Hi, This patch creates an insn_and_split pattern which helps the duplicated constant vector replace the source pseudo of store insn in fwprop pass. Thus the store can be implemented by a single stxvd2x and it eliminates the unnecessary byte swap insn on P8 LE. The test case shows the optimization.
The patch depends on the first generic patch which uses insn cost in fwprop. https://gcc.gnu.org/pipermail/gcc-patches/2024-June/654276.html Compared to previous version, the main change is to remove the predict and put the check in insn condition and gcc assertion. Bootstrapped and tested on x86 and powerpc64-linux BE and LE with no regressions. Thanks Gui Haochen ChangeLog rs6000: Eliminate unnecessary byte swaps for duplicated constant vector store gcc/ PR target/113325 * config/rs6000/vsx.md (vsx_stxvd2x4_le_const_<mode>): New. gcc/testsuite/ PR target/113325 * gcc.target/powerpc/pr113325.c: New. patch.diff diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md index f135fa079bd..89eb32a0758 100644 --- a/gcc/config/rs6000/vsx.md +++ b/gcc/config/rs6000/vsx.md @@ -3368,6 +3368,32 @@ (define_insn "*vsx_stxvd2x4_le_<mode>" "stxvd2x %x1,%y0" [(set_attr "type" "vecstore")]) +(define_insn_and_split "vsx_stxvd2x4_le_const_<mode>" + [(set (match_operand:VSX_W 0 "memory_operand" "=Z") + (match_operand:VSX_W 1 "immediate_operand" "W"))] + "!BYTES_BIG_ENDIAN + && VECTOR_MEM_VSX_P (<MODE>mode) + && !TARGET_P9_VECTOR + && const_vec_duplicate_p (operands[1])" + "#" + "&& 1" + [(set (match_dup 2) + (match_dup 1)) + (set (match_dup 0) + (vec_select:VSX_W + (match_dup 2) + (parallel [(const_int 2) (const_int 3) + (const_int 0) (const_int 1)])))] +{ + /* Here all the constants must be loaded without memory. */ + gcc_assert (easy_altivec_constant (operands[1], <MODE>mode)); + operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[1]) + : operands[1]; + +} + [(set_attr "type" "vecstore") + (set_attr "length" "8")]) + (define_insn "*vsx_stxvd2x8_le_V8HI" [(set (match_operand:V8HI 0 "memory_operand" "=Z") (vec_select:V8HI diff --git a/gcc/testsuite/gcc.target/powerpc/pr113325.c b/gcc/testsuite/gcc.target/powerpc/pr113325.c new file mode 100644 index 00000000000..3ca1fcbc9ba --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr113325.c @@ -0,0 +1,9 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -mdejagnu-cpu=power8 -mvsx" } */ +/* { dg-require-effective-target powerpc_vsx } */ +/* { dg-final { scan-assembler-not {\mxxpermdi\M} } } */ + +void* foo (void* s1) +{ + return __builtin_memset (s1, 0, 32); +}
