "register_operand" "f")]
@@ -1642,6 +1655,17 @@ (define_insn "lasx_xvfrsqrt_<flasxfmt>"
[(set_attr "type" "simd_fdiv")
(set_attr "mode" "<MODE>")])
+;; Approximate Reciprocal Square Root Instructions.
+
+(define_insn "lasx_xvfrsqrte_<flasxfmt>"
+ [(set (match_operand:FLASX 0 "register_operand" "=f")
+ (unspec:FLASX [(match_operand:FLASX 1 "register_operand" "f")]
+ UNSPEC_LASX_XVFRSQRTE))]
+ "ISA_HAS_LASX && TARGET_FRECIPE"
+ "xvfrsqrte.<flasxfmt>\t%u0,%u1"
+ [(set_attr "type" "simd_fdiv")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "lasx_xvftint_u_<ilasxfmt_u>_<flasxfmt>"
[(set (match_operand:<VIMODE256> 0 "register_operand" "=f")
(unspec:<VIMODE256> [(match_operand:FLASX 1 "register_operand" "f")]
diff --git a/gcc/config/loongarch/lasxintrin.h b/gcc/config/loongarch/lasxintrin.h
index 7bce2c757f1..c76eb6c58ef 100644
--- a/gcc/config/loongarch/lasxintrin.h
+++ b/gcc/config/loongarch/lasxintrin.h
@@ -2399,6 +2399,40 @@ __m256d __lasx_xvfrecip_d (__m256d _1)
return (__m256d)__builtin_lasx_xvfrecip_d ((v4f64)_1);
}
+#ifdef TARGET_FRECIPE
+/* Assembly instruction format: xd, xj. */
+/* Data types in instruction templates: V8SF, V8SF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m256 __lasx_xvfrecipe_s (__m256 _1)
+{
+ return (__m256)__builtin_lasx_xvfrecipe_s ((v8f32)_1);
+}
+
+/* Assembly instruction format: xd, xj. */
+/* Data types in instruction templates: V4DF, V4DF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m256d __lasx_xvfrecipe_d (__m256d _1)
+{
+ return (__m256d)__builtin_lasx_xvfrecipe_d ((v4f64)_1);
+}
+
+/* Assembly instruction format: xd, xj. */
+/* Data types in instruction templates: V8SF, V8SF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m256 __lasx_xvfrsqrte_s (__m256 _1)
+{
+ return (__m256)__builtin_lasx_xvfrsqrte_s ((v8f32)_1);
+}
+
+/* Assembly instruction format: xd, xj. */
+/* Data types in instruction templates: V4DF, V4DF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m256d __lasx_xvfrsqrte_d (__m256d _1)
+{
+ return (__m256d)__builtin_lasx_xvfrsqrte_d ((v4f64)_1);
+}
+#endif
+
/* Assembly instruction format: xd, xj. */
/* Data types in instruction templates: V8SF, V8SF. */
extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
diff --git a/gcc/config/loongarch/loongarch-builtins.cc b/gcc/config/loongarch/loongarch-builtins.cc
index 5d037ab7f10..bf95a44c0d2 100644
--- a/gcc/config/loongarch/loongarch-builtins.cc
+++ b/gcc/config/loongarch/loongarch-builtins.cc
@@ -120,6 +120,9 @@ struct loongarch_builtin_description
AVAIL_ALL (hard_float, TARGET_HARD_FLOAT_ABI)
AVAIL_ALL (lsx, ISA_HAS_LSX)
AVAIL_ALL (lasx, ISA_HAS_LASX)
+AVAIL_ALL (frecipe, TARGET_FRECIPE)
+AVAIL_ALL (lsx_frecipe, ISA_HAS_LSX && TARGET_FRECIPE)
+AVAIL_ALL (lasx_frecipe, ISA_HAS_LASX && TARGET_FRECIPE)
/* Construct a loongarch_builtin_description from the given arguments.
