https://gcc.gnu.org/g:125f6f684ebeb4f02d065ee42edace1170db7ce8
commit 125f6f684ebeb4f02d065ee42edace1170db7ce8 Author: Michael Meissner <[email protected]> Date: Fri Jan 30 16:45:01 2026 -0500 PR target/117251: Improve vector andc to vector andc 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 #8 of 45 to generate the 'XXEVAL' instruction on power10 and power11 instead of using the Altivec 'VANDC' instruction feeding into 'VANDC'. 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: vandc t,c,d vandc 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,13 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/vector andc/andc 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 595217ed7c83..6b283c2f29e1 100644 --- a/gcc/config/rs6000/fusion.md +++ b/gcc/config/rs6000/fusion.md @@ -2054,20 +2054,23 @@ ;; logical-logical fusion pattern generated by gen_logical_addsubf ;; vector vandc -> vandc (define_insn "*fuse_vandc_vandc" - [(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")) - (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") + (and: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\;vandc %3,%3,%2 vandc %3,%1,%0\;vandc %3,%3,%2 vandc %3,%1,%0\;vandc %3,%3,%2 + xxeval %x3,%x2,%x1,%x0,13 vandc %4,%1,%0\;vandc %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 -> vandc diff --git a/gcc/config/rs6000/genfusion.pl b/gcc/config/rs6000/genfusion.pl index da33b402e10e..53021a8005b7 100755 --- a/gcc/config/rs6000/genfusion.pl +++ b/gcc/config/rs6000/genfusion.pl @@ -222,6 +222,7 @@ sub gen_logical_addsubf "vnor_vand" => 8, "veqv_vand" => 9, "vorc_vand" => 11, + "vandc_vandc" => 13, ); KIND: foreach $kind ('scalar','vector') {
