https://gcc.gnu.org/g:4759feb7e92188b65dac815c6b526c4dc4b29d69

commit 4759feb7e92188b65dac815c6b526c4dc4b29d69
Author: Michael Meissner <[email protected]>
Date:   Fri Feb 6 13:58:05 2026 -0500

    PR target/117251: Improve vector nand to vector or 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 #36 of 45 to generate the 'XXEVAL' instruction on power10
    and power11 instead of using the Altivec 'VNAND' instruction feeding
    into 'VOR'.  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:
    
            vnand  t,c,d
            vor    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,239
    
    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?
    
    2026-01-30  Michael Meissner  <[email protected]>
    
    gcc/
    
            PR target/117251
            * config/rs6000/fusion.md: Regenerate.
            * config/rs6000/genfusion.pl (gen_logical_addsubf): Add support
            to generate vector nand => or 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 e1d90583f7b3..ff358854ada5 100644
--- a/gcc/config/rs6000/fusion.md
+++ b/gcc/config/rs6000/fusion.md
@@ -2858,20 +2858,23 @@
 ;; logical-logical fusion pattern generated by gen_logical_addsubf
 ;; vector vandc -> vorc
 (define_insn "*fuse_vandc_vorc"
-  [(set (match_operand:VM 3 "altivec_register_operand" "=&0,&1,&v,v")
-        (ior:VM (and:VM (not:VM (match_operand:VM 0 "altivec_register_operand" 
"v,v,v,v"))
-                          (match_operand:VM 1 "altivec_register_operand" 
"v,v,v,v"))
-                 (not:VM (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")
+        (ior:VM (and:VM (not:VM (match_operand:VM 0 "vector_fusion_operand" 
"v,v,v,wa,v"))
+                          (match_operand:VM 1 "vector_fusion_operand" 
"v,v,v,wa,v"))
+                 (not:VM (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)"
   "@
    vandc %3,%1,%0\;vorc %3,%3,%2
    vandc %3,%1,%0\;vorc %3,%3,%2
    vandc %3,%1,%0\;vorc %3,%3,%2
+   xxeval %x3,%x2,%x1,%x0,244
    vandc %4,%1,%0\;vorc %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 veqv -> vorc
diff --git a/gcc/config/rs6000/genfusion.pl b/gcc/config/rs6000/genfusion.pl
index 3856296e88ec..7f853a2e13e2 100755
--- a/gcc/config/rs6000/genfusion.pl
+++ b/gcc/config/rs6000/genfusion.pl
@@ -253,6 +253,7 @@ sub gen_logical_addsubf
       "vnand_vor"   => 239,
       "vnand_vnand" => 241,
       "vorc_vnand"  => 244,
+      "vandc_vorc"  => 244,
       "veqv_vnand"  => 246,
       "vnor_vnand"  => 247,
       "vor_vnand"   => 248,

Reply via email to