Re: [Aarch64] Use vector wide add for mixed-mode adds
This is a followup patch which addresses formatting comments posted here: https://gcc.gnu.org/ml/gcc-patches/2015-11/msg02611.html 2015-11-24 Michael Collison* config/aarch64/aarch64-simd.md (widen_ssum, widen_usum) (aarch64_w_internal): New patterns * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. * gcc.target/aarch64/saddw-1.c: New test. * gcc.target/aarch64/saddw-2.c: New test. * gcc.target/aarch64/uaddw-1.c: New test. * gcc.target/aarch64/uaddw-2.c: New test. * gcc.target/aarch64/uaddw-3.c: New test. * lib/target-support.exp (check_effective_target_vect_widen_sum_hi_to_si_pattern): Add aarch64 to list of support targets. Okay to commit? -- Michael Collison Linaro Toolchain Working Group michael.colli...@linaro.org diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index 3fa23b3..79be6be 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -2777,6 +2777,62 @@ ;; w. +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (sign_extend: + (match_operand:VQW 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_saddw_internal (temp, operands[2], + operands[1], p)); +emit_insn (gen_aarch64_saddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (sign_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_saddw (operands[0], operands[2], operands[1])); + DONE; +}) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (zero_extend: + (match_operand:VQW 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_uaddw_internal (temp, operands[2], + operands[1], p)); +emit_insn (gen_aarch64_uaddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (zero_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_uaddw (operands[0], operands[2], operands[1])); + DONE; +}) + (define_insn "aarch64_w" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") @@ -2787,6 +2843,18 @@ [(set_attr "type" "neon__widen")] ) +(define_insn "aarch64_w_internal" + [(set (match_operand: 0 "register_operand" "=w") +(ADDSUB: (match_operand: 1 "register_operand" "w") + (ANY_EXTEND: + (vec_select: + (match_operand:VQW 2 "register_operand" "w") + (match_operand:VQW 3 "vect_par_cnst_lo_half" "")] + "TARGET_SIMD" + "w\\t%0., %1., %2." + [(set_attr "type" "neon__widen")] +) + (define_insn "aarch64_w2_internal" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md index c2eb7de..02e930b 100644 --- a/gcc/config/aarch64/iterators.md +++ b/gcc/config/aarch64/iterators.md @@ -479,6 +479,13 @@ (V4SF "V2SF") (V4HF "V2HF") (V8HF "V4HF") (V2DF "DF")]) +;; Half modes of all vector modes, in lower-case. +(define_mode_attr Vhalf [(V8QI "v4qi") (V16QI "v8qi") + (V4HI "v2hi") (V8HI "v4hi") + (V2SI "si")(V4SI "v2si") + (V2DI "di")(V2SF "sf") + (V4SF "v2sf") (V2DF "df")]) + ;; Double modes of vector modes. (define_mode_attr VDBL [(V8QI "V16QI") (V4HI "V8HI") (V4HF "V8HF") @@ -496,6 +503,11 @@ (SI "v2si") (DI "v2di") (DF "v2df")]) +;; Modes with double-width elements. +(define_mode_attr VDBLW [(V8QI "V4HI") (V16QI "V8HI") + (V4HI "V2SI") (V8HI "V4SI") + (V2SI "DI") (V4SI "V2DI")]) + ;; Narrowed modes for VDN. (define_mode_attr VNARROWD [(V4HI "V8QI") (V2SI "V4HI") (DI "V2SI")]) diff --git a/gcc/testsuite/gcc.target/aarch64/saddw-1.c b/gcc/testsuite/gcc.target/aarch64/saddw-1.c new file mode 100644 index 000..7500fb8 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/saddw-1.c @@ -0,0 +1,16 @@ +/* { dg-do compile } */ +/* { dg-options "-O3" } */ + +int +t6(int len, void * dummy, short * __restrict x) +{ + len = len & ~31; + int result = 0; + __asm volatile (""); + for (int i = 0; i < len; i++) +result += x[i]; + return result; +} + +/* { dg-final {
Re: [Aarch64] Use vector wide add for mixed-mode adds