@@ -164,6 +167,15 @@ AVAIL_ALL (lasx, ISA_HAS_LASX)
"__builtin_lsx_" #INSN, LARCH_BUILTIN_DIRECT, \
FUNCTION_TYPE, loongarch_builtin_avail_lsx }
+ /* Define an LSX LARCH_BUILTIN_DIRECT function __builtin_lsx_<INSN>
+ for instruction CODE_FOR_lsx_<INSN>. FUNCTION_TYPE is a builtin_description
+ field. AVAIL is the name of the availability predicate, without the leading
+ loongarch_builtin_avail_. */
+#define LSX_EXT_BUILTIN(INSN, FUNCTION_TYPE, AVAIL) \
+ { CODE_FOR_lsx_ ## INSN, \
+ "__builtin_lsx_" #INSN, LARCH_BUILTIN_DIRECT, \
+ FUNCTION_TYPE, loongarch_builtin_avail_##AVAIL }
+
/* Define an LSX LARCH_BUILTIN_LSX_TEST_BRANCH function __builtin_lsx_<INSN>
for instruction CODE_FOR_lsx_<INSN>. FUNCTION_TYPE is a builtin_description
@@ -189,6 +201,15 @@ AVAIL_ALL (lasx, ISA_HAS_LASX)
"__builtin_lasx_" #INSN, LARCH_BUILTIN_LASX, \
FUNCTION_TYPE, loongarch_builtin_avail_lasx }
+/* Define an LASX LARCH_BUILTIN_DIRECT function __builtin_lasx_<INSN>
+ for instruction CODE_FOR_lasx_<INSN>. FUNCTION_TYPE is a builtin_description
+ field. AVAIL is the name of the availability predicate, without the leading
+ loongarch_builtin_avail_. */
+#define LASX_EXT_BUILTIN(INSN, FUNCTION_TYPE, AVAIL) \
+ { CODE_FOR_lasx_ ## INSN, \
+ "__builtin_lasx_" #INSN, LARCH_BUILTIN_LASX, \
+ FUNCTION_TYPE, loongarch_builtin_avail_##AVAIL }
+
/* Define an LASX LARCH_BUILTIN_DIRECT_NO_TARGET function __builtin_lasx_<INSN>
for instruction CODE_FOR_lasx_<INSN>. FUNCTION_TYPE is a builtin_description
field. */
@@ -804,6 +825,27 @@ static const struct loongarch_builtin_description loongarch_builtins[] = {
DIRECT_NO_TARGET_BUILTIN (syscall, LARCH_VOID_FTYPE_USI, default),
DIRECT_NO_TARGET_BUILTIN (break, LARCH_VOID_FTYPE_USI, default),
+ /* Built-in functions for frecipe.{s/d} and frsqrte.{s/d}. */
+
+ DIRECT_BUILTIN (frecipe_s, LARCH_SF_FTYPE_SF, frecipe),
+ DIRECT_BUILTIN (frecipe_d, LARCH_DF_FTYPE_DF, frecipe),
+ DIRECT_BUILTIN (frsqrte_s, LARCH_SF_FTYPE_SF, frecipe),
+ DIRECT_BUILTIN (frsqrte_d, LARCH_DF_FTYPE_DF, frecipe),
+
+ /* Built-in functions for new LSX instructions. */
+
+ LSX_EXT_BUILTIN (vfrecipe_s, LARCH_V4SF_FTYPE_V4SF, lsx_frecipe),
+ LSX_EXT_BUILTIN (vfrecipe_d, LARCH_V2DF_FTYPE_V2DF, lsx_frecipe),
+ LSX_EXT_BUILTIN (vfrsqrte_s, LARCH_V4SF_FTYPE_V4SF, lsx_frecipe),
+ LSX_EXT_BUILTIN (vfrsqrte_d, LARCH_V2DF_FTYPE_V2DF, lsx_frecipe),
+
+ /* Built-in functions for new LASX instructions. */
+
+ LASX_EXT_BUILTIN (xvfrecipe_s, LARCH_V8SF_FTYPE_V8SF, lasx_frecipe),
+ LASX_EXT_BUILTIN (xvfrecipe_d, LARCH_V4DF_FTYPE_V4DF, lasx_frecipe),
+ LASX_EXT_BUILTIN (xvfrsqrte_s, LARCH_V8SF_FTYPE_V8SF, lasx_frecipe),
+ LASX_EXT_BUILTIN (xvfrsqrte_d, LARCH_V4DF_FTYPE_V4DF, lasx_frecipe),
+
/* Built-in functions for LSX. */
LSX_BUILTIN (vsll_b, LARCH_V16QI_FTYPE_V16QI_V16QI),
LSX_BUILTIN (vsll_h, LARCH_V8HI_FTYPE_V8HI_V8HI),
diff --git a/gcc/config/loongarch/loongarch-cpucfg-map.h b/gcc/config/loongarch/loongarch-cpucfg-map.h
index 02ff1671255..148333c249c 100644
--- a/gcc/config/loongarch/loongarch-cpucfg-map.h
+++ b/gcc/config/loongarch/loongarch-cpucfg-map.h
@@ -29,6 +29,7 @@ static constexpr struct {
