https://gcc.gnu.org/g:354265eee1a38f71029c210b2ef0c0c71a4a0f81
commit 354265eee1a38f71029c210b2ef0c0c71a4a0f81 Author: Michael Meissner <[email protected]> Date: Fri Jan 30 16:58:03 2026 -0500 PR target/117251: Improve vector nor to vector nor 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 #21 of 45 to generate the 'XXEVAL' instruction on power10 and power11 instead of using the Altivec 'VNOR' instruction feeding into 'VNOR'. 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 vnor 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,112 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 nor => nor 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 d2dcd8f290c4..6fd9f333306a 100644 --- a/gcc/config/rs6000/fusion.md +++ b/gcc/config/rs6000/fusion.md @@ -2555,20 +2555,23 @@ ;; logical-logical fusion pattern generated by gen_logical_addsubf ;; vector vnor -> vnor (define_insn "*fuse_vnor_vnor" - [(set (match_operand:VM 3 "altivec_register_operand" "=&0,&1,&v,v") - (and:VM (not: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")))) - (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 (not: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")))) + (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)" "@ vnor %3,%1,%0\;vnor %3,%3,%2 vnor %3,%1,%0\;vnor %3,%3,%2 vnor %3,%1,%0\;vnor %3,%3,%2 + xxeval %x3,%x2,%x1,%x0,112 vnor %4,%1,%0\;vnor %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 -> vnor diff --git a/gcc/config/rs6000/genfusion.pl b/gcc/config/rs6000/genfusion.pl index 216aee1eb9a3..a4a95388fcde 100755 --- a/gcc/config/rs6000/genfusion.pl +++ b/gcc/config/rs6000/genfusion.pl @@ -235,6 +235,7 @@ sub gen_logical_addsubf "veqv_vnor" => 96, "vxor_vxor" => 105, "vxor_vor" => 111, + "vnor_vnor" => 112, ); KIND: foreach $kind ('scalar','vector') {
