[PATCH] rs6000: Prefer VSX insns over VMX ones (part 1: perm and mrg)
Segher Boessenkool
segher@kernel.crashing.org
Fri May 29 23:07:50 GMT 2020
There are various VSX insns that do the same job as (older) AltiVec
insns, just with a wider range of possible registers. Many patterns
for such insns have the "v" alternative before the "wa" alternative,
which makes the output less readable than possible (since vs32 is v0,
and most insns before or after this insn will be VSX as well).
This changes the define_insns for the mrg and perm machine instructions
to prefer the VSX form. No behaviour change. Only one testcase needed
a little adjustment as well.
Tested on powerpc64-linux {-m32,-m64}. Applying to trunk.
Segher
2020-05-29 Segher Boessenkool <segher@kernel.crashing.org>
* config/rs6000/altivec.md (altivec_vmrghw_direct): Prefer VSX form.
(altivec_vmrglw_direct): Ditto.
(altivec_vperm_<mode>_direct): Ditto.
(altivec_vperm_v8hiv16qi): Ditto.
(*altivec_vperm_<mode>_uns_internal): Ditto.
(*altivec_vpermr_<mode>_internal): Ditto.
(vperm_v8hiv4si): Ditto.
(vperm_v16qiv8hi): Ditto.
testsuite/
* gcc.target/powerpc/vsx-vector-6.p9.c: Allow xxperm as perm as well.
---
gcc/config/rs6000/altivec.md | 104 ++++++++++-----------
gcc/testsuite/gcc.target/powerpc/vsx-vector-6.p9.c | 2 +-
2 files changed, 53 insertions(+), 53 deletions(-)
diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index 792ca4f..159f24e 100644
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -1216,14 +1216,14 @@ (define_insn "*altivec_vmrghw_internal"
[(set_attr "type" "vecperm")])
(define_insn "altivec_vmrghw_direct"
- [(set (match_operand:V4SI 0 "register_operand" "=v,wa")
- (unspec:V4SI [(match_operand:V4SI 1 "register_operand" "v,wa")
- (match_operand:V4SI 2 "register_operand" "v,wa")]
+ [(set (match_operand:V4SI 0 "register_operand" "=wa,v")
+ (unspec:V4SI [(match_operand:V4SI 1 "register_operand" "wa,v")
+ (match_operand:V4SI 2 "register_operand" "wa,v")]
UNSPEC_VMRGH_DIRECT))]
"TARGET_ALTIVEC"
"@
- vmrghw %0,%1,%2
- xxmrghw %x0,%x1,%x2"
+ xxmrghw %x0,%x1,%x2
+ vmrghw %0,%1,%2"
[(set_attr "type" "vecperm")])
(define_insn "*altivec_vmrghsf"
@@ -1364,14 +1364,14 @@ (define_insn "*altivec_vmrglw_internal"
[(set_attr "type" "vecperm")])
(define_insn "altivec_vmrglw_direct"
- [(set (match_operand:V4SI 0 "register_operand" "=v,wa")
- (unspec:V4SI [(match_operand:V4SI 1 "register_operand" "v,wa")
- (match_operand:V4SI 2 "register_operand" "v,wa")]
+ [(set (match_operand:V4SI 0 "register_operand" "=wa,v")
+ (unspec:V4SI [(match_operand:V4SI 1 "register_operand" "wa,v")
+ (match_operand:V4SI 2 "register_operand" "wa,v")]
UNSPEC_VMRGL_DIRECT))]
"TARGET_ALTIVEC"
"@
- vmrglw %0,%1,%2
- xxmrglw %x0,%x1,%x2"
+ xxmrglw %x0,%x1,%x2
+ vmrglw %0,%1,%2"
[(set_attr "type" "vecperm")])
(define_insn "*altivec_vmrglsf"