unsigned int cpucfg_bit;
HOST_WIDE_INT isa_evolution_bit;
} cpucfg_map[] = {
+ { 2, 1u << 25, OPTION_MASK_ISA_FRECIPE },
{ 2, 1u << 26, OPTION_MASK_ISA_DIV32 },
{ 2, 1u << 27, OPTION_MASK_ISA_LAM_BH },
{ 2, 1u << 28, OPTION_MASK_ISA_LAMCAS },
diff --git a/gcc/config/loongarch/loongarch-str.h b/gcc/config/loongarch/loongarch-str.h
index 0384493765c..236b804766e 100644
--- a/gcc/config/loongarch/loongarch-str.h
+++ b/gcc/config/loongarch/loongarch-str.h
@@ -69,6 +69,7 @@ along with GCC; see the file COPYING3. If not see
#define STR_EXPLICIT_RELOCS_NONE "none"
#define STR_EXPLICIT_RELOCS_ALWAYS "always"
+#define OPTSTR_FRECIPE "frecipe"
#define OPTSTR_DIV32 "div32"
#define OPTSTR_LAM_BH "lam-bh"
#define OPTSTR_LAMCAS "lamcas"
diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index 3545e66a10e..57a20bec8a4 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -11503,6 +11503,7 @@ loongarch_asm_code_end (void)
loongarch_cpu_strings [la_target.cpu_tune]);
fprintf (asm_out_file, "%s Base ISA: %s\n", ASM_COMMENT_START,
loongarch_isa_base_strings [la_target.isa.base]);
+ DUMP_FEATURE (TARGET_FRECIPE);
DUMP_FEATURE (TARGET_DIV32);
DUMP_FEATURE (TARGET_LAM_BH);
DUMP_FEATURE (TARGET_LAMCAS);
diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index 7a101dd64b7..07beede8892 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -59,6 +59,12 @@ (define_c_enum "unspec" [
;; Stack tie
UNSPEC_TIE
+ ;; RSQRT
+ UNSPEC_RSQRTE
+
+ ;; RECIP
+ UNSPEC_RECIPE
+
;; CRC
UNSPEC_CRC
UNSPEC_CRCC
@@ -220,6 +226,7 @@ (define_attr "qword_mode" "no,yes"
;; fmadd floating point multiply-add
;; fdiv floating point divide
;; frdiv floating point reciprocal divide
+;; frecipe floating point approximate reciprocal
;; fabs floating point absolute value
;; flogb floating point exponent extract
;; fneg floating point negation
@@ -229,6 +236,7 @@ (define_attr "qword_mode" "no,yes"
;; fscaleb floating point scale
;; fsqrt floating point square root
;; frsqrt floating point reciprocal square root
+;; frsqrte floating point approximate reciprocal square root
;; multi multiword sequence (or user asm statements)
;; atomic atomic memory update instruction
;; syncloop memory atomic operation implemented as a sync loop
@@ -238,8 +246,8 @@ (define_attr "type"
"unknown,branch,jump,call,load,fpload,fpidxload,store,fpstore,fpidxstore,
prefetch,prefetchx,condmove,mgtf,mftg,const,arith,logical,
shift,slt,signext,clz,trap,imul,idiv,move,
- fmove,fadd,fmul,fmadd,fdiv,frdiv,fabs,flogb,fneg,fcmp,fcopysign,fcvt,
- fscaleb,fsqrt,frsqrt,accext,accmod,multi,atomic,syncloop,nop,ghost,
+ fmove,fadd,fmul,fmadd,fdiv,frdiv,frecipe,fabs,flogb,fneg,fcmp,fcopysign,fcvt,
+ fscaleb,fsqrt,frsqrt,frsqrte,accext,accmod,multi,atomic,syncloop,nop,ghost,
simd_div,simd_fclass,simd_flog2,simd_fadd,simd_fcvt,simd_fmul,simd_fmadd,
simd_fdiv,simd_bitins,simd_bitmov,simd_insert,simd_sld,simd_mul,simd_fcmp,
simd_fexp2,simd_int_arith,simd_bit,simd_shift,simd_splat,simd_fill,
@@ -908,6 +916,18 @@ (define_insn "*recip<mode>3"
[(set_attr "type" "frdiv")
(set_attr "mode" "<UNITMODE>")])
+;; Approximate Reciprocal Instructions.
