From: Jakub Jelinek Date: Sat, 8 Feb 2020 09:59:40 +0000 (+0100) Subject: i386: Make xmm16-xmm31 call used even in ms ABI [PR65782] X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=79ab8c4321b2dc940bb706a7432a530e26f0df1a;p=gcc.git i386: Make xmm16-xmm31 call used even in ms ABI [PR65782] On Tue, Feb 04, 2020 at 11:16:06AM +0100, Uros Bizjak wrote: > I guess that Comment #9 patch form the PR should be trivially correct, > but althouhg it looks obvious, I don't want to propose the patch since > I have no means of testing it. I don't have means of testing it either. https://docs.microsoft.com/en-us/cpp/build/x64-calling-convention?view=vs-2019 is quite explicit that [xyz]mm16-31 are call clobbered and only xmm6-15 (low 128-bits only) are call preserved. We are talking e.g. about /* { dg-options "-O2 -mabi=ms -mavx512vl" } */ typedef double V __attribute__((vector_size (16))); void foo (void); V bar (void); void baz (V); void qux (void) { V c; { register V a __asm ("xmm18"); V b = bar (); asm ("" : "=x" (a) : "0" (b)); c = a; } foo (); { register V d __asm ("xmm18"); V e; d = c; asm ("" : "=x" (e) : "0" (d)); baz (e); } } where according to the MSDN doc gcc incorrectly holds the c value in xmm18 register across the foo call; if foo is compiled by some Microsoft compiler (or LLVM), then it could clobber %xmm18. If all xmm18 occurrences are changed to say xmm15, then it is valid to hold the 128-bit value across the foo call (though, surprisingly, LLVM saves it into stack anyway). The other parts are I guess mainly about SEH. Consider e.g. void foo (void) { register double x __asm ("xmm14"); register double y __asm ("xmm18"); asm ("" : "=x" (x)); asm ("" : "=v" (y)); x += y; y += x; asm ("" : : "x" (x)); asm ("" : : "v" (y)); } looking at cross-compiler output, with -O2 -mavx512f this emits .file "abcdeq.c" .text .align 16 .globl foo .def foo; .scl 2; .type 32; .endef .seh_proc foo foo: subq $40, %rsp .seh_stackalloc 40 vmovaps %xmm14, (%rsp) .seh_savexmm %xmm14, 0 vmovaps %xmm18, 16(%rsp) .seh_savexmm %xmm18, 16 .seh_endprologue vaddsd %xmm18, %xmm14, %xmm14 vaddsd %xmm18, %xmm14, %xmm18 vmovaps (%rsp), %xmm14 vmovaps 16(%rsp), %xmm18 addq $40, %rsp ret .seh_endproc .ident "GCC: (GNU) 10.0.1 20200207 (experimental)" Does whatever assembler mingw64 uses even assemble this (I mean the .seh_savexmm %xmm16, 16 could be problematic)? I can find e.g. https://stackoverflow.com/questions/43152633/invalid-register-for-seh-savexmm-in-cygwin/43210527 which then links to https://gcc.gnu.org/PR65782 2020-02-08 Uroš Bizjak Jakub Jelinek PR target/65782 * config/i386/i386.h (CALL_USED_REGISTERS): Make xmm16-xmm31 call-used even in 64-bit ms-abi. * gcc.target/i386/pr65782.c: New test. Co-authored-by: Uroš Bizjak --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index d255bd9ea13..ed3aac49f1b 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,10 @@ +2020-02-08 UroÅ¡ Bizjak + Jakub Jelinek + + PR target/65782 + * config/i386/i386.h (CALL_USED_REGISTERS): Make + xmm16-xmm31 call-used even in 64-bit ms-abi. + 2020-02-07 Dennis Zhang * config/aarch64/aarch64-simd-builtins.def (simd_smmla): New entry. diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h index 943e9a5c783..98235f75a9e 100644 --- a/gcc/config/i386/i386.h +++ b/gcc/config/i386/i386.h @@ -1128,9 +1128,9 @@ extern const char *host_detect_local_cpu (int argc, const char **argv); /*xmm8,xmm9,xmm10,xmm11,xmm12,xmm13,xmm14,xmm15*/ \ 6, 6, 6, 6, 6, 6, 6, 6, \ /*xmm16,xmm17,xmm18,xmm19,xmm20,xmm21,xmm22,xmm23*/ \ - 6, 6, 6, 6, 6, 6, 6, 6, \ + 1, 1, 1, 1, 1, 1, 1, 1, \ /*xmm24,xmm25,xmm26,xmm27,xmm28,xmm29,xmm30,xmm31*/ \ - 6, 6, 6, 6, 6, 6, 6, 6, \ + 1, 1, 1, 1, 1, 1, 1, 1, \ /* k0, k1, k2, k3, k4, k5, k6, k7*/ \ 1, 1, 1, 1, 1, 1, 1, 1 } diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 63836b9a44e..149996686b5 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,9 @@ +2020-02-08 UroÅ¡ Bizjak + Jakub Jelinek + + PR target/65782 + * gcc.target/i386/pr65782.c: New test. + 2020-02-07 Marek Polacek PR c++/92947 - Paren init of aggregates in unevaluated context. diff --git a/gcc/testsuite/gcc.target/i386/pr65782.c b/gcc/testsuite/gcc.target/i386/pr65782.c new file mode 100644 index 00000000000..298dca1be97 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr65782.c @@ -0,0 +1,16 @@ +/* PR target/65782 */ +/* { dg-do assemble { target { avx512vl && { ! ia32 } } } } */ +/* { dg-options "-O2 -mavx512vl" } */ + +void +foo (void) +{ + register double x __asm ("xmm14"); + register double y __asm ("xmm18"); + asm ("" : "=x" (x)); + asm ("" : "=v" (y)); + x += y; + y += x; + asm ("" : : "x" (x)); + asm ("" : : "v" (y)); +}