The maximum size of the current op_by_pieces operations are limited by MAX_FIXED_MODE_SIZE which is an integer expression for the size in bits of the largest integer machine mode that should actually be used. But a target can use TImode/OImode/XImode, which can be larger than MAX_FIXED_MODE_SIZE, to perform op_by_pieces operations. Here are a set of patches to remove such limitation so that TImode/OImode/XImode can be used for piecewise move and store:
1. Remove MAX_FIXED_MODE_SIZE limit in alignment_for_piecewise_move. 2. Allow generating pseudo register with specific alignment for hard registers which will never be spilled onto stack to avoid re-aligning stack. 3. Add TARGET_READ_MEMSET_VALUE and TARGET_GEN_MEMSET_VALUE to support target instructions to duplicate QImode value to TImode/OImode/XImode value for memmset. 4. x86: Avoid stack realignment when copying data 5. x86: Remov MAX_BITSIZE_MODE_ANY_INT. Only x86 backend defines it. 6. x86: Use TImode/OImode/XImode integers for piecewise move and store. 7. x86: Add tests for TImode/OImode/XImode for piecewise move and store. 8. x86: Adjust existing tests. On x86-64, SPEC CPU 2017 performance impact is neutral. Glibc code size differences with -O2 build are: Before After libc.so 1870718 1870222 ld.so 185120 184984 Some code sequence differences in libc.so are: Before After mov 0x10(%rsp),%edx mov 0x10(%rsp),%edx mov %edx,(%rax) mov %edx,(%rax) movzwl 0x14(%rsp),%edx | mov 0x13(%rsp),%edx mov %dx,0x4(%rax) | mov %edx,0x3(%rax) movzbl 0x16(%rsp),%edx < mov %dl,0x6(%rax) < add %rcx,%rax add %rcx,%rax ret ret movdqu (%rsi),%xmm1 | movdqu (%rcx),%xmm1 mov %rdi,0x20(%rsp) mov %rdi,0x20(%rsp) movups %xmm1,(%rax) movups %xmm1,(%rax) mov 0x10(%rsi),%rdx | movdqu 0xc(%rcx),%xmm2 mov %rdx,0x10(%rax) | movups %xmm2,0xc(%rax) mov 0x18(%rsi),%edx | mov %rax,(%r14,%rdx,8) mov %edx,0x18(%rax) | add $0x1,%rdx mov %rax,(%r14,%rcx,8) | cmp %r8,%rdx add $0x1,%rcx | je <__resolv_conf_allocate+0x22d> cmp %r8,%rcx | mov 0x20(%rsp),%rsi je <__resolv_conf_allocate+0x22f> | mov (%r9,%rdx,8),%rcx test %eax,%eax test %eax,%eax mov $0xff,%eax mov $0xff,%eax cmove %eax,%ebx cmove %eax,%ebx movzbl %bl,%ecx | movd %ebx,%xmm0 mov %ebx,0xc(%rsp) mov %ebx,0xc(%rsp) mov %rcx,%rax | punpcklbw %xmm0,%xmm0 mov %rcx,%rsi | punpcklwd %xmm0,%xmm0 mul %rdi | pshufd $0x0,%xmm0,%xmm0 imul %rdi,%rsi | movups %xmm0,0x50(%r12) mov %rax,0x50(%r12) | movups %xmm0,0x60(%r12) mov %rcx,%rax | movups %xmm0,0x70(%r12) add %rdx,%rsi | movups %xmm0,0x80(%r12) mul %rdi | movups %xmm0,0x90(%r12) mov %rsi,0x58(%r12) | movups %xmm0,0xa0(%r12) mov %rsi,0x68(%r12) | movups %xmm0,0xb0(%r12) mov %rax,0x60(%r12) | movups %xmm0,0xc0(%r12) mov %rcx,%rax | movups %xmm0,0xd0(%r12) mul %rdi | movups %xmm0,0xe0(%r12) mov %rsi,0x78(%r12) | movups %xmm0,0xf0(%r12) mov %rsi,0x88(%r12) | movups %xmm0,0x100(%r12) mov %rsi,0x98(%r12) | movups %xmm0,0x110(%r12) mov %rax,0x70(%r12) | movups %xmm0,0x120(%r12) mov %rcx,%rax | movups %xmm0,0x130(%r12) mul %rdi | movups %xmm0,0x140(%r12) mov %rsi,0xa8(%r12) < mov %rsi,0xb8(%r12) < mov %rsi,0xc8(%r12) < mov %rax,0x80(%r12) < mov %rcx,%rax < mul %rdi < mov %rsi,0xd8(%r12) < mov %rsi,0xe8(%r12) < mov %rsi,0xf8(%r12) < mov %rax,0x90(%r12) < mov %rcx,%rax < mul %rdi < mov %rsi,0x108(%r12) < mov %rsi,0x118(%r12) < mov %rsi,0x128(%r12) < mov %rax,0xa0(%r12) < mov %rcx,%rax < mul %rdi < mov %rsi,0x138(%r12) < mov %rax,0xb0(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0xc0(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0xd0(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0xe0(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0xf0(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0x100(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0x110(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0x120(%r12) < mov %rcx,%rax < mul %rdi < mov %rax,0x130(%r12) < mov %rcx,%rax < mul %rdi < mov %r12,%rdi < mov %rax,0x140(%r12) < mov %rsi,0x148(%r12) < call <xprt_register@GLIBC_2.2.5> call <xprt_register@GLIBC_2.2.5> add $0x28,%rsp add $0x28,%rsp mov %r12,%rax mov %r12,%rax pop %rbx pop %rbx pop %rbp pop %rbp pop %r12 pop %r12 pop %r13 pop %r13 pop %r14 pop %r14 pop %r15 pop %r15 ret ret H.J. Lu (12): Update alignment_for_piecewise_move Allow generating pseudo register with specific alignment Add TARGET_READ_MEMSET_VALUE/TARGET_GEN_MEMSET_VALUE x86: Avoid stack realignment when copying data Remove MAX_BITSIZE_MODE_ANY_INT x86: Update piecewise move and store x86: Add AVX2 tests for PR middle-end/90773 x86: Add tests for piecewise move and store x86: Also pass -mno-avx to pr72839.c x86: Also pass -mno-avx to cold-attribute-1.c x86: Also pass -mno-avx to sw-1.c for ia32 x86: Update gcc.target/i386/incoming-11.c gcc/builtins.c | 45 +-- gcc/config/i386/i386-expand.c | 9 +- gcc/config/i386/i386-modes.def | 15 +- gcc/config/i386/i386-protos.h | 2 + gcc/config/i386/i386.c | 257 +++++++++++++++++- gcc/config/i386/i386.h | 31 ++- gcc/doc/tm.texi | 16 ++ gcc/doc/tm.texi.in | 4 + gcc/emit-rtl.c | 5 +- gcc/explow.c | 6 +- gcc/explow.h | 2 +- gcc/expr.c | 13 +- gcc/expr.h | 6 +- gcc/rtl.h | 2 +- gcc/target.def | 20 ++ gcc/targhooks.c | 54 ++++ gcc/targhooks.h | 4 + .../gcc.target/i386/cold-attribute-1.c | 2 +- gcc/testsuite/gcc.target/i386/incoming-11.c | 2 +- .../gcc.target/i386/pieces-memcpy-10.c | 16 ++ .../gcc.target/i386/pieces-memcpy-11.c | 17 ++ .../gcc.target/i386/pieces-memcpy-12.c | 16 ++ .../gcc.target/i386/pieces-memcpy-13.c | 16 ++ .../gcc.target/i386/pieces-memcpy-14.c | 17 ++ .../gcc.target/i386/pieces-memcpy-15.c | 16 ++ .../gcc.target/i386/pieces-memcpy-16.c | 16 ++ .../gcc.target/i386/pieces-memcpy-7.c | 15 + .../gcc.target/i386/pieces-memcpy-8.c | 14 + .../gcc.target/i386/pieces-memcpy-9.c | 14 + .../gcc.target/i386/pieces-memset-1.c | 16 ++ .../gcc.target/i386/pieces-memset-10.c | 16 ++ .../gcc.target/i386/pieces-memset-11.c | 16 ++ .../gcc.target/i386/pieces-memset-12.c | 16 ++ .../gcc.target/i386/pieces-memset-13.c | 16 ++ .../gcc.target/i386/pieces-memset-14.c | 16 ++ .../gcc.target/i386/pieces-memset-15.c | 16 ++ .../gcc.target/i386/pieces-memset-16.c | 16 ++ .../gcc.target/i386/pieces-memset-17.c | 16 ++ .../gcc.target/i386/pieces-memset-18.c | 16 ++ .../gcc.target/i386/pieces-memset-19.c | 17 ++ .../gcc.target/i386/pieces-memset-2.c | 12 + .../gcc.target/i386/pieces-memset-20.c | 17 ++ .../gcc.target/i386/pieces-memset-21.c | 17 ++ .../gcc.target/i386/pieces-memset-22.c | 17 ++ .../gcc.target/i386/pieces-memset-23.c | 17 ++ .../gcc.target/i386/pieces-memset-24.c | 17 ++ .../gcc.target/i386/pieces-memset-25.c | 17 ++ .../gcc.target/i386/pieces-memset-26.c | 17 ++ .../gcc.target/i386/pieces-memset-27.c | 17 ++ .../gcc.target/i386/pieces-memset-28.c | 17 ++ .../gcc.target/i386/pieces-memset-29.c | 17 ++ .../gcc.target/i386/pieces-memset-3.c | 18 ++ .../gcc.target/i386/pieces-memset-30.c | 17 ++ .../gcc.target/i386/pieces-memset-31.c | 17 ++ .../gcc.target/i386/pieces-memset-32.c | 17 ++ .../gcc.target/i386/pieces-memset-33.c | 17 ++ .../gcc.target/i386/pieces-memset-34.c | 17 ++ .../gcc.target/i386/pieces-memset-35.c | 17 ++ .../gcc.target/i386/pieces-memset-36.c | 17 ++ .../gcc.target/i386/pieces-memset-37.c | 15 + .../gcc.target/i386/pieces-memset-38.c | 17 ++ .../gcc.target/i386/pieces-memset-39.c | 16 ++ .../gcc.target/i386/pieces-memset-4.c | 16 ++ .../gcc.target/i386/pieces-memset-40.c | 17 ++ .../gcc.target/i386/pieces-memset-41.c | 16 ++ .../gcc.target/i386/pieces-memset-42.c | 17 ++ .../gcc.target/i386/pieces-memset-43.c | 17 ++ .../gcc.target/i386/pieces-memset-5.c | 12 + .../gcc.target/i386/pieces-memset-6.c | 16 ++ .../gcc.target/i386/pieces-memset-7.c | 16 ++ .../gcc.target/i386/pieces-memset-8.c | 16 ++ .../gcc.target/i386/pieces-memset-9.c | 16 ++ gcc/testsuite/gcc.target/i386/pr72839.c | 2 +- gcc/testsuite/gcc.target/i386/pr90773-1.c | 10 +- gcc/testsuite/gcc.target/i386/pr90773-14.c | 2 +- gcc/testsuite/gcc.target/i386/pr90773-15.c | 14 + gcc/testsuite/gcc.target/i386/pr90773-16.c | 14 + gcc/testsuite/gcc.target/i386/pr90773-17.c | 14 + gcc/testsuite/gcc.target/i386/pr90773-18.c | 15 + gcc/testsuite/gcc.target/i386/pr90773-19.c | 14 + gcc/testsuite/gcc.target/i386/pr90773-20.c | 13 + gcc/testsuite/gcc.target/i386/pr90773-21.c | 13 + gcc/testsuite/gcc.target/i386/pr90773-22.c | 13 + gcc/testsuite/gcc.target/i386/pr90773-23.c | 13 + gcc/testsuite/gcc.target/i386/pr90773-4.c | 2 +- gcc/testsuite/gcc.target/i386/sw-1.c | 1 + 86 files changed, 1404 insertions(+), 91 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-10.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-11.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-12.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-13.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-14.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-15.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-16.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-7.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-8.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memcpy-9.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-1.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-10.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-11.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-12.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-13.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-14.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-15.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-16.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-17.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-18.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-19.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-2.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-20.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-21.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-22.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-23.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-24.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-25.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-26.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-27.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-28.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-29.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-3.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-30.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-31.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-32.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-33.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-34.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-35.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-36.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-37.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-38.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-39.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-4.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-40.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-41.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-42.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-43.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-5.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-6.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-7.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-8.c create mode 100644 gcc/testsuite/gcc.target/i386/pieces-memset-9.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-15.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-16.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-17.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-18.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-19.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-20.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-21.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-22.c create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-23.c -- 2.31.1