+
+(define_insn "loongarch_frecipe_<fmt>"
+ [(set (match_operand:ANYF 0 "register_operand" "=f")
+ (unspec:ANYF [(match_operand:ANYF 1 "register_operand" "f")]
+ UNSPEC_RECIPE))]
+ "TARGET_FRECIPE"
+ "frecipe.<fmt>\t%0,%1"
+ [(set_attr "type" "frecipe")
+ (set_attr "mode" "<UNITMODE>")
+ (set_attr "insn_count" "1")])
+
;; Integer division and modulus.
(define_expand "<optab><mode>3"
[(set (match_operand:GPR 0 "register_operand")
@@ -1133,6 +1153,17 @@ (define_insn "*rsqrt<mode>b"
[(set_attr "type" "frsqrt")
(set_attr "mode" "<UNITMODE>")
(set_attr "insn_count" "1")])
+
+;; Approximate Reciprocal Square Root Instructions.
+
+(define_insn "loongarch_frsqrte_<fmt>"
+ [(set (match_operand:ANYF 0 "register_operand" "=f")
+ (unspec:ANYF [(match_operand:ANYF 1 "register_operand" "f")]
+ UNSPEC_RSQRTE))]
+ "TARGET_FRECIPE"
+ "frsqrte.<fmt>\t%0,%1"
+ [(set_attr "type" "frsqrte")
+ (set_attr "mode" "<UNITMODE>")])
\f
;;
;; ....................
diff --git a/gcc/config/loongarch/loongarch.opt b/gcc/config/loongarch/loongarch.opt
index 4d36e3ec4de..38c6b23d400 100644
--- a/gcc/config/loongarch/loongarch.opt
+++ b/gcc/config/loongarch/loongarch.opt
@@ -263,6 +263,10 @@ default value is 4.
Variable
HOST_WIDE_INT isa_evolution = 0
+mfrecipe
+Target Mask(ISA_FRECIPE) Var(isa_evolution)
+Support frecipe.{s/d} and frsqrte.{s/d} instructions.
+
mdiv32
Target Mask(ISA_DIV32) Var(isa_evolution)
Support div.w[u] and mod.w[u] instructions with inputs not sign-extended.
diff --git a/gcc/config/loongarch/lsx.md b/gcc/config/loongarch/lsx.md
index 23239993404..e2393aed139 100644
--- a/gcc/config/loongarch/lsx.md
+++ b/gcc/config/loongarch/lsx.md
@@ -42,8 +42,10 @@ (define_c_enum "unspec" [
UNSPEC_LSX_VFCVTL
UNSPEC_LSX_VFLOGB
UNSPEC_LSX_VFRECIP
+ UNSPEC_LSX_VFRECIPE
UNSPEC_LSX_VFRINT
UNSPEC_LSX_VFRSQRT
+ UNSPEC_LSX_VFRSQRTE
UNSPEC_LSX_VFCMP_SAF
UNSPEC_LSX_VFCMP_SEQ
UNSPEC_LSX_VFCMP_SLE
@@ -1546,6 +1548,17 @@ (define_insn "lsx_vfrecip_<flsxfmt>"
[(set_attr "type" "simd_fdiv")
(set_attr "mode" "<MODE>")])
+;; Approximate Reciprocal Instructions.
+
+(define_insn "lsx_vfrecipe_<flsxfmt>"
+ [(set (match_operand:FLSX 0 "register_operand" "=f")
+ (unspec:FLSX [(match_operand:FLSX 1 "register_operand" "f")]
+ UNSPEC_LSX_VFRECIPE))]
+ "ISA_HAS_LSX && TARGET_FRECIPE"
+ "vfrecipe.<flsxfmt>\t%w0,%w1"
+ [(set_attr "type" "simd_fdiv")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "lsx_vfrsqrt_<flsxfmt>"
[(set (match_operand:FLSX 0 "register_operand" "=f")
(unspec:FLSX [(match_operand:FLSX 1 "register_operand" "f")]
@@ -1555,6 +1568,17 @@ (define_insn "lsx_vfrsqrt_<flsxfmt>"
[(set_attr "type" "simd_fdiv")
(set_attr "mode" "<MODE>")])
+;; Approximate Reciprocal Square Root Instructions.
