Hi,
Please find attached the patch that adds "neon_pairwise_add" &
"neon_pairwise_add_qcrypto_pmull" for AArch64.
The patch doesn't change spec but improve other benchmarks.
Bootstrapped and Regression tested on aarch64-thunder-linux.
Please review the patch and let us know if its okay for Stage-1?
Thanks,
Naveen
2017-03-06 Julian Brown <jul...@codesourcery.com>
Naveen H.S <naveen.hurugalaw...@cavium.com>
* config/aarch64/aarch64-simd.md (aarch64_reduc_plus_internal<mode>)
(aarch64_reduc_plus_internalv2si, aarch64_addp<mode>, aarch64_addpdi):
Use neon_pairwise_add/neon_pairwise_add_q as appropriate.
* config/aarch64/iterators.md (reduc_pairwise): New mode attribute.
* config/aarch64/thunderx.md (thunderx_neon_add, thunderx_neon_add_q):
Tweak for neon_pairwise_add split.
* config/aarch64/thunderx2t99.md (thunderx2t99_asimd_int): Add
neon_pairwise_add/neon_pairwise_add_q types.
* config/arm/cortex-a15-neon.md (cortex_a15_neon_type): Likewise.
* config/arm/cortex-a17-neon.md (cortex_a17_neon_type): Likewise.
* config/arm/cortex-a57.md (cortex_a57_neon_type): Likewise.
* config/arm/cortex-a8-neon.md (cortex_a8_neon_type): Likewise.
* config/arm/cortex-a9-neon.md (cortex_a9_neon_type): Likewise.
* config/arm/xgene1.md (xgene1_neon_arith): Likewise.
* config/arm/types.md (neon_pairwise_add, neon_pairwise_add_q): Add.
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 338b9f8..878f86a 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -2101,7 +2101,7 @@
UNSPEC_ADDV))]
"TARGET_SIMD"
"add<VDQV:vp>\\t%<Vetype>0, %1.<Vtype>"
- [(set_attr "type" "neon_reduc_add<q>")]
+ [(set_attr "type" "neon_<reduc_pairwise>_add<q>")]
)
(define_insn "aarch64_reduc_plus_internalv2si"
@@ -2110,7 +2110,7 @@
UNSPEC_ADDV))]
"TARGET_SIMD"
"addp\\t%0.2s, %1.2s, %1.2s"
- [(set_attr "type" "neon_reduc_add")]
+ [(set_attr "type" "neon_pairwise_add")]
)
(define_insn "reduc_plus_scal_<mode>"
@@ -4405,7 +4405,7 @@
UNSPEC_ADDP))]
"TARGET_SIMD"
"addp\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
- [(set_attr "type" "neon_reduc_add<q>")]
+ [(set_attr "type" "neon_pairwise_add<q>")]
)
(define_insn "aarch64_addpdi"
@@ -4415,7 +4415,7 @@
UNSPEC_ADDP))]
"TARGET_SIMD"
"addp\t%d0, %1.2d"
- [(set_attr "type" "neon_reduc_add")]
+ [(set_attr "type" "neon_pairwise_add")]
)
;; sqrt
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index c59d31e..c829cb5 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -790,6 +790,12 @@
(V2SF "p") (V4SF "v")
(V4HF "v") (V8HF "v")])
+(define_mode_attr reduc_pairwise [(V8QI "reduc") (V16QI "reduc")
+ (V4HI "reduc") (V8HI "reduc")
+ (V2SI "pairwise") (V4SI "reduc")
+ (V2DI "pairwise") (V2DF "pairwise")
