aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKyrylo Tkachov <kyrylo.tkachov@arm.com>2023-04-24 09:41:42 +0100
committerKyrylo Tkachov <kyrylo.tkachov@arm.com>2023-04-24 09:41:42 +0100
commitc60654918bc14c3d8fe04d3e7c3aa9daee0a3820 (patch)
tree02635a70e61a8a390478dc5e0e751139956cf33e
parent6ec565d8755afe1c187cda69fb8e478e669cfd02 (diff)
downloadgcc-c60654918bc14c3d8fe04d3e7c3aa9daee0a3820.zip
gcc-c60654918bc14c3d8fe04d3e7c3aa9daee0a3820.tar.gz
gcc-c60654918bc14c3d8fe04d3e7c3aa9daee0a3820.tar.bz2
[1/4] aarch64: Convert UABDL and SABDL patterns to standard RTL codes
This is the first patch in a series to improve the RTL representation of the sum-of-absolute-differences patterns in the backend. We can use standard RTL codes and remove some unspecs. For UABDL and SABDL we have a widening of the result so we can represent uabdl (x, y) as (zero_extend (minus (smax (x, y) (smin (x, y))))) and sabdl (x, y) as (zero_extend (minus (umax (x, y) (umin (x, y))))). It is important to use zero_extend rather than sign_extend for the sabdl case, as the result of the absolute difference is still a positive unsigned value (the signedness of the operation refers to the values being diffed, not the absolute value of the difference) that must be zero-extended. Bootstrapped and tested on aarch64-none-linux-gnu (these intrinsics are reasonably well-covered by the advsimd-intrinsics.exp tests) gcc/ChangeLog: * config/aarch64/aarch64-simd.md (aarch64_<sur>abdl<mode>): Rename to... (aarch64_<su>abdl<mode>): ... This. Use standard RTL ops instead of unspec. * config/aarch64/aarch64.md (UNSPEC_SABDL, UNSPEC_UABDL): Delete. * config/aarch64/iterators.md (ABDL): Delete. (sur): Remove handling of UNSPEC_SABDL and UNSPEC_UABDL.
-rw-r--r--gcc/config/aarch64/aarch64-simd.md16
-rw-r--r--gcc/config/aarch64/aarch64.md2
-rw-r--r--gcc/config/aarch64/iterators.md4
3 files changed, 10 insertions, 12 deletions
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index d1e74a6..b46eb1d 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -899,14 +899,18 @@
[(set_attr "type" "neon_abd<q>")]
)
-
-(define_insn "aarch64_<sur>abdl<mode>"
+(define_insn "aarch64_<su>abdl<mode>"
[(set (match_operand:<VWIDE> 0 "register_operand" "=w")
- (unspec:<VWIDE> [(match_operand:VD_BHSI 1 "register_operand" "w")
- (match_operand:VD_BHSI 2 "register_operand" "w")]
- ABDL))]
+ (zero_extend:<VWIDE>
+ (minus:VD_BHSI
+ (USMAX:VD_BHSI
+ (match_operand:VD_BHSI 1 "register_operand" "w")
+ (match_operand:VD_BHSI 2 "register_operand" "w"))
+ (<max_opp>:VD_BHSI
+ (match_dup 1)
+ (match_dup 2)))))]
"TARGET_SIMD"
- "<sur>abdl\t%0.<Vwtype>, %1.<Vtype>, %2.<Vtype>"
+ "<su>abdl\t%0.<Vwtype>, %1.<Vtype>, %2.<Vtype>"
[(set_attr "type" "neon_abd<q>")]
)
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index eaa87bf..a1f35f2 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -206,7 +206,6 @@
UNSPEC_RBIT
UNSPEC_SABAL
UNSPEC_SABAL2
- UNSPEC_SABDL
UNSPEC_SABDL2
UNSPEC_SADALP
UNSPEC_SCVTF
@@ -230,7 +229,6 @@
UNSPEC_TLSLE48
UNSPEC_UABAL
UNSPEC_UABAL2
- UNSPEC_UABDL
UNSPEC_UABDL2
UNSPEC_UADALP
UNSPEC_UCVTF
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index d0184c8..b7d67a6 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -2570,9 +2570,6 @@
;; The unspec codes for the SABAL, UABAL AdvancedSIMD instructions.
(define_int_iterator ABAL [UNSPEC_SABAL UNSPEC_UABAL])
-;; The unspec codes for the SABDL, UABDL AdvancedSIMD instructions.
-(define_int_iterator ABDL [UNSPEC_SABDL UNSPEC_UABDL])
-
;; The unspec codes for the SABAL2, UABAL2 AdvancedSIMD instructions.
(define_int_iterator ABAL2 [UNSPEC_SABAL2 UNSPEC_UABAL2])
@@ -3362,7 +3359,6 @@
(UNSPEC_ADDHN "") (UNSPEC_RADDHN "r")
(UNSPEC_SABAL "s") (UNSPEC_UABAL "u")
(UNSPEC_SABAL2 "s") (UNSPEC_UABAL2 "u")
- (UNSPEC_SABDL "s") (UNSPEC_UABDL "u")
(UNSPEC_SABDL2 "s") (UNSPEC_UABDL2 "u")
(UNSPEC_SADALP "s") (UNSPEC_UADALP "u")
(UNSPEC_SUBHN "") (UNSPEC_RSUBHN "r")