+
+(define_insn "lsx_vfrsqrte_<flsxfmt>"
+ [(set (match_operand:FLSX 0 "register_operand" "=f")
+ (unspec:FLSX [(match_operand:FLSX 1 "register_operand" "f")]
+ UNSPEC_LSX_VFRSQRTE))]
+ "ISA_HAS_LSX && TARGET_FRECIPE"
+ "vfrsqrte.<flsxfmt>\t%w0,%w1"
+ [(set_attr "type" "simd_fdiv")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "lsx_vftint_u_<ilsxfmt_u>_<flsxfmt>"
[(set (match_operand:<VIMODE> 0 "register_operand" "=f")
(unspec:<VIMODE> [(match_operand:FLSX 1 "register_operand" "f")]
diff --git a/gcc/config/loongarch/lsxintrin.h b/gcc/config/loongarch/lsxintrin.h
index 29553c093fa..890173c53e0 100644
--- a/gcc/config/loongarch/lsxintrin.h
+++ b/gcc/config/loongarch/lsxintrin.h
@@ -2480,6 +2480,40 @@ __m128d __lsx_vfrecip_d (__m128d _1)
return (__m128d)__builtin_lsx_vfrecip_d ((v2f64)_1);
}
+#ifdef TARGET_FRECIPE
+/* Assembly instruction format: vd, vj. */
+/* Data types in instruction templates: V4SF, V4SF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m128 __lsx_vfrecipe_s (__m128 _1)
+{
+ return (__m128)__builtin_lsx_vfrecipe_s ((v4f32)_1);
+}
+
+/* Assembly instruction format: vd, vj. */
+/* Data types in instruction templates: V2DF, V2DF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m128d __lsx_vfrecipe_d (__m128d _1)
+{
+ return (__m128d)__builtin_lsx_vfrecipe_d ((v2f64)_1);
+}
+
+/* Assembly instruction format: vd, vj. */
+/* Data types in instruction templates: V4SF, V4SF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m128 __lsx_vfrsqrte_s (__m128 _1)
+{
+ return (__m128)__builtin_lsx_vfrsqrte_s ((v4f32)_1);
+}
+
+/* Assembly instruction format: vd, vj. */
+/* Data types in instruction templates: V2DF, V2DF. */
+extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+__m128d __lsx_vfrsqrte_d (__m128d _1)
+{
+ return (__m128d)__builtin_lsx_vfrsqrte_d ((v2f64)_1);
+}
+#endif
+
/* Assembly instruction format: vd, vj. */
/* Data types in instruction templates: V4SF, V4SF. */
extern __inline __attribute__((__gnu_inline__, __always_inline__, __artificial__))
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 32ae15e1d5b..99eeb83043f 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -17020,6 +17020,11 @@ The intrinsics provided are listed below:
void __builtin_loongarch_iocsrwr_w (unsigned int, unsigned int)
void __builtin_loongarch_iocsrwr_d (unsigned long int, unsigned int)
+ float __builtin_loongarch_frecipe_s (float);
+ double __builtin_loongarch_frecipe_d (double);
+ float __builtin_loongarch_frsqrte_s (float);
+ double __builtin_loongarch_frsqrte_d (double);
+
void __builtin_loongarch_dbar (imm0_32767)
void __builtin_loongarch_ibar (imm0_32767)
@@ -17092,6 +17097,11 @@ function you need to include @code{larchintrin.h}.
