procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Disparage slightly for the alternative which move DFmode between SSE_REGS and GENERAL_REGS.

Browse source 
For testcase

void __cond_swap(double* __x, double* __y) {
  bool __r = (*__x < *__y);
  auto __tmp = __r ? *__x : *__y;
  *__y = __r ? *__y : *__x;
  *__x = __tmp;
}

GCC-14 with -O2 and -march=x86-64 options generates the following code:

__cond_swap(double*, double*):
        movsd   xmm1, QWORD PTR [rdi]
        movsd   xmm0, QWORD PTR [rsi]
        comisd  xmm0, xmm1
        jbe     .L2
        movq    rax, xmm1
        movapd  xmm1, xmm0
        movq    xmm0, rax
.L2:
        movsd   QWORD PTR [rsi], xmm1
        movsd   QWORD PTR [rdi], xmm0
        ret

rax is used to save and restore DFmode value. In RA both GENERAL_REGS
and SSE_REGS cost zero since we didn't disparage the
alternative in movdf_internal pattern, according to register
allocation order, GENERAL_REGS is allocated. The patch add ? for
alternative (r,v) and (v,r) just like we did for movsf/hf/bf_internal
pattern, after that we get optimal RA.

__cond_swap:
.LFB0:
	.cfi_startproc
	movsd