@@ -2193,30 +2193,30 @@ (define_expand "altivec_vperm_<mode>"
;; Slightly prefer vperm, since the target does not overlap the source
(define_insn "altivec_vperm_<mode>_direct"
- [(set (match_operand:VM 0 "register_operand" "=v,?wa")
- (unspec:VM [(match_operand:VM 1 "register_operand" "v,wa")
- (match_operand:VM 2 "register_operand" "v,0")
- (match_operand:V16QI 3 "register_operand" "v,wa")]
+ [(set (match_operand:VM 0 "register_operand" "=?wa,v")
+ (unspec:VM [(match_operand:VM 1 "register_operand" "wa,v")
+ (match_operand:VM 2 "register_operand" "0,v")
+ (match_operand:V16QI 3 "register_operand" "wa,v")]
UNSPEC_VPERM))]
"TARGET_ALTIVEC"
"@
- vperm %0,%1,%2,%3
- xxperm %x0,%x1,%x3"
+ xxperm %x0,%x1,%x3
+ vperm %0,%1,%2,%3"
[(set_attr "type" "vecperm")
- (set_attr "isa" "*,p9v")])
+ (set_attr "isa" "p9v,*")])
(define_insn "altivec_vperm_v8hiv16qi"
- [(set (match_operand:V16QI 0 "register_operand" "=v,?wa")
- (unspec:V16QI [(match_operand:V8HI 1 "register_operand" "v,wa")
- (match_operand:V8HI 2 "register_operand" "v,0")
- (match_operand:V16QI 3 "register_operand" "v,wa")]
+ [(set (match_operand:V16QI 0 "register_operand" "=?wa,v")
+ (unspec:V16QI [(match_operand:V8HI 1 "register_operand" "wa,v")
+ (match_operand:V8HI 2 "register_operand" "0,v")
+ (match_operand:V16QI 3 "register_operand" "wa,v")]
UNSPEC_VPERM))]
"TARGET_ALTIVEC"
"@
- vperm %0,%1,%2,%3
- xxperm %x0,%x1,%x3"
+ xxperm %x0,%x1,%x3
+ vperm %0,%1,%2,%3"
[(set_attr "type" "vecperm")
- (set_attr "isa" "*,p9v")])
+ (set_attr "isa" "p9v,*")])
(define_expand "altivec_vperm_<mode>_uns"
[(set (match_operand:VM 0 "register_operand")
@@ -2234,17 +2234,17 @@ (define_expand "altivec_vperm_<mode>_uns"
})
(define_insn "*altivec_vperm_<mode>_uns_internal"
- [(set (match_operand:VM 0 "register_operand" "=v,?wa")
- (unspec:VM [(match_operand:VM 1 "register_operand" "v,wa")
- (match_operand:VM 2 "register_operand" "v,0")
- (match_operand:V16QI 3 "register_operand" "v,wa")]
+ [(set (match_operand:VM 0 "register_operand" "=?wa,v")
+ (unspec:VM [(match_operand:VM 1 "register_operand" "wa,v")
+ (match_operand:VM 2 "register_operand" "0,v")
+ (match_operand:V16QI 3 "register_operand" "wa,v")]
UNSPEC_VPERM_UNS))]
"TARGET_ALTIVEC"
"@
- vperm %0,%1,%2,%3
- xxperm %x0,%x1,%x3"
+ xxperm %x0,%x1,%x3
+ vperm %0,%1,%2,%3"
[(set_attr "type" "vecperm")
- (set_attr "isa" "*,p9v")])
+ (set_attr "isa" "p9v,*")])
(define_expand "vec_permv16qi"
[(set (match_operand:V16QI 0 "register_operand")
@@ -2261,17 +2261,17 @@ (define_expand "vec_permv16qi"
})
(define_insn "*altivec_vpermr_<mode>_internal"
- [(set (match_operand:VM 0 "register_operand" "=v,?wa")
- (unspec:VM [(match_operand:VM 1 "register_operand" "v,wa")
- (match_operand:VM 2 "register_operand" "v,0")
- (match_operand:V16QI 3 "register_operand" "v,wa")]
+ [(set (match_operand:VM 0 "register_operand" "=?wa,v")
