Re: [PATCH] AArch64: Add support for __builtin_roundeven[f] [PR100966]
Wilco Dijkstra writes: > Hi Richard, > >> So rather than have two patterns that generate frintn, I think >> it would be better to change the existing frint_pattern entry to >> "roundeven" instead, and fix whatever the fallout is. Hopefully it >> shouldn't be too bad, since we already use the optab names for the >> other UNSPEC_FRINT* codes. > > Well it requires various changes to the arm_neon headers since they use > existing intrinsics. If that is not considered a risky ABI change then here is > v2: > > Enable __builtin_roundeven[f] by changing existing frintn to roundeven. Yeah, changing the arm_neon.h->compiler interface is OK, since we only support using the version of arm_neon.h that ships with the compiler, not an older or newer version. There have already been quite a few changes like that since GCC 11 branched (to get better optimisation). > Bootstrap OK and passes regress. > > ChangeLog: > 2021-06-18 Wilco Dijkstra > > PR target/100966 > * config/aarch64/aarch64.md (frint_pattern): Update comment. > * config/aarch64/aarch64-simd-builtins.def: Change frintn to > roundeven. > * config/aarch64/arm_fp16.h: Change frintn to roundeven. > * config/aarch64/arm_neon.h: Likewise. > * config/aarch64/iterators.md (frint_pattern): Use roundeven for > FRINTN. > > gcc/testsuite > PR target/100966 > * gcc.target/aarch64/frint.x: Add roundeven tests. > * gcc.target/aarch64/frint_double.c: Likewise. > * gcc.target/aarch64/frint_float.c: Likewise. OK, thanks. Richard > > --- > > diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def > b/gcc/config/aarch64/ > aarch64-simd-builtins.def > index > b885bd5b38bf7ad83eb9d801284bf9b34db17210..534cc8ccb538c4fb0c208a7035020e131656260d > 100644 > --- a/gcc/config/aarch64/aarch64-simd-builtins.def > +++ b/gcc/config/aarch64/aarch64-simd-builtins.def > @@ -485,7 +485,7 @@ >BUILTIN_VHSDF (UNOP, nearbyint, 2, FP) >BUILTIN_VHSDF (UNOP, rint, 2, FP) >BUILTIN_VHSDF (UNOP, round, 2, FP) > - BUILTIN_VHSDF_HSDF (UNOP, frintn, 2, FP) > + BUILTIN_VHSDF_HSDF (UNOP, roundeven, 2, FP) > >VAR1 (UNOP, btrunc, 2, FP, hf) >VAR1 (UNOP, ceil, 2, FP, hf) > diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md > index > 30effca6f3562f6870a6cc8097750e63bb0d424d..8977330b142d2cde1d2faa4a01282b01a68e25c5 > 100644 > --- a/gcc/config/aarch64/aarch64.md > +++ b/gcc/config/aarch64/aarch64.md > @@ -5922,7 +5922,7 @@ (define_insn "*bswapsi2_uxtw" > ;; --- > > ;; frint floating-point round to integral standard patterns. > -;; Expands to btrunc, ceil, floor, nearbyint, rint, round, frintn. > +;; Expands to btrunc, ceil, floor, nearbyint, rint, round, roundeven. > > (define_insn "2" >[(set (match_operand:GPF_F16 0 "register_operand" "=w") > diff --git a/gcc/config/aarch64/arm_fp16.h b/gcc/config/aarch64/arm_fp16.h > index > 2afbd1203361b54d6e1315ffaa1bec21834c060e..3efa7e1f19817df1409bf781266f4e238c128f0b > 100644 > --- a/gcc/config/aarch64/arm_fp16.h > +++ b/gcc/config/aarch64/arm_fp16.h > @@ -333,7 +333,7 @@ vrndmh_f16 (float16_t __a) > __extension__ static __inline float16_t __attribute__ ((__always_inline__)) > vrndnh_f16 (float16_t __a) > { > - return __builtin_aarch64_frintnhf (__a); > + return __builtin_aarch64_roundevenhf (__a); > } > > __extension__ static __inline float16_t __attribute__ ((__always_inline__)) > diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h > index > baa30bd5a9d96c1bf04a37fb105091ea56a6444a..c88a8a627d3082d3577b0fe222381e93c35d7251 > 100644 > --- a/gcc/config/aarch64/arm_neon.h > +++ b/gcc/config/aarch64/arm_neon.h > @@ -24657,35 +24657,35 @@ __extension__ extern __inline float32_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > vrndns_f32 (float32_t __a) > { > - return __builtin_aarch64_frintnsf (__a); > + return __builtin_aarch64_roundevensf (__a); > } > > __extension__ extern __inline float32x2_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > vrndn_f32 (float32x2_t __a) > { > - return __builtin_aarch64_frintnv2sf (__a); > + return __builtin_aarch64_roundevenv2sf (__a); > } > > __extension__ extern __inline float64x1_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > vrndn_f64 (float64x1_t __a) > { > - return (float64x1_t) {__builtin_aarch64_frintndf (__a[0])}; > + return (float64x1_t) {__builtin_aarch64_roundevendf (__a[0])}; > } > > __extension__ extern __inline float32x4_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > vrndnq_f32 (float32x4_t __a) > { > - return __builtin_aarch64_frintnv4sf (__a); > + return __builtin_aarch64_roundevenv4sf (__a); > } > > __extension__ extern __inline float64x2_t > __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) > vrndnq_f64 (float64x2_t __a) > {
Re: [PATCH] AArch64: Add support for __builtin_roundeven[f] [PR100966]
Hi Richard, > So rather than have two patterns that generate frintn, I think > it would be better to change the existing frint_pattern entry to > "roundeven" instead, and fix whatever the fallout is. Hopefully it > shouldn't be too bad, since we already use the optab names for the > other UNSPEC_FRINT* codes. Well it requires various changes to the arm_neon headers since they use existing intrinsics. If that is not considered a risky ABI change then here is v2: Enable __builtin_roundeven[f] by changing existing frintn to roundeven. Bootstrap OK and passes regress. ChangeLog: 2021-06-18 Wilco Dijkstra PR target/100966 * config/aarch64/aarch64.md (frint_pattern): Update comment. * config/aarch64/aarch64-simd-builtins.def: Change frintn to roundeven. * config/aarch64/arm_fp16.h: Change frintn to roundeven. * config/aarch64/arm_neon.h: Likewise. * config/aarch64/iterators.md (frint_pattern): Use roundeven for FRINTN. gcc/testsuite PR target/100966 * gcc.target/aarch64/frint.x: Add roundeven tests. * gcc.target/aarch64/frint_double.c: Likewise. * gcc.target/aarch64/frint_float.c: Likewise. --- diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def index b885bd5b38bf7ad83eb9d801284bf9b34db17210..534cc8ccb538c4fb0c208a7035020e131656260d 100644 --- a/gcc/config/aarch64/aarch64-simd-builtins.def +++ b/gcc/config/aarch64/aarch64-simd-builtins.def @@ -485,7 +485,7 @@ BUILTIN_VHSDF (UNOP, nearbyint, 2, FP) BUILTIN_VHSDF (UNOP, rint, 2, FP) BUILTIN_VHSDF (UNOP, round, 2, FP) - BUILTIN_VHSDF_HSDF (UNOP, frintn, 2, FP) + BUILTIN_VHSDF_HSDF (UNOP, roundeven, 2, FP) VAR1 (UNOP, btrunc, 2, FP, hf) VAR1 (UNOP, ceil, 2, FP, hf) diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md index 30effca6f3562f6870a6cc8097750e63bb0d424d..8977330b142d2cde1d2faa4a01282b01a68e25c5 100644 --- a/gcc/config/aarch64/aarch64.md +++ b/gcc/config/aarch64/aarch64.md @@ -5922,7 +5922,7 @@ (define_insn "*bswapsi2_uxtw" ;; --- ;; frint floating-point round to integral standard patterns. -;; Expands to btrunc, ceil, floor, nearbyint, rint, round, frintn. +;; Expands to btrunc, ceil, floor, nearbyint, rint, round, roundeven. (define_insn "2" [(set (match_operand:GPF_F16 0 "register_operand" "=w") diff --git a/gcc/config/aarch64/arm_fp16.h b/gcc/config/aarch64/arm_fp16.h index 2afbd1203361b54d6e1315ffaa1bec21834c060e..3efa7e1f19817df1409bf781266f4e238c128f0b 100644 --- a/gcc/config/aarch64/arm_fp16.h +++ b/gcc/config/aarch64/arm_fp16.h @@ -333,7 +333,7 @@ vrndmh_f16 (float16_t __a) __extension__ static __inline float16_t __attribute__ ((__always_inline__)) vrndnh_f16 (float16_t __a) { - return __builtin_aarch64_frintnhf (__a); + return __builtin_aarch64_roundevenhf (__a); } __extension__ static __inline float16_t __attribute__ ((__always_inline__)) diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h index baa30bd5a9d96c1bf04a37fb105091ea56a6444a..c88a8a627d3082d3577b0fe222381e93c35d7251 100644 --- a/gcc/config/aarch64/arm_neon.h +++ b/gcc/config/aarch64/arm_neon.h @@ -24657,35 +24657,35 @@ __extension__ extern __inline float32_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndns_f32 (float32_t __a) { - return __builtin_aarch64_frintnsf (__a); + return __builtin_aarch64_roundevensf (__a); } __extension__ extern __inline float32x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndn_f32 (float32x2_t __a) { - return __builtin_aarch64_frintnv2sf (__a); + return __builtin_aarch64_roundevenv2sf (__a); } __extension__ extern __inline float64x1_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndn_f64 (float64x1_t __a) { - return (float64x1_t) {__builtin_aarch64_frintndf (__a[0])}; + return (float64x1_t) {__builtin_aarch64_roundevendf (__a[0])}; } __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndnq_f32 (float32x4_t __a) { - return __builtin_aarch64_frintnv4sf (__a); + return __builtin_aarch64_roundevenv4sf (__a); } __extension__ extern __inline float64x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndnq_f64 (float64x2_t __a) { - return __builtin_aarch64_frintnv2df (__a); + return __builtin_aarch64_roundevenv2df (__a); } /* vrndp */ @@ -31287,14 +31287,14 @@ __extension__ extern __inline float16x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndn_f16 (float16x4_t __a) { - return __builtin_aarch64_frintnv4hf (__a); + return __builtin_aarch64_roundevenv4hf (__a); } __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vrndnq_f16 (float16x8_t __a) { - return __builtin_aarch64_frintnv8
