I didn't receive
https://gcc.gnu.org/pipermail/gcc-patches/2021-June/572436.html in my
gmail account, does anyone know why?
>--- a/gcc/config/i386/i386-protos.h
>+++ b/gcc/config/i386/i386-protos.h
>@@ -260,6 +260,7 @@ extern void ix86_expand_mul_widen_hilo (rtx, rtx, rtx,
>bool, bool);
> extern void ix86_expand_sse2_mulv4si3 (rtx, rtx, rtx);
> extern void ix86_expand_sse2_mulvxdi3 (rtx, rtx, rtx);
> extern void ix86_expand_sse2_abs (rtx, rtx);
>+extern bool ix86_expand_integer_vec_duplicate (rtx *);
>
> /* In i386-c.c */
> extern void ix86_target_macros (void);
>diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
>index 2a34756be2a..f094e5a2586 100644
>--- a/gcc/config/i386/sse.md
>+++ b/gcc/config/i386/sse.md
>@@ -24570,3 +24570,24 @@
> "TARGET_WIDEKL"
> "aes<aeswideklvariant>\t{%0}"
> [(set_attr "type" "other")])
>+
>+;; Modes handled by broadcast patterns.
>+(define_mode_iterator INT_BROADCAST_MODE
>+ [(V64QI "TARGET_AVX512F") (V32QI "TARGET_AVX") V16QI
>+ (V32HI "TARGET_AVX512F") (V16HI "TARGET_AVX") V8HI
>+ (V16SI "TARGET_AVX512F") (V8SI "TARGET_AVX") V4SI
>+ (V8DI "TARGET_AVX512F && TARGET_64BIT")
>+ (V4DI "TARGET_AVX && TARGET_64BIT") (V2DI "TARGET_64BIT")])
TARGET_AVX512BW is needed for V64QI and V32HImode.
And consider the scenario, TARGET_AVX2 is needed for all other
128/256-bit modes?
>+
>+;; Broadcast from an integer. NB: Enable broadcast only if we can move
>+;; from GPR to SSE register directly.
>+(define_expand "vec_duplicate<mode>"
>+ [(set (match_operand:INT_BROADCAST_MODE 0 "register_operand")
>+ (vec_duplicate:INT_BROADCAST_MODE
>+ (match_operand:<ssescalarmode> 1 "general_operand")))]
>+ "TARGET_SSE2 && TARGET_INTER_UNIT_MOVES_TO_VEC"
Why not directly use TARGET_AVX2 here, not in ix86_expand_integer_vec_duplicate.
Also define some predicate to restrict operand[1] to be const_int but
not const0_rtx and constm1_rtx.
w/ this, guess there's no need for FAIL? and you can directly
call ix86_expand_vector_init_duplicate.
>+{
>+ if (!ix86_expand_integer_vec_duplicate (operands))
>+ FAIL;
>+ DONE;
>
On Fri, Jun 25, 2021 at 1:30 AM H.J. Lu via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> On Wed, Jun 9, 2021 at 4:39 PM H.J. Lu <hjl.to...@gmail.com> wrote:
> >
> > 1. Update move expanders to convert the CONST_WIDE_INT and CONST_VECTO
> > operands to vector broadcast from an integer with AVX2.
> > 2. Add ix86_gen_scratch_sse_rtx to return a scratch SSE register which
> > won't increase stack alignment requirement and blocks transformation by
> > the combine pass.
> >
> > A small benchmark:
> >
> > https://gitlab.com/x86-benchmarks/microbenchmark/-/tree/memset/broadcast
> >
> > shows that broadcast is a little bit faster on Intel Core i7-8559U:
> >
> > $ make
> > gcc -g -I. -O2 -c -o test.o test.c
> > gcc -g -c -o memory.o memory.S
> > gcc -g -c -o broadcast.o broadcast.S
> > gcc -g -c -o vec_dup_sse2.o vec_dup_sse2.S
> > gcc -o test test.o memory.o broadcast.o vec_dup_sse2.o
> > ./test
> > memory : 147215
> > broadcast : 121213
> > vec_dup_sse2: 171366
> > $
> >
> > broadcast is also smaller:
> >
> > $ size memory.o broadcast.o
> > text data bss dec hex filename
> > 132 0 0 132 84 memory.o
> > 122 0 0 122 7a broadcast.o
> > $
> >
> > 3. Update PR 87767 tests to expect integer broadcast instead of broadcast
> > from memory.
> > 4. Update avx512f_cond_move.c to expect integer broadcast.
> >
> > A small benchmark:
> >
> > https://gitlab.com/x86-benchmarks/microbenchmark/-/tree/vpaddd/broadcast
> >
> > shows that integer broadcast is faster than embedded memory broadcast:
> >
> > $ make
> > gcc -g -I. -O2 -march=skylake-avx512 -c -o test.o test.c
> > gcc -g -c -o memory.o memory.S
> > gcc -g -c -o broadcast.o broadcast.S
> > gcc -o test test.o memory.o broadcast.o
> > ./test
> > memory : 425538
> > broadcast : 375260
> > $
> >
> > 5. Update vec_duplicate to allow to fail so that backend can only allow
> > broadcasting an integer constant to a vector when broadcast instruction
> > is available. This can be used by memset expander to avoid vec_duplicate
> > when loading from constant pool is more efficient.
> > 6. Add vec_duplicate<mode> expander and enable vec_duplicate from a
> > non-standard SSE constant integer only if vector broadcast is available.
> >
> > H.J. Lu (2):
> > x86: Convert CONST_WIDE_INT/CONST_VECTOR to broadcast
> > x86: Add vec_duplicate<mode> expander
> >
> > gcc/config/i386/i386-expand.c | 208 +++++++++++++++++-
> > gcc/config/i386/i386-protos.h | 3 +
> > gcc/config/i386/i386.c | 13 ++
> > gcc/config/i386/sse.md | 21 ++
> > gcc/doc/md.texi | 2 -
> > .../i386/avx512f-broadcast-pr87767-1.c | 7 +-
> > .../i386/avx512f-broadcast-pr87767-5.c | 5 +-
> > .../gcc.target/i386/avx512f_cond_move.c | 4 +-
> > .../i386/avx512vl-broadcast-pr87767-1.c | 12 +-
> > .../i386/avx512vl-broadcast-pr87767-5.c | 9 +-
> > gcc/testsuite/gcc.target/i386/pr100865-1.c | 13 ++
> > gcc/testsuite/gcc.target/i386/pr100865-10a.c | 33 +++
> > gcc/testsuite/gcc.target/i386/pr100865-10b.c | 7 +
> > gcc/testsuite/gcc.target/i386/pr100865-11a.c | 23 ++
> > gcc/testsuite/gcc.target/i386/pr100865-11b.c | 8 +
> > gcc/testsuite/gcc.target/i386/pr100865-12a.c | 20 ++
> > gcc/testsuite/gcc.target/i386/pr100865-12b.c | 8 +
> > gcc/testsuite/gcc.target/i386/pr100865-2.c | 14 ++
> > gcc/testsuite/gcc.target/i386/pr100865-3.c | 15 ++
> > gcc/testsuite/gcc.target/i386/pr100865-4a.c | 16 ++
> > gcc/testsuite/gcc.target/i386/pr100865-4b.c | 9 +
> > gcc/testsuite/gcc.target/i386/pr100865-5a.c | 16 ++
> > gcc/testsuite/gcc.target/i386/pr100865-5b.c | 9 +
> > gcc/testsuite/gcc.target/i386/pr100865-6a.c | 16 ++
> > gcc/testsuite/gcc.target/i386/pr100865-6b.c | 9 +
> > gcc/testsuite/gcc.target/i386/pr100865-7a.c | 17 ++
> > gcc/testsuite/gcc.target/i386/pr100865-7b.c | 9 +
> > gcc/testsuite/gcc.target/i386/pr100865-8a.c | 24 ++
> > gcc/testsuite/gcc.target/i386/pr100865-8b.c | 7 +
> > gcc/testsuite/gcc.target/i386/pr100865-9a.c | 25 +++
> > gcc/testsuite/gcc.target/i386/pr100865-9b.c | 7 +
> > 31 files changed, 563 insertions(+), 26 deletions(-)
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-1.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-10a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-10b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-11a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-11b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-12a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-12b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-2.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-3.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-4a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-4b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-5a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-5b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-6a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-6b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-7a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-7b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-8a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-8b.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-9a.c
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr100865-9b.c
> >
> > --
> > 2.31.1
> >
>
> PING^1.
>
> --
> H.J.
--
BR,
Hongtao