void __iocsrwr_w (unsigned int, unsigned int)
void __iocsrwr_d (unsigned long, unsigned int)
+ float __frecipe_s (float);
+ double __frecipe_d (double);
+ float __frsqrte_s (float);
+ double __frsqrte_d (double);
+
void __dbar (imm0_32767)
void __ibar (imm0_32767)
@@ -17434,6 +17444,8 @@ __m128d __lsx_vfnmsub_d (__m128d, __m128d, __m128d);
__m128 __lsx_vfnmsub_s (__m128, __m128, __m128);
__m128d __lsx_vfrecip_d (__m128d);
__m128 __lsx_vfrecip_s (__m128);
+__m128d __lsx_vfrecipe_d (__m128d);
+__m128 __lsx_vfrecipe_s (__m128);
__m128d __lsx_vfrint_d (__m128d);
__m128i __lsx_vfrintrm_d (__m128d);
__m128i __lsx_vfrintrm_s (__m128);
@@ -17446,6 +17458,8 @@ __m128i __lsx_vfrintrz_s (__m128);
__m128 __lsx_vfrint_s (__m128);
__m128d __lsx_vfrsqrt_d (__m128d);
__m128 __lsx_vfrsqrt_s (__m128);
+__m128d __lsx_vfrsqrte_d (__m128d);
+__m128 __lsx_vfrsqrte_s (__m128);
__m128i __lsx_vfrstp_b (__m128i, __m128i, __m128i);
__m128i __lsx_vfrstp_h (__m128i, __m128i, __m128i);
__m128i __lsx_vfrstpi_b (__m128i, __m128i, imm0_31);
@@ -18269,6 +18283,8 @@ __m256d __lasx_xvfnmsub_d (__m256d, __m256d, __m256d);
__m256 __lasx_xvfnmsub_s (__m256, __m256, __m256);
__m256d __lasx_xvfrecip_d (__m256d);
__m256 __lasx_xvfrecip_s (__m256);
+__m256d __lasx_xvfrecipe_d (__m256d);
+__m256 __lasx_xvfrecipe_s (__m256);
__m256d __lasx_xvfrint_d (__m256d);
__m256i __lasx_xvfrintrm_d (__m256d);
__m256i __lasx_xvfrintrm_s (__m256);
@@ -18281,6 +18297,8 @@ __m256i __lasx_xvfrintrz_s (__m256);
__m256 __lasx_xvfrint_s (__m256);
__m256d __lasx_xvfrsqrt_d (__m256d);
__m256 __lasx_xvfrsqrt_s (__m256);
+__m256d __lasx_xvfrsqrte_d (__m256d);
+__m256 __lasx_xvfrsqrte_s (__m256);
__m256i __lasx_xvfrstp_b (__m256i, __m256i, __m256i);
__m256i __lasx_xvfrstp_h (__m256i, __m256i, __m256i);
__m256i __lasx_xvfrstpi_b (__m256i, __m256i, imm0_31);
diff --git a/gcc/testsuite/gcc.target/loongarch/larch-frecipe-builtin.c b/gcc/testsuite/gcc.target/loongarch/larch-frecipe-builtin.c
new file mode 100644
index 00000000000..b9329f34676
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/larch-frecipe-builtin.c
@@ -0,0 +1,28 @@
+/* Test builtins for frecipe.{s/d} and frsqrte.{s/d} instructions */
+/* { dg-do compile } */
+/* { dg-options "-mfrecipe" } */
+/* { dg-final { scan-assembler-times "test_frecipe_s:.*frecipe\\.s.*test_frecipe_s" 1 } } */
+/* { dg-final { scan-assembler-times "test_frecipe_d:.*frecipe\\.d.*test_frecipe_d" 1 } } */
+/* { dg-final { scan-assembler-times "test_frsqrte_s:.*frsqrte\\.s.*test_frsqrte_s" 1 } } */
+/* { dg-final { scan-assembler-times "test_frsqrte_d:.*frsqrte\\.d.*test_frsqrte_d" 1 } } */
+
+float
+test_frecipe_s (float _1)
+{
+ return __builtin_loongarch_frecipe_s (_1);
+}
+double
+test_frecipe_d (double _1)
+{
+ return __builtin_loongarch_frecipe_d (_1);
+}
+float
+test_frsqrte_s (float _1)
+{
+ return __builtin_loongarch_frsqrte_s (_1);
+}
+double
+test_frsqrte_d (double _1)
+{
+ return __builtin_loongarch_frsqrte_d (_1);
+}
diff --git a/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-frecipe-builtin.c b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-frecipe-builtin.c
new file mode 100644
index 00000000000..522535b45a3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-frecipe-builtin.c
