https://gcc.gnu.org/g:27773b4db8507d5d0f5c203b6ad54bdd1268fb45
commit 27773b4db8507d5d0f5c203b6ad54bdd1268fb45
Author: Michael Meissner <meiss...@linux.ibm.com>
Date: Wed Jul 9 01:37:05 2025 -0400
PR target/117251: Improve vector nor to vector and fusion
See the following post for a complete explanation of what the patches
for PR target/117251:
* https://gcc.gnu.org/pipermail/gcc-patches/2025-June/686474.html
This is patch #5 of 45 to generate the 'XXEVAL' instruction on power10
and power11 instead of using the Altivec 'VNOR' instruction feeding
into 'VAND'. The 'XXEVAL' instruction can use all 64 vector registers,
instead of the 32 registers that traditional Altivec vector
instructions use. By allowing all of the vector registers to be used,
it reduces the amount of spilling that a large benchmark generated.
Currently the following code:
vector int a, b, c, d;
a = (~ (c | d)) & b;
Generates:
vnor t,c,d
vand a,t,b
Now in addition with this patch, if the arguments or result is
allocated to a traditional FPR register, the GCC compiler will now
generate the following code instead of adding vector move instructions:
xxeval a,b,c,8
Since fusion using 2 Altivec instructions is slightly faster than using
the 'XXEVAL' instruction we prefer to generate the Altivec instructions
if we can. In addition, because 'XXEVAL' is a prefixed instruction, it
possibly might generate an extra NOP instruction to align the 'XXEVAL'
instruction.
I have tested these patches on both big endian and little endian
PowerPC servers, with no regressions. Can I check these patchs into
the trunk?
2025-07-09 Michael Meissner <meiss...@linux.ibm.com>
gcc/
PR target/117251
* config/rs6000/fusion.md: Regenerate.
* config/rs6000/genfusion.pl (gen_logical_addsubf): Add support
to generate vector/vector nor/and fusion if XXEVAL is
supported.
Diff:
---
gcc/config/rs6000/fusion.md | 15 +++++++++------
gcc/config/rs6000/genfusion.pl | 1 +
2 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/gcc/config/rs6000/fusion.md b/gcc/config/rs6000/fusion.md
index 161419b7f586..ed15fccdf760 100644
--- a/gcc/config/rs6000/fusion.md
+++ b/gcc/config/rs6000/fusion.md
@@ -1949,20 +1949,23 @@
;; logical-logical fusion pattern generated by gen_logical_addsubf
;; vector vnor -> vand
(define_insn "*fuse_vnor_vand"
- [(set (match_operand:VM 3 "altivec_register_operand" "=&0,&1,&v,v")
- (and:VM (and:VM (not:VM (match_operand:VM 0 "altivec_register_operand"
"v,v,v,v"))
- (not:VM (match_operand:VM 1
"altivec_register_operand" "v,v,v,v")))
- (match_operand:VM 2 "altivec_register_operand" "v,v,v,v")))
- (clobber (match_scratch:VM 4 "=X,X,X,&v"))]
+ [(set (match_operand:VM 3 "vector_fusion_operand" "=&0,&1,&v,wa,v")
+ (and:VM (and:VM (not:VM (match_operand:VM 0 "vector_fusion_operand"
"v,v,v,wa,v"))
+ (not:VM (match_operand:VM 1 "vector_fusion_operand"
"v,v,v,wa,v")))
+ (match_operand:VM 2 "vector_fusion_operand" "v,v,v,wa,v")))
+ (clobber (match_scratch:VM 4 "=X,X,X,X,&v"))]
"(TARGET_P10_FUSION)"
"@
vnor %3,%1,%0\;vand %3,%3,%2
vnor %3,%1,%0\;vand %3,%3,%2
vnor %3,%1,%0\;vand %3,%3,%2
+ xxeval %x3,%x2,%x1,%x0,8
vnor %4,%1,%0\;vand %3,%4,%2"
[(set_attr "type" "fused_vector")
(set_attr "cost" "6")
- (set_attr "length" "8")])
+ (set_attr "length" "8")
+ (set_attr "prefixed" "*,*,*,yes,*")
+ (set_attr "isa" "*,*,*,xxeval,*")])
;; logical-logical fusion pattern generated by gen_logical_addsubf
;; vector vor -> vand
diff --git a/gcc/config/rs6000/genfusion.pl b/gcc/config/rs6000/genfusion.pl
index 9d3a01a4704a..40d62ae8e9c1 100755
--- a/gcc/config/rs6000/genfusion.pl
+++ b/gcc/config/rs6000/genfusion.pl
@@ -219,6 +219,7 @@ sub gen_logical_addsubf
"vandc_vand" => 2,
"vxor_vand" => 6,
"vor_vand" => 7,
+ "vnor_vand" => 8,
);
KIND: foreach $kind ('scalar','vector') {