On Tue, Nov 24, 2015 at 02:24:30AM -0700, Michael Collison wrote: > This is a followup patch which addresses formatting comments posted here: > > https://gcc.gnu.org/ml/gcc-patches/2015-11/msg02611.html > > 2015-11-24 Michael Collison> * config/aarch64/aarch64-simd.md (widen_ssum, widen_usum) > (aarch64_w_internal): New patterns > * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. > * gcc.target/aarch64/saddw-1.c: New test. > * gcc.target/aarch64/saddw-2.c: New test. > * gcc.target/aarch64/uaddw-1.c: New test. > * gcc.target/aarch64/uaddw-2.c: New test. > * gcc.target/aarch64/uaddw-3.c: New test. > * lib/target-support.exp > (check_effective_target_vect_widen_sum_hi_to_si_pattern): > Add aarch64 to list of support targets. > > Okay to commit? OK. Thanks, James
Re: [Aarch64] Use vector wide add for mixed-mode adds
On Sun, Nov 22, 2015 at 06:24:19PM -0700, Michael Collison wrote: > > > On 11/22/2015 8:48 AM, James Greenhalgh wrote: > >On Sun, Nov 08, 2015 at 11:51:47PM -0700, Michael Collison wrote: > >>2015-11-06 Michael Collison> >> * config/aarch64/aarch64-simd.md (widen_ssum, widen_usum) > >>(aarch64_w_internal): New patterns > >> * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. > >> * gcc.target/aarch64/saddw-1.c: New test. > >> * gcc.target/aarch64/saddw-2.c: New test. > >> * gcc.target/aarch64/uaddw-1.c: New test. > >> * gcc.target/aarch64/uaddw-2.c: New test. > >> * gcc.target/aarch64/uaddw-3.c: New test. > >> * lib/target-support.exp > >> (check_effective_target_vect_widen_sum_hi_to_si_pattern): > >> Add aarch64 to list of support targets. > > > >These hunks are all OK (with the minor style comments below applied). > > Okay I will update with your comments. > > > >As we understand what's happening here, let's take the regressions below > >for now and add AArch64 to the targets affected by pr68333. > > > >> * gcc.dg/vect/slp-multitypes-4.c: Disable test for > >> targets with widening adds from V8HI=>V4SI. > >> * gcc.dg/vect/slp-multitypes-5.c: Ditto. > >> * gcc.dg/vect/vect-125.c: Ditto. > >Let's leave these for now, while we wait for pr68333. > > To clarify you would like me to exclude these bits from the patch? Yes, given the direction that pr68333 is going (a bug that should be fixed, rather than an expected failure) that seems best to me. Thanks, James
Re: [Aarch64] Use vector wide add for mixed-mode adds
On 11/22/2015 8:48 AM, James Greenhalgh wrote: On Sun, Nov 08, 2015 at 11:51:47PM -0700, Michael Collison wrote: 2015-11-06 Michael Collison* config/aarch64/aarch64-simd.md (widen_ssum, widen_usum) (aarch64_w_internal): New patterns * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. * gcc.target/aarch64/saddw-1.c: New test. * gcc.target/aarch64/saddw-2.c: New test. * gcc.target/aarch64/uaddw-1.c: New test. * gcc.target/aarch64/uaddw-2.c: New test. * gcc.target/aarch64/uaddw-3.c: New test. * lib/target-support.exp (check_effective_target_vect_widen_sum_hi_to_si_pattern): Add aarch64 to list of support targets. These hunks are all OK (with the minor style comments below applied). Okay I will update with your comments. As we understand what's happening here, let's take the regressions below for now and add AArch64 to the targets affected by pr68333. * gcc.dg/vect/slp-multitypes-4.c: Disable test for targets with widening adds from V8HI=>V4SI. * gcc.dg/vect/slp-multitypes-5.c: Ditto. * gcc.dg/vect/vect-125.c: Ditto. Let's leave these for now, while we wait for pr68333. To clarify you would like me to exclude these bits from the patch? diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index 65a2b6f..acb7cf0 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -2750,6 +2750,60 @@ ;; w. +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (sign_extend: (match_operand:VQW 1 "register_operand" "")) Split this line (more than 80 characters). + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_saddw_internal (temp, operands[2], + operands[1], p)); +emit_insn (gen_aarch64_saddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (sign_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_saddw (operands[0], operands[2], operands[1])); + DONE; +}) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (zero_extend: (match_operand:VQW 1 "register_operand" "")) Split this line (more than 80 characters). + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_uaddw_internal (temp, operands[2], +operands[1], p)); +emit_insn (gen_aarch64_uaddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (zero_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_uaddw (operands[0], operands[2], operands[1])); + DONE; +}) + (define_insn "aarch64_w" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") @@ -2760,6 +2814,18 @@ [(set_attr "type" "neon__widen")] ) +(define_insn "aarch64_w_internal" + [(set (match_operand: 0 "register_operand" "=w") +(ADDSUB: (match_operand: 1 "register_operand" "w") + (ANY_EXTEND: + (vec_select: + (match_operand:VQW 2 "register_operand" "w") + (match_operand:VQW 3 "vect_par_cnst_lo_half" "")] + "TARGET_SIMD" + "w\\t%0., %1., %2." + [(set_attr "type" "neon__widen")] +) + (define_insn "aarch64_w2_internal" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") diff --git a/gcc/testsuite/gcc.target/aarch64/saddw-1.c b/gcc/testsuite/gcc.target/aarch64/saddw-1.c new file mode 100644 index 000..9db5d00 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/saddw-1.c @@ -0,0 +1,20 @@ +/* { dg-do compile } */ +/* { dg-options "-O3" } */ + + Extra newline. +int +t6(int len, void * dummy, short * __restrict x) +{ + len = len & ~31; + int result = 0; + __asm volatile (""); + for (int i = 0; i < len; i++) +result += x[i]; + return result; +} + +/* { dg-final { scan-assembler "saddw" } } */ +/* { dg-final { scan-assembler "saddw2" } } */ + + + Trailing newlines. diff --git a/gcc/testsuite/gcc.target/aarch64/saddw-2.c
Re: [Aarch64] Use vector wide add for mixed-mode adds
On Sun, Nov 08, 2015 at 11:51:47PM -0700, Michael Collison wrote: > 2015-11-06 Michael Collison> * config/aarch64/aarch64-simd.md (widen_ssum, widen_usum) > (aarch64_w_internal): New patterns > * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. > * gcc.target/aarch64/saddw-1.c: New test. > * gcc.target/aarch64/saddw-2.c: New test. > * gcc.target/aarch64/uaddw-1.c: New test. > * gcc.target/aarch64/uaddw-2.c: New test. > * gcc.target/aarch64/uaddw-3.c: New test. > * lib/target-support.exp > (check_effective_target_vect_widen_sum_hi_to_si_pattern): > Add aarch64 to list of support targets. These hunks are all OK (with the minor style comments below applied). As we understand what's happening here, let's take the regressions below for now and add AArch64 to the targets affected by pr68333. > * gcc.dg/vect/slp-multitypes-4.c: Disable test for > targets with widening adds from V8HI=>V4SI. > * gcc.dg/vect/slp-multitypes-5.c: Ditto. > * gcc.dg/vect/vect-125.c: Ditto. Let's leave these for now, while we wait for pr68333. > diff --git a/gcc/config/aarch64/aarch64-simd.md > b/gcc/config/aarch64/aarch64-simd.md > index 65a2b6f..acb7cf0 100644 > --- a/gcc/config/aarch64/aarch64-simd.md > +++ b/gcc/config/aarch64/aarch64-simd.md > @@ -2750,6 +2750,60 @@ > > ;; w. > > +(define_expand "widen_ssum3" > + [(set (match_operand: 0 "register_operand" "") > + (plus: (sign_extend: (match_operand:VQW 1 > "register_operand" "")) Split this line (more than 80 characters). > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > + { > +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); > +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); > + > +emit_insn (gen_aarch64_saddw_internal (temp, operands[2], > + operands[1], p)); > +emit_insn (gen_aarch64_saddw2 (operands[0], temp, operands[1])); > +DONE; > + } > +) > + > +(define_expand "widen_ssum3" > + [(set (match_operand: 0 "register_operand" "") > + (plus: (sign_extend: > +(match_operand:VD_BHSI 1 "register_operand" "")) > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > +{ > + emit_insn (gen_aarch64_saddw (operands[0], operands[2], > operands[1])); > + DONE; > +}) > + > +(define_expand "widen_usum3" > + [(set (match_operand: 0 "register_operand" "") > + (plus: (zero_extend: (match_operand:VQW 1 > "register_operand" "")) Split this line (more than 80 characters). > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > + { > +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); > +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); > + > +emit_insn (gen_aarch64_uaddw_internal (temp, operands[2], > + operands[1], p)); > +emit_insn (gen_aarch64_uaddw2 (operands[0], temp, operands[1])); > +DONE; > + } > +) > + > +(define_expand "widen_usum3" > + [(set (match_operand: 0 "register_operand" "") > + (plus: (zero_extend: > +(match_operand:VD_BHSI 1 "register_operand" "")) > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > +{ > + emit_insn (gen_aarch64_uaddw (operands[0], operands[2], > operands[1])); > + DONE; > +}) > + > (define_insn "aarch64_w" >[(set (match_operand: 0 "register_operand" "=w") > (ADDSUB: (match_operand: 1 "register_operand" "w") > @@ -2760,6 +2814,18 @@ >[(set_attr "type" "neon__widen")] > ) > > +(define_insn "aarch64_w_internal" > + [(set (match_operand: 0 "register_operand" "=w") > +(ADDSUB: (match_operand: 1 "register_operand" "w") > + (ANY_EXTEND: > + (vec_select: > +(match_operand:VQW 2 "register_operand" "w") > +(match_operand:VQW 3 "vect_par_cnst_lo_half" "")] > + "TARGET_SIMD" > + "w\\t%0., %1., %2." > + [(set_attr "type" "neon__widen")] > +) > + > (define_insn "aarch64_w2_internal" >[(set (match_operand: 0 "register_operand" "=w") > (ADDSUB: (match_operand: 1 "register_operand" "w") > diff --git a/gcc/testsuite/gcc.target/aarch64/saddw-1.c > b/gcc/testsuite/gcc.target/aarch64/saddw-1.c > new file mode 100644 > index 000..9db5d00 > --- /dev/null > +++ b/gcc/testsuite/gcc.target/aarch64/saddw-1.c > @@ -0,0 +1,20 @@ > +/* { dg-do compile } */ > +/* { dg-options "-O3" } */ > + > + Extra newline. > +int > +t6(int len, void * dummy, short * __restrict x) > +{ > + len = len & ~31; > + int result = 0; > + __asm volatile (""); > + for (int i = 0; i < len; i++) > +result += x[i]; > + return result; > +} > + > +/* { dg-final { scan-assembler "saddw" } } */ > +/* { dg-final { scan-assembler "saddw2" } } */ > + > + > + Trailing newlines. > diff --git
Re: [Aarch64] Use vector wide add for mixed-mode adds
This is a followup patch to my earlier patch here: https://gcc.gnu.org/ml/gcc-patches/2015-09/msg00408.html and comments here: https://gcc.gnu.org/ml/gcc-patches/2015-09/msg01300.html This patches fixes the failure in slp-reduc-3.c by adding aarch64 support in check_effective_target_vect_widen_sum_hi_to_si_pattern in target-supports.exp. The remaining failures in slp-multitypes-[45].c and vect-125.c appear to be deficiencies in the vectorizer, as the same failures are seen on PowerPC and ia64. See here: PowerPC: https://gcc.gnu.org/ml/gcc-testresults/2015-10/msg03293.html ia64: https://gcc.gnu.org/ml/gcc-testresults/2015-10/msg03176.html Thanks to James Greenhalgh at Arm for pointing this out. My patch disables these tests for targets with widening adds that support V8HI to V4SI. Tested on aarch64-none-elf, aarch64_be-none-elf, and aarch64-none-linus-gnu. 2015-11-06 Michael Collison* config/aarch64/aarch64-simd.md (widen_ssum, widen_usum) (aarch64_w_internal): New patterns * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. * gcc.target/aarch64/saddw-1.c: New test. * gcc.target/aarch64/saddw-2.c: New test. * gcc.target/aarch64/uaddw-1.c: New test. * gcc.target/aarch64/uaddw-2.c: New test. * gcc.target/aarch64/uaddw-3.c: New test. * gcc.dg/vect/slp-multitypes-4.c: Disable test for targets with widening adds from V8HI=>V4SI. * gcc.dg/vect/slp-multitypes-5.c: Ditto. * gcc.dg/vect/vect-125.c: Ditto. * lib/target-support.exp (check_effective_target_vect_widen_sum_hi_to_si_pattern): Add aarch64 to list of support targets. Okay to commit? -- Michael Collison Linaro Toolchain Working Group michael.colli...