+ (unspec:VM [(match_operand:VM 1 "register_operand" "wa,v")
+ (match_operand:VM 2 "register_operand" "0,v")
+ (match_operand:V16QI 3 "register_operand" "wa,v")]
UNSPEC_VPERMR))]
"TARGET_P9_VECTOR"
"@
- vpermr %0,%1,%2,%3
- xxpermr %x0,%x1,%x3"
+ xxpermr %x0,%x1,%x3
+ vpermr %0,%1,%2,%3"
[(set_attr "type" "vecperm")
- (set_attr "isa" "*,p9v")])
+ (set_attr "isa" "p9v,*")])
(define_insn "altivec_vrfip" ; ceil
[(set (match_operand:V4SF 0 "register_operand" "=v")
@@ -3414,30 +3414,30 @@ (define_expand "vec_unpacks_lo_<VP_small_lc>"
"")
(define_insn "vperm_v8hiv4si"
- [(set (match_operand:V4SI 0 "register_operand" "=v,?wa")
- (unspec:V4SI [(match_operand:V8HI 1 "register_operand" "v,wa")
- (match_operand:V4SI 2 "register_operand" "v,0")
- (match_operand:V16QI 3 "register_operand" "v,wa")]
+ [(set (match_operand:V4SI 0 "register_operand" "=?wa,v")
+ (unspec:V4SI [(match_operand:V8HI 1 "register_operand" "wa,v")
+ (match_operand:V4SI 2 "register_operand" "0,v")
+ (match_operand:V16QI 3 "register_operand" "wa,v")]
UNSPEC_VPERMSI))]
"TARGET_ALTIVEC"
"@
- vperm %0,%1,%2,%3
- xxperm %x0,%x1,%x3"
+ xxperm %x0,%x1,%x3
+ vperm %0,%1,%2,%3"
[(set_attr "type" "vecperm")
- (set_attr "isa" "*,p9v")])
+ (set_attr "isa" "p9v,*")])
(define_insn "vperm_v16qiv8hi"
- [(set (match_operand:V8HI 0 "register_operand" "=v,?wa")
- (unspec:V8HI [(match_operand:V16QI 1 "register_operand" "v,wa")
- (match_operand:V8HI 2 "register_operand" "v,0")
- (match_operand:V16QI 3 "register_operand" "v,wa")]
+ [(set (match_operand:V8HI 0 "register_operand" "=?wa,v")
+ (unspec:V8HI [(match_operand:V16QI 1 "register_operand" "wa,v")
+ (match_operand:V8HI 2 "register_operand" "0,v")
+ (match_operand:V16QI 3 "register_operand" "wa,v")]
UNSPEC_VPERMHI))]
"TARGET_ALTIVEC"
"@
- vperm %0,%1,%2,%3
- xxperm %x0,%x1,%x3"
+ xxperm %x0,%x1,%x3
+ vperm %0,%1,%2,%3"
[(set_attr "type" "vecperm")
- (set_attr "isa" "*,p9v")])
+ (set_attr "isa" "p9v,*")])
(define_insn "xxeval"
[(set (match_operand:V2DI 0 "register_operand" "=wa")
diff --git a/gcc/testsuite/gcc.target/powerpc/vsx-vector-6.p9.c b/gcc/testsuite/gcc.target/powerpc/vsx-vector-6.p9.c
index eabdf71..43d2e85 100644
--- a/gcc/testsuite/gcc.target/powerpc/vsx-vector-6.p9.c
+++ b/gcc/testsuite/gcc.target/powerpc/vsx-vector-6.p9.c
@@ -9,7 +9,7 @@
/* { dg-final { scan-assembler-times {\mvmaxub\M} 1 } } */
/* { dg-final { scan-assembler-times {\mvmsumshs\M} 1 } } */
/* { dg-final { scan-assembler-times {\mvmsumuhs\M} 1 } } */
-/* { dg-final { scan-assembler-times {\mvpermr?\M} 1 } } */
+/* { dg-final { scan-assembler-times {\m(?:vpermr?|xxperm)\M} 1 } } */
/* { dg-final { scan-assembler-times {\mxvabsdp\M} 1 } } */
/* { dg-final { scan-assembler-times {\mxvadddp\M} 1 } } */
/* { dg-final { scan-assembler-times {\mxvcmpeqdp\M} 9 } } */
--
1.8.3.1
More information about the Gcc-patches
mailing list