Re: [PATCH] AArch64: Add support for __builtin_roundeven[f] [PR100966]
Wilco Dijkstra writes: > Enable __builtin_roundeven[f] by adding roundeven as an alias to the > existing frintn support. Although frint_pattern maps UNSPEC_FRINTN to "frintn", "frintn" doesn't mean anything to the target-independent part of the compiler. I assume it was just picked as a placeholder since the roundeven optabs didn't exist at the time. So rather than have two patterns that generate frintn, I think it would be better to change the existing frint_pattern entry to "roundeven" instead, and fix whatever the fallout is. Hopefully it shouldn't be too bad, since we already use the optab names for the other UNSPEC_FRINT* codes. Thanks, Richard > Bootstrap OK and passes regress. > > ChangeLog: > 2021-06-18 Wilco Dijkstra > > PR target/100966 > * config/aarch64/aarch64.md (UNSPEC_FRINTR): Add. > * config/aarch64/aarch64.c (aarch64_frint_unspec_p): Add > UNSPEC_FRINTR. > (aarch64_rtx_cost): Likewise. > * config/aarch64/iterators.md (FRINT): Add UNSPEC_FRINTR. > (frint_pattern): Likewise. > (frint_suffix): Likewise. > > gcc/testsuite > PR target/100966 > * gcc.target/aarch64/frint.x: Add roundeven tests. > * gcc.target/aarch64/frint_double.c: Likewise. > * gcc.target/aarch64/frint_float.c: Likewise. > > --- > > diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c > index > f4d264bbc817153b330bac9ab423bf561689ebf2..63bd49d475433c04faa89bb380a9d17e4ad4bc6c > 100644 > --- a/gcc/config/aarch64/aarch64.c > +++ b/gcc/config/aarch64/aarch64.c > @@ -12253,6 +12253,7 @@ aarch64_frint_unspec_p (unsigned int u) >case UNSPEC_FRINTM: >case UNSPEC_FRINTA: >case UNSPEC_FRINTN: > + case UNSPEC_FRINTR: >case UNSPEC_FRINTX: >case UNSPEC_FRINTI: > return true; > @@ -13648,6 +13649,7 @@ cost_plus: >|| uns_code == UNSPEC_FRINTM >|| uns_code == UNSPEC_FRINTN >|| uns_code == UNSPEC_FRINTP > + || uns_code == UNSPEC_FRINTR >|| uns_code == UNSPEC_FRINTZ) > x = XVECEXP (x, 0, 0); > } > diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md > index > 30effca6f3562f6870a6cc8097750e63bb0d424d..70e46f28259640a273d444a2b963246ed9a91109 > 100644 > --- a/gcc/config/aarch64/aarch64.md > +++ b/gcc/config/aarch64/aarch64.md > @@ -167,6 +167,7 @@ (define_c_enum "unspec" [ > UNSPEC_FRINTM > UNSPEC_FRINTN > UNSPEC_FRINTP > +UNSPEC_FRINTR > UNSPEC_FRINTX > UNSPEC_FRINTZ > UNSPEC_GOTSMALLPIC > diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md > index > cac33ae812b382cd55611b0da8a6e9eac3a513c4..1542661c6d101ed53c6e1c8683cbca32baefebbd > 100644 > --- a/gcc/config/aarch64/iterators.md > +++ b/gcc/config/aarch64/iterators.md > @@ -2291,7 +2291,7 @@ (define_int_iterator REVERSE [UNSPEC_REV64 UNSPEC_REV32 > UNSPEC_REV16]) > > (define_int_iterator FRINT [UNSPEC_FRINTZ UNSPEC_FRINTP UNSPEC_FRINTM > UNSPEC_FRINTN UNSPEC_FRINTI UNSPEC_FRINTX > -UNSPEC_FRINTA]) > +UNSPEC_FRINTA UNSPEC_FRINTR ]) > > (define_int_iterator FCVT [UNSPEC_FRINTZ UNSPEC_FRINTP UNSPEC_FRINTM > UNSPEC_FRINTA UNSPEC_FRINTN]) > @@ -3079,13 +3079,14 @@ (define_int_attr frint_pattern [(UNSPEC_FRINTZ > "btrunc") > (UNSPEC_FRINTI "nearbyint") > (UNSPEC_FRINTX "rint") > (UNSPEC_FRINTA "round") > - (UNSPEC_FRINTN "frintn")]) > + (UNSPEC_FRINTN "frintn") > + (UNSPEC_FRINTR "roundeven")]) > > ;; frint suffix for floating-point rounding instructions. > (define_int_attr frint_suffix [(UNSPEC_FRINTZ "z") (UNSPEC_FRINTP "p") >(UNSPEC_FRINTM "m") (UNSPEC_FRINTI "i") >(UNSPEC_FRINTX "x") (UNSPEC_FRINTA "a") > - (UNSPEC_FRINTN "n")]) > + (UNSPEC_FRINTN "n") (UNSPEC_FRINTR "n")]) > > (define_int_attr fcvt_pattern [(UNSPEC_FRINTZ "btrunc") (UNSPEC_FRINTA > "round") >(UNSPEC_FRINTP "ceil") (UNSPEC_FRINTM "floor") > diff --git a/gcc/testsuite/gcc.target/aarch64/frint.x > b/gcc/testsuite/gcc.target/aarch64/frint.x > index > 1403740686ea3927d2c39eb2466ef8cc67e223b2..d598a25ff21b8feeca6a96de79848b2fbde7f31e > 100644 > --- a/gcc/testsuite/gcc.target/aarch64/frint.x > +++ b/gcc/testsuite/gcc.target/aarch64/frint.x > @@ -4,6 +4,7 @@ extern GPF SUFFIX(floor) (GPF); > extern GPF SUFFIX(nearbyint) (GPF); > extern GPF SUFFIX(rint) (GPF); > extern GPF SUFFIX(round) (GPF); > +extern GPF SUFFIX(roundeven) (GPF); > > GPF test1a (GPF x) > { > @@ -64,3 +65,14 @@ GPF test6b (GPF x) > { >return SUFFIX(ro
[PATCH] AArch64: Add support for __builtin_roundeven[f] [PR100966]
Enable __builtin_roundeven[f] by adding roundeven as an alias to the existing frintn support. Bootstrap OK and passes regress. ChangeLog: 2021-06-18 Wilco Dijkstra PR target/100966 * config/aarch64/aarch64.md (UNSPEC_FRINTR): Add. * config/aarch64/aarch64.c (aarch64_frint_unspec_p): Add UNSPEC_FRINTR. (aarch64_rtx_cost): Likewise. * config/aarch64/iterators.md (FRINT): Add UNSPEC_FRINTR. (frint_pattern): Likewise. (frint_suffix): Likewise. gcc/testsuite PR target/100966 * gcc.target/aarch64/frint.x: Add roundeven tests. * gcc.target/aarch64/frint_double.c: Likewise. * gcc.target/aarch64/frint_float.c: Likewise. --- diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c index f4d264bbc817153b330bac9ab423bf561689ebf2..63bd49d475433c04faa89bb380a9d17e4ad4bc6c 100644 --- a/gcc/config/aarch64/aarch64.c +++ b/gcc/config/aarch64/aarch64.c @@ -12253,6 +12253,7 @@ aarch64_frint_unspec_p (unsigned int u) case UNSPEC_FRINTM: case UNSPEC_FRINTA: case UNSPEC_FRINTN: + case UNSPEC_FRINTR: case UNSPEC_FRINTX: case UNSPEC_FRINTI: return true; @@ -13648,6 +13649,7 @@ cost_plus: || uns_code == UNSPEC_FRINTM || uns_code == UNSPEC_FRINTN || uns_code == UNSPEC_FRINTP + || uns_code == UNSPEC_FRINTR || uns_code == UNSPEC_FRINTZ) x = XVECEXP (x, 0, 0); } diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md index 30effca6f3562f6870a6cc8097750e63bb0d424d..70e46f28259640a273d444a2b963246ed9a91109 100644 --- a/gcc/config/aarch64/aarch64.md +++ b/gcc/config/aarch64/aarch64.md @@ -167,6 +167,7 @@ (define_c_enum "unspec" [ UNSPEC_FRINTM UNSPEC_FRINTN UNSPEC_FRINTP +UNSPEC_FRINTR UNSPEC_FRINTX UNSPEC_FRINTZ UNSPEC_GOTSMALLPIC diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md index cac33ae812b382cd55611b0da8a6e9eac3a513c4..1542661c6d101ed53c6e1c8683cbca32baefebbd 100644 --- a/gcc/config/aarch64/iterators.md +++ b/gcc/config/aarch64/iterators.md @@ -2291,7 +2291,7 @@ (define_int_iterator REVERSE [UNSPEC_REV64 UNSPEC_REV32 UNSPEC_REV16]) (define_int_iterator FRINT [UNSPEC_FRINTZ UNSPEC_FRINTP UNSPEC_FRINTM UNSPEC_FRINTN UNSPEC_FRINTI UNSPEC_FRINTX -UNSPEC_FRINTA]) +UNSPEC_FRINTA UNSPEC_FRINTR ]) (define_int_iterator FCVT [UNSPEC_FRINTZ UNSPEC_FRINTP UNSPEC_FRINTM UNSPEC_FRINTA UNSPEC_FRINTN]) @@ -3079,13 +3079,14 @@ (define_int_attr frint_pattern [(UNSPEC_FRINTZ "btrunc") (UNSPEC_FRINTI "nearbyint") (UNSPEC_FRINTX "rint") (UNSPEC_FRINTA "round") - (UNSPEC_FRINTN "frintn")]) + (UNSPEC_FRINTN "frintn") + (UNSPEC_FRINTR "roundeven")]) ;; frint suffix for floating-point rounding instructions. (define_int_attr frint_suffix [(UNSPEC_FRINTZ "z") (UNSPEC_FRINTP "p") (UNSPEC_FRINTM "m") (UNSPEC_FRINTI "i") (UNSPEC_FRINTX "x") (UNSPEC_FRINTA "a") - (UNSPEC_FRINTN "n")]) + (UNSPEC_FRINTN "n") (UNSPEC_FRINTR "n")]) (define_int_attr fcvt_pattern [(UNSPEC_FRINTZ "btrunc") (UNSPEC_FRINTA "round") (UNSPEC_FRINTP "ceil") (UNSPEC_FRINTM "floor") diff --git a/gcc/testsuite/gcc.target/aarch64/frint.x b/gcc/testsuite/gcc.target/aarch64/frint.x index 1403740686ea3927d2c39eb2466ef8cc67e223b2..d598a25ff21b8feeca6a96de79848b2fbde7f31e 100644 --- a/gcc/testsuite/gcc.target/aarch64/frint.x +++ b/gcc/testsuite/gcc.target/aarch64/frint.x @@ -4,6 +4,7 @@ extern GPF SUFFIX(floor) (GPF); extern GPF SUFFIX(nearbyint) (GPF); extern GPF SUFFIX(rint) (GPF); extern GPF SUFFIX(round) (GPF); +extern GPF SUFFIX(roundeven) (GPF); GPF test1a (GPF x) { @@ -64,3 +65,14 @@ GPF test6b (GPF x) { return SUFFIX(round)(x); } + +GPF test7a (GPF x) +{ + return SUFFIX(__builtin_roundeven)(x); +} + +GPF test7b (GPF x) +{ + return SUFFIX(roundeven)(x); +} + diff --git a/gcc/testsuite/gcc.target/aarch64/frint_double.c b/gcc/testsuite/gcc.target/aarch64/frint_double.c index 96139496ca454cebd41d31e8b018dab7ffa33a3f..1d28eb09e11842802ab632a7696de4407263f8ce 100644 --- a/gcc/testsuite/gcc.target/aarch64/frint_double.c +++ b/gcc/testsuite/gcc.target/aarch64/frint_double.c @@ -12,3 +12,4 @@ /* { dg-final { scan-assembler-times "frinti\td\[0-9\]" 2 } } */ /* { dg-final { scan-assembler-times "frintx\td\[0-9\]" 2 } } */ /* { dg-final { scan-assembler-times "frinta\td\[0-9\]" 2 } } */ +/* { dg-final { scan-assembler-times "frintn\td\[0-9\]" 2 } } */ diff --git a/gcc/testsuite/gc