@linaro.org diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index 65a2b6f..acb7cf0 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -2750,6 +2750,60 @@ ;; w. +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (sign_extend: (match_operand:VQW 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_saddw_internal (temp, operands[2], + operands[1], p)); +emit_insn (gen_aarch64_saddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (sign_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_saddw (operands[0], operands[2], operands[1])); + DONE; +}) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (zero_extend: (match_operand:VQW 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_uaddw_internal (temp, operands[2], + operands[1], p)); +emit_insn (gen_aarch64_uaddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") + (plus: (zero_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_uaddw (operands[0], operands[2], operands[1])); + DONE; +}) + (define_insn "aarch64_w" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") @@ -2760,6 +2814,18 @@ [(set_attr "type" "neon__widen")] ) +(define_insn "aarch64_w_internal" + [(set (match_operand: 0 "register_operand" "=w") +(ADDSUB: (match_operand: 1 "register_operand" "w") + (ANY_EXTEND: + (vec_select: + (match_operand:VQW 2 "register_operand" "w") + (match_operand:VQW 3 "vect_par_cnst_lo_half" "")] + "TARGET_SIMD" + "w\\t%0., %1., %2." + [(set_attr "type" "neon__widen")] +) + (define_insn "aarch64_w2_internal" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md index 964f8f1..f851dca 100644 --- a/gcc/config/aarch64/iterators.md +++ b/gcc/config/aarch64/iterators.md @@ -455,6 +455,13 @@ (V4SF "V2SF") (V4HF "V2HF") (V8HF "V4HF") (V2DF "DF")]) +;; Half modes of all vector modes, in lower-case. +(define_mode_attr Vhalf [(V8QI "v4qi") (V16QI "v8qi") + (V4HI "v2hi") (V8HI "v4hi") + (V2SI "si")(V4SI "v2si") + (V2DI "di")(V2SF "sf") + (V4SF "v2sf") (V2DF "df")]) + ;; Double modes of vector modes. (define_mode_attr VDBL [(V8QI
Re: [Aarch64] Use vector wide add for mixed-mode adds
On Mon, Sep 07, 2015 at 06:54:30AM +0100, Michael Collison wrote: > This patch is designed to address code that was not being vectorized due > to missing widening patterns in the aarch64 backend. Code such as: > > int t6(int len, void * dummy, short * __restrict x) > { >len = len & ~31; >int result = 0; >__asm volatile (""); >for (int i = 0; i < len; i++) > result += x[i]; >return result; > } > > Validated on aarch64-none-elf, aarch64_be-none-elf, and > aarch64-none-linus-gnu. > > Note that there are three non-execution tree dump vectorization > regressions where previously code was being vectorized. They are: I'd like to understand these better before taking the patch... > > Passed now fails [PASS => FAIL]: >gcc.dg/vect/slp-multitypes-4.c -flto -ffat-lto-objects > scan-tree-dump-times vect "vectorized 1 loops" 1 >gcc.dg/vect/slp-multitypes-4.c -flto -ffat-lto-objects > scan-tree-dump-times vect "vectorizing stmts using SLP" 1 >gcc.dg/vect/slp-multitypes-4.c scan-tree-dump-times vect "vectorized 1 > loops" 1 >gcc.dg/vect/slp-multitypes-4.c scan-tree-dump-times vect "vectorizing > stmts using SLP" 1 >gcc.dg/vect/slp-multitypes-5.c -flto -ffat-lto-objects > scan-tree-dump-times vect "vectorized 1 loops" 1 >gcc.dg/vect/slp-multitypes-5.c -flto -ffat-lto-objects > scan-tree-dump-times vect "vectorizing stmts using SLP" 1 >gcc.dg/vect/slp-multitypes-5.c scan-tree-dump-times vect "vectorized 1 > loops" 1 >gcc.dg/vect/slp-multitypes-5.c scan-tree-dump-times vect "vectorizing > stmts using SLP" 1 These look like weaknesses in SLP trying to build a widening add by a constant in the wider mode (i.e. (short) w+ (int)). I'd like to understand what the issue is here. >gcc.dg/vect/slp-reduc-3.c -flto -ffat-lto-objects scan-tree-dump-times > vect "vectorizing stmts using SLP" 1 >gcc.dg/vect/slp-reduc-3.c scan-tree-dump-times vect "vectorizing stmts > using SLP" 1 Is this one as simple as setting check_effective_target_vect_widen_sum_hi_to_si_pattern in testsuite/lib/target-supports.exp ? >gcc.dg/vect/vect-125.c -flto -ffat-lto-objects scan-tree-dump vect > "vectorized 1 loops" >gcc.dg/vect/vect-125.c scan-tree-dump vect "vectorized 1 loops" These look like a failure to match the widening optab for operand types (int) w+ (short) -> (int), so I'm also concerned here. > I would like to treat these as saperate bugs and resolve them separately. I think we shouldn't write these off without at least partially understanding the issues. > diff --git a/gcc/config/aarch64/aarch64-simd.md > b/gcc/config/aarch64/aarch64-simd.md > index 9777418..d6c5d61 100644 > --- a/gcc/config/aarch64/aarch64-simd.md > +++ b/gcc/config/aarch64/aarch64-simd.md > @@ -2636,6 +2636,60 @@ > > ;; w. > > +(define_expand "widen_ssum3" > + [(set (match_operand: 0 "register_operand" "") > +(plus: (sign_extend: (match_operand:VQW 1 > "register_operand" "")) Please check your mail settings, as the patch currently does not apply. The last time I saw this issue it was a mail client turning on format=flowed which caused carnage for patch files ( https://gcc.gnu.org/ml/gcc-patches/2015-08/msg00179.html ) > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > + { > +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); > +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); > + > +emit_insn (gen_aarch64_saddw_internal (temp, operands[2], > +operands[1], p)); Replace 8 spaces with a tab (mail client?). Thanks, James > +emit_insn (gen_aarch64_saddw2 (operands[0], temp, operands[1])); > +DONE; > + } > +) > + > +(define_expand "widen_ssum3" > + [(set (match_operand: 0 "register_operand" "") > +(plus: (sign_extend: > + (match_operand:VD_BHSI 1 "register_operand" "")) > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > +{ > + emit_insn (gen_aarch64_saddw (operands[0], operands[2], > operands[1])); > + DONE; > +}) > + > +(define_expand "widen_usum3" > + [(set (match_operand: 0 "register_operand" "=") > +(plus: (zero_extend: (match_operand:VQW 1 > "register_operand" "")) > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > + { > +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); > +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); > + > +emit_insn (gen_aarch64_uaddw_internal (temp, operands[2], > + operands[1], p)); > +emit_insn (gen_aarch64_uaddw2 (operands[0], temp, operands[1])); > +DONE; > + } > +) > + > +(define_expand "widen_usum3" > + [(set (match_operand: 0 "register_operand" "") > +(plus: (zero_extend: > + (match_operand:VD_BHSI 1 "register_operand" "")) > + (match_operand: 2 "register_operand" "")))] > + "TARGET_SIMD" > +{ > + emit_insn (gen_aarch64_uaddw (operands[0], operands[2], > operands[1])); > +
[PING] [Aarch64] Use vector wide add for mixed-mode adds
Ping. Originally posted here: https://gcc.gnu.org/ml/gcc-patches/2015-09/msg00408.html Regards, Michael Collison -- Michael Collison Linaro Toolchain Working Group michael.colli...@linaro.org
[Aarch64] Use vector wide add for mixed-mode adds
This patch is designed to address code that was not being vectorized due to missing widening patterns in the aarch64 backend. Code such as: int t6(int len, void * dummy, short * __restrict x) { len = len & ~31; int result = 0; __asm volatile (""); for (int i = 0; i < len; i++) result += x[i]; return result; } Validated on aarch64-none-elf, aarch64_be-none-elf, and aarch64-none-linus-gnu. Note that there are three non-execution tree dump vectorization regressions where previously code was being vectorized. They are: Passed now fails [PASS => FAIL]: gcc.dg/vect/slp-multitypes-4.c -flto -ffat-lto-objects scan-tree-dump-times vect "vectorized 1 loops" 1 gcc.dg/vect/slp-multitypes-4.c -flto -ffat-lto-objects scan-tree-dump-times vect "vectorizing stmts using SLP" 1 gcc.dg/vect/slp-multitypes-4.c scan-tree-dump-times vect "vectorized 1 loops" 1 gcc.dg/vect/slp-multitypes-4.c scan-tree-dump-times vect "vectorizing stmts using SLP" 1 gcc.dg/vect/slp-multitypes-5.c -flto -ffat-lto-objects scan-tree-dump-times vect "vectorized 1 loops" 1 gcc.dg/vect/slp-multitypes-5.c -flto -ffat-lto-objects scan-tree-dump-times vect "vectorizing stmts using SLP" 1 gcc.dg/vect/slp-multitypes-5.c scan-tree-dump-times vect "vectorized 1 loops" 1 gcc.dg/vect/slp-multitypes-5.c scan-tree-dump-times vect "vectorizing stmts using SLP" 1 gcc.dg/vect/slp-reduc-3.c -flto -ffat-lto-objects scan-tree-dump-times vect "vectorizing stmts using SLP" 1 gcc.dg/vect/slp-reduc-3.c scan-tree-dump-times vect "vectorizing stmts using SLP" 1 gcc.dg/vect/vect-125.c -flto -ffat-lto-objects scan-tree-dump vect "vectorized 1 loops" gcc.dg/vect/vect-125.c scan-tree-dump vect "vectorized 1 loops" I would like to treat these as saperate bugs and resolve them separately. 2015-09-04 Michael Collison* config/aarch64/aarch64-simd.md (widen_ssum, widen_usum, aarch64_w_internal): New patterns * config/aarch64/iterators.md (Vhalf, VDBLW): New mode attributes. * gcc.target/aarch64/saddw-1.c: New test. * gcc.target/aarch64/saddw-2.c: New test. * gcc.target/aarch64/uaddw-1.c: New test. * gcc.target/aarch64/uaddw-2.c: New test. * gcc.target/aarch64/uaddw-3.c: New test. diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index 9777418..d6c5d61 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -2636,6 +2636,60 @@ ;; w. +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") +(plus: (sign_extend: (match_operand:VQW 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_saddw_internal (temp, operands[2], +operands[1], p)); +emit_insn (gen_aarch64_saddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_ssum3" + [(set (match_operand: 0 "register_operand" "") +(plus: (sign_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_saddw (operands[0], operands[2], operands[1])); + DONE; +}) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "=") +(plus: (zero_extend: (match_operand:VQW 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" + { +rtx p = aarch64_simd_vect_par_cnst_half (mode, false); +rtx temp = gen_reg_rtx (GET_MODE (operands[0])); + +emit_insn (gen_aarch64_uaddw_internal (temp, operands[2], + operands[1], p)); +emit_insn (gen_aarch64_uaddw2 (operands[0], temp, operands[1])); +DONE; + } +) + +(define_expand "widen_usum3" + [(set (match_operand: 0 "register_operand" "") +(plus: (zero_extend: + (match_operand:VD_BHSI 1 "register_operand" "")) + (match_operand: 2 "register_operand" "")))] + "TARGET_SIMD" +{ + emit_insn (gen_aarch64_uaddw (operands[0], operands[2], operands[1])); + DONE; +}) + (define_insn "aarch64_w" [(set (match_operand: 0 "register_operand" "=w") (ADDSUB: (match_operand: 1 "register_operand" "w") @@ -2646,6 +2700,18 @@ [(set_attr "type" "neon__widen")] ) +(define_insn "aarch64_w_internal" + [(set (match_operand: 0 "register_operand" "=w") +(ADDSUB: (match_operand: 1 "register_operand" "w") +(ANY_EXTEND: + (vec_select: + (match_operand:VQW 2 "register_operand" "w") + (match_operand:VQW 3 "vect_par_cnst_lo_half" "")] + "TARGET_SIMD" +