@@ -0,0 +1,30 @@
+/* Test builtins for xvfrecipe.{s/d} and xvfrsqrte.{s/d} instructions */
+/* { dg-do compile } */
+/* { dg-options "-mlasx -mfrecipe" } */
+/* { dg-final { scan-assembler-times "lasx_xvfrecipe_s:.*xvfrecipe\\.s.*lasx_xvfrecipe_s" 1 } } */
+/* { dg-final { scan-assembler-times "lasx_xvfrecipe_d:.*xvfrecipe\\.d.*lasx_xvfrecipe_d" 1 } } */
+/* { dg-final { scan-assembler-times "lasx_xvfrsqrte_s:.*xvfrsqrte\\.s.*lasx_xvfrsqrte_s" 1 } } */
+/* { dg-final { scan-assembler-times "lasx_xvfrsqrte_d:.*xvfrsqrte\\.d.*lasx_xvfrsqrte_d" 1 } } */
+
+#include <lasxintrin.h>
+
+v8f32
+__lasx_xvfrecipe_s (v8f32 _1)
+{
+ return __builtin_lasx_xvfrecipe_s (_1);
+}
+v4f64
+__lasx_xvfrecipe_d (v4f64 _1)
+{
+ return __builtin_lasx_xvfrecipe_d (_1);
+}
+v8f32
+__lasx_xvfrsqrte_s (v8f32 _1)
+{
+ return __builtin_lasx_xvfrsqrte_s (_1);
+}
+v4f64
+__lasx_xvfrsqrte_d (v4f64 _1)
+{
+ return __builtin_lasx_xvfrsqrte_d (_1);
+}
diff --git a/gcc/testsuite/gcc.target/loongarch/vector/lsx/lsx-frecipe-builtin.c b/gcc/testsuite/gcc.target/loongarch/vector/lsx/lsx-frecipe-builtin.c
new file mode 100644
index 00000000000..4ad0cb0ffd6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/vector/lsx/lsx-frecipe-builtin.c
@@ -0,0 +1,30 @@
+/* Test builtins for vfrecipe.{s/d} and vfrsqrte.{s/d} instructions */
+/* { dg-do compile } */
+/* { dg-options "-mlsx -mfrecipe" } */
+/* { dg-final { scan-assembler-times "lsx_vfrecipe_s:.*vfrecipe\\.s.*lsx_vfrecipe_s" 1 } } */
+/* { dg-final { scan-assembler-times "lsx_vfrecipe_d:.*vfrecipe\\.d.*lsx_vfrecipe_d" 1 } } */
+/* { dg-final { scan-assembler-times "lsx_vfrsqrte_s:.*vfrsqrte\\.s.*lsx_vfrsqrte_s" 1 } } */
+/* { dg-final { scan-assembler-times "lsx_vfrsqrte_d:.*vfrsqrte\\.d.*lsx_vfrsqrte_d" 1 } } */
+
+#include <lsxintrin.h>
+
+v4f32
+__lsx_vfrecipe_s (v4f32 _1)
+{
+ return __builtin_lsx_vfrecipe_s (_1);
+}
+v2f64
+__lsx_vfrecipe_d (v2f64 _1)
+{
+ return __builtin_lsx_vfrecipe_d (_1);
+}
+v4f32
+__lsx_vfrsqrte_s (v4f32 _1)
+{
+ return __builtin_lsx_vfrsqrte_s (_1);
+}
+v2f64
+__lsx_vfrsqrte_d (v2f64 _1)
+{
+ return __builtin_lsx_vfrsqrte_d (_1);
+}
--
2.20.1
next prev parent reply other threads:[~2023-12-05 7:02 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-05 7:01 [PATCH v2 0/5] Add support for approximate instructions and optimize divf/sqrtf/rsqrt operations Jiahao Xu
2023-12-05 7:01 ` Jiahao Xu [this message]
2023-12-05 7:01 ` [PATCH v2 2/5] LoongArch: Use standard pattern name for xvfrsqrt/vfrsqrt instructions Jiahao Xu
2023-12-05 7:01 ` [PATCH v2 3/5] LoongArch: Redefine pattern for xvfrecip/vfrecip instructions Jiahao Xu
2023-12-05 7:01 ` [PATCH v2 4/5] LoongArch: New options -mrecip and -mrecip= with ffast-math Jiahao Xu
2023-12-05 7:01 ` [PATCH v2 5/5] LoongArch: Vectorized loop unrolling is disable for divf/sqrtf/rsqrtf when -mrecip is enabled Jiahao Xu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231205070147.53352-2-xujiahao@loongson.cn \
--to=xujiahao@loongson.cn \
--cc=chenglulu@loongson.cn \
--cc=gcc-patches@gcc.gnu.org \
--cc=i@xen0n.name \
--cc=xry111@xry111.site \
--cc=xuchenghua@loongson.cn \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).