+ (V2SF "pairwise") (V4SF "reduc")])
+
(define_mode_attr vsi2qi [(V2SI "v8qi") (V4SI "v16qi")])
(define_mode_attr VSI2QI [(V2SI "V8QI") (V4SI "V16QI")])
diff --git a/gcc/config/aarch64/thunderx.md b/gcc/config/aarch64/thunderx.md
index b67671d..95bfad4 100644
--- a/gcc/config/aarch64/thunderx.md
+++ b/gcc/config/aarch64/thunderx.md
@@ -266,7 +266,8 @@
(define_insn_reservation "thunderx_neon_add" 4
(and (eq_attr "tune" "thunderx")
- (eq_attr "type" "neon_reduc_add, neon_reduc_minmax, neon_fp_reduc_add_s, \
+ (eq_attr "type" "neon_reduc_add, neon_pairwise_add, neon_reduc_minmax,\
+ neon_fp_reduc_add_s, \
neon_fp_reduc_add_d, neon_fp_to_int_s, neon_fp_to_int_d, \
neon_add_halve, neon_sub_halve, neon_qadd, neon_compare, \
neon_compare_zero, neon_minmax, neon_abd, neon_add, neon_sub, \
@@ -280,7 +281,8 @@
(define_insn_reservation "thunderx_neon_add_q" 5
(and (eq_attr "tune" "thunderx")
- (eq_attr "type" "neon_reduc_add_q, neon_reduc_minmax_q, neon_fp_reduc_add_s_q, \
+ (eq_attr "type" "neon_reduc_add_q, neon_pairwise_add_q,\
+ neon_reduc_minmax_q, neon_fp_reduc_add_s_q, \
neon_fp_reduc_add_d_q, neon_fp_to_int_s_q, neon_fp_to_int_d_q, \
neon_add_halve_q, neon_sub_halve_q, neon_qadd_q, neon_compare_q, \
neon_compare_zero_q, neon_minmax_q, neon_abd_q, neon_add_q, neon_sub_q, \
diff --git a/gcc/config/aarch64/thunderx2t99.md b/gcc/config/aarch64/thunderx2t99.md
index 67011ac..f807547 100644
--- a/gcc/config/aarch64/thunderx2t99.md
+++ b/gcc/config/aarch64/thunderx2t99.md
@@ -231,6 +231,7 @@
neon_abs,neon_abs_q,\
neon_add,neon_add_q,\
neon_neg,neon_neg_q,\
+ neon_pairwise_add,neon_pairwise_add_q,\
neon_add_long,neon_add_widen,\
neon_add_halve,neon_add_halve_q,\
neon_sub_long,neon_sub_widen,\
diff --git a/gcc/config/arm/cortex-a15-neon.md b/gcc/config/arm/cortex-a15-neon.md
index 73ee84c..1a02fa2 100644
--- a/gcc/config/arm/cortex-a15-neon.md
+++ b/gcc/config/arm/cortex-a15-neon.md
@@ -48,6 +48,7 @@
(eq_attr "type" "neon_add, neon_add_q, neon_add_long,\
neon_add_widen, neon_neg, neon_neg_q,\
neon_reduc_add, neon_reduc_add_q,\
+ neon_pairwise_add, neon_pairwise_add_q,\
neon_reduc_add_long, neon_sub, neon_sub_q,\
neon_sub_long, neon_sub_widen, neon_logic,\
neon_logic_q, neon_tst, neon_tst_q")
diff --git a/gcc/config/arm/cortex-a17-neon.md b/gcc/config/arm/cortex-a17-neon.md
index 29d08de..d4f9e03 100644
--- a/gcc/config/arm/cortex-a17-neon.md
+++ b/gcc/config/arm/cortex-a17-neon.md
@@ -47,6 +47,7 @@
(eq_attr "type" "neon_add, neon_add_q, neon_add_long,\
neon_add_widen, neon_neg, neon_neg_q,\
neon_reduc_add, neon_reduc_add_q,\
+ neon_pairwise_add, neon_pairwise_add_q,\
neon_reduc_add_long, neon_sub, neon_sub_q,\
neon_sub_long, neon_sub_widen, neon_logic,\
neon_logic_q, neon_tst, neon_tst_q")
diff --git a/gcc/config/arm/cortex-a57.md b/gcc/config/arm/cortex-a57.md
index ebf4a49..cb5e181 100644
--- a/gcc/config/arm/cortex-a57.md
+++ b/gcc/config/arm/cortex-a57.md
@@ -50,6 +50,7 @@
(eq_attr "type" "neon_add, neon_add_q, neon_add_long,\
neon_add_widen, neon_neg, neon_neg_q,\
neon_reduc_add, neon_reduc_add_q,\
+ neon_pairwise_add, neon_pairwise_add_q,\
neon_reduc_add_long, neon_sub, neon_sub_q,\
neon_sub_long, neon_sub_widen, neon_logic,\
neon_logic_q, neon_tst, neon_tst_q")
diff --git a/gcc/config/arm/cortex-a8-neon.md b/gcc/config/arm/cortex-a8-neon.md
index baa9180..652ba4e 100644
--- a/gcc/config/arm/cortex-a8-neon.md
+++ b/gcc/config/arm/cortex-a8-neon.md
@@ -51,6 +51,7 @@
(const_string "neon_int_2")
(eq_attr "type" "neon_neg, neon_neg_q,\
neon_reduc_add, neon_reduc_add_q,\
+ neon_pairwise_add, neon_pairwise_add_q,\
neon_reduc_add_long,\
neon_add_long, neon_sub_long")
(const_string "neon_int_3")
diff --git a/gcc/config/arm/cortex-a9-neon.md b/gcc/config/arm/cortex-a9-neon.md
index 9e9827f..bb1e300 100644
--- a/gcc/config/arm/cortex-a9-neon.md
+++ b/gcc/config/arm/cortex-a9-neon.md
@@ -52,6 +52,7 @@
(const_string "neon_int_2")
(eq_attr "type" "neon_neg, neon_neg_q,\
neon_reduc_add, neon_reduc_add_q,\
+ neon_pairwise_add, neon_pairwise_add_q,\
neon_reduc_add_long,\
neon_add_long, neon_sub_long")
(const_string "neon_int_3")
diff --git a/gcc/config/arm/types.md b/gcc/config/arm/types.md
index 253f496..ce1b6bc 100644
--- a/gcc/config/arm/types.md
+++ b/gcc/config/arm/types.md
@@ -274,6 +274,8 @@
; neon_reduc_add_long
; neon_reduc_add_acc
; neon_reduc_add_acc_q
+; neon_pairwise_add
+; neon_pairwise_add_q
; neon_reduc_minmax
; neon_reduc_minmax_q
; neon_logic
@@ -788,6 +790,8 @@
neon_reduc_add_long,\
neon_reduc_add_acc,\
neon_reduc_add_acc_q,\
+ neon_pairwise_add,\
+ neon_pairwise_add_q,\
neon_reduc_minmax,\
neon_reduc_minmax_q,\
neon_logic,\
@@ -1116,6 +1120,7 @@
neon_compare_q, neon_compare_zero, neon_compare_zero_q,\
neon_arith_acc, neon_arith_acc_q, neon_reduc_add,\
neon_reduc_add_q, neon_reduc_add_long, neon_reduc_add_acc,\
+ neon_pairwise_add, neon_pairwise_add_q,\
neon_reduc_add_acc_q, neon_reduc_minmax, neon_reduc_minmax_q,\
neon_logic, neon_logic_q, neon_tst, neon_tst_q,\
neon_shift_imm, neon_shift_imm_q, neon_shift_imm_narrow_q,\
diff --git a/gcc/config/arm/xgene1.md b/gcc/config/arm/xgene1.md
index 34a13f4..1f68305 100644
--- a/gcc/config/arm/xgene1.md
+++ b/gcc/config/arm/xgene1.md
@@ -288,6 +288,8 @@
neon_arith_acc_q,\
neon_reduc_add,\
neon_reduc_add_q,\
+ neon_pairwise_add,\
+ neon_pairwise_add_q,\
neon_add_halve,\
neon_add_halve_q,\
neon_sub_halve,\
