https://gcc.gnu.org/g:9e52245dd8aa2574bc1c215a45b2d7f8a8aa3cfd
commit 9e52245dd8aa2574bc1c215a45b2d7f8a8aa3cfd Author: Michael Meissner <meiss...@linux.ibm.com> Date: Wed Apr 10 11:34:46 2024 -0400 PR target/112886, Add %S<n> to print_operand for vector pair support. In looking at support for load vector pair and store vector pair for the PowerPC in GCC, I noticed that we were missing a print_operand output modifier if you are dealing with vector pairs to print the 2nd register in the vector pair. If the instruction inside of the asm used the Altivec encoding, then we could use the %L<n> modifier: __vector_pair *p, *q, *r; // ... __asm__ ("vaddudm %0,%1,%2\n\tvaddudm %L0,%L1,%L2" : "=v" (*p) : "v" (*q), "v" (*r)); Likewise if we know the value to be in a tradiational FPR register, %L<n> will work for instructions that use the VSX encoding: __vector_pair *p, *q, *r; // ... __asm__ ("xvadddp %x0,%x1,%x2\n\txvadddp %L0,%L1,%L2" : "=f" (*p) : "f" (*q), "f" (*r)); But if have a value that is in a traditional Altivec register, and the instruction uses the VSX encoding, %L<n> will a value between 0 and 31, when it should give a value between 32 and 63. This patch adds %S<n> that acts like %x<n>, except that it adds 1 to the register number. This is version 2 of the patch. The only difference is I made the test case simpler to read. I have tested this on power10 and power9 little endian systems and on a power9 big endian system. There were no regressions in the patch. Can I apply it to the trunk? It would be nice if I could apply it to the open branches. Can I backport it after a burn-in period? 2024-04-10 Michael Meissner <meiss...@linux.ibm.com> gcc/ PR target/112886 * config/rs6000/rs6000.cc (print_operand): Add %S<n> output modifier. * doc/md.texi (Modifiers): Mention %S can be used like %x. gcc/testsuite/ PR target/112886 * /gcc.target/powerpc/pr112886.c: New test. Diff: --- gcc/config/rs6000/rs6000.cc | 10 +++++++--- gcc/doc/md.texi | 5 +++-- gcc/testsuite/gcc.target/powerpc/pr112886.c | 29 +++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+), 5 deletions(-) diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc index 2921e72aea8..ec860c13074 100644 --- a/gcc/config/rs6000/rs6000.cc +++ b/gcc/config/rs6000/rs6000.cc @@ -14454,13 +14454,17 @@ print_operand (FILE *file, rtx x, int code) print_operand (file, x, 0); return; + case 'S': case 'x': - /* X is a FPR or Altivec register used in a VSX context. */ + /* X is a FPR or Altivec register used in a VSX context. %x<n> prints + the VSX register number, %S<n> prints the 2nd register number for + vector pair, decimal 128-bit floating and IBM 128-bit binary floating + values. */ if (!REG_P (x) || !VSX_REGNO_P (REGNO (x))) - output_operand_lossage ("invalid %%x value"); + output_operand_lossage ("invalid %%%c value", (code == 'S' ? 'S' : 'x')); else { - int reg = REGNO (x); + int reg = REGNO (x) + (code == 'S' ? 1 : 0); int vsx_reg = (FP_REGNO_P (reg) ? reg - 32 : reg - FIRST_ALTIVEC_REGNO + 32); diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index 5730bda80dc..7b7e6507754 100644 --- a/gcc/doc/md.texi +++ b/gcc/doc/md.texi @@ -3386,8 +3386,9 @@ A VSX register (VSR), @code{vs0}@dots{}@code{vs63}. This is either an FPR (@code{vs0}@dots{}@code{vs31} are @code{f0}@dots{}@code{f31}) or a VR (@code{vs32}@dots{}@code{vs63} are @code{v0}@dots{}@code{v31}). -When using @code{wa}, you should use the @code{%x} output modifier, so that -the correct register number is printed. For example: +When using @code{wa}, you should use either the @code{%x} or @code{%S} +output modifier, so that the correct register number is printed. For +example: @smallexample asm ("xvadddp %x0,%x1,%x2" diff --git a/gcc/testsuite/gcc.target/powerpc/pr112886.c b/gcc/testsuite/gcc.target/powerpc/pr112886.c new file mode 100644 index 00000000000..4e59dcda6ea --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr112886.c @@ -0,0 +1,29 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +/* PR target/112886: Test that print_operand %S<n> gives the correct register + number for VSX registers (i.e. if the register is an Altivec register, the + register number is 32..63 instead of 0..31. */ + +void +test (__vector_pair *ptr1, __vector_pair *ptr2, __vector_pair *ptr3) +{ + register __vector_pair p asm ("vs10"); + register __vector_pair q asm ("vs42"); + register __vector_pair r asm ("vs44"); + + q = *ptr2; + r = *ptr3; + + __asm__ ("xvadddp %x0,%x1,%x2\n\txvadddp %S0,%S1,%S2" + : "=wa" (p) + : "wa" (q), "wa" (r)); + + *ptr1 = p; +} + +/* { dg-final { scan-assembler-times {\mxvadddp 10,42,44\M} 1 } } */ +/* { dg-final { scan-assembler-times {\mxvadddp 11,43,45\M} 1 } } */ +/* { dg-final { scan-assembler-times {\mlxvpx?\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mstxvpx?\M} 1 } } */