Hi, This patch implements V8HI byte reverse on Power8 by vector rotation. It should be effecient than orignial vector permute. The patch comes from Xionghu's comments in PR. I just added a test case for it.
Bootstrapped and tested on ppc64 Linux BE and LE with no regressions. Is this okay for trunk? Any recommendations? Thanks a lot. ChangeLog 2022-10-24 Xionghu Luo <xionghu...@tencent.com> gcc/ PR target/100866 * config/rs6000/altivec.md: (*altivec_vrl<VI_char>): Named to... (altivec_vrl<VI_char>): ...this. * config/rs6000/vsx.md (revb_<mode>): Call vspltish and vrlh when target is Power8 and mode is V8HI. gcc/testsuite/ PR target/100866 * gcc.target/powerpc/pr100866-2.c: New. patch.diff diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md index 2c4940f2e21..84660073f32 100644 --- a/gcc/config/rs6000/altivec.md +++ b/gcc/config/rs6000/altivec.md @@ -1875,7 +1875,7 @@ (define_insn "altivec_vpku<VI_char>um_direct" } [(set_attr "type" "vecperm")]) -(define_insn "*altivec_vrl<VI_char>" +(define_insn "altivec_vrl<VI_char>" [(set (match_operand:VI2 0 "register_operand" "=v") (rotate:VI2 (match_operand:VI2 1 "register_operand" "v") (match_operand:VI2 2 "register_operand" "v")))] diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md index e226a93bbe5..34662a7252d 100644 --- a/gcc/config/rs6000/vsx.md +++ b/gcc/config/rs6000/vsx.md @@ -6092,12 +6092,21 @@ (define_expand "revb_<mode>" emit_insn (gen_p9_xxbr<VSX_XXBR>_<mode> (operands[0], operands[1])); else { - /* Want to have the elements in reverse order relative - to the endian mode in use, i.e. in LE mode, put elements - in BE order. */ - rtx sel = swap_endian_selector_for_mode(<MODE>mode); - emit_insn (gen_altivec_vperm_<mode> (operands[0], operands[1], - operands[1], sel)); + if (<MODE>mode == V8HImode) + { + rtx splt = gen_reg_rtx (V8HImode); + emit_insn (gen_altivec_vspltish (splt, GEN_INT (8))); + emit_insn (gen_altivec_vrlh (operands[0], operands[1], splt)); + } + else + { + /* Want to have the elements in reverse order relative + to the endian mode in use, i.e. in LE mode, put elements + in BE order. */ + rtx sel = swap_endian_selector_for_mode (<MODE>mode); + emit_insn (gen_altivec_vperm_<mode> (operands[0], operands[1], + operands[1], sel)); + } } DONE; diff --git a/gcc/testsuite/gcc.target/powerpc/pr100866-2.c b/gcc/testsuite/gcc.target/powerpc/pr100866-2.c new file mode 100644 index 00000000000..4357d1beb09 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr100866-2.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target powerpc_p8vector_ok } */ +/* { dg-options "-O2 -mdejagnu-cpu=power8" } */ +/* { dg-final { scan-assembler {\mvspltish\M} } } */ +/* { dg-final { scan-assembler {\mvrlh\M} } } */ + +#include <altivec.h> + +vector unsigned short revb(vector unsigned short a) +{ + return vec_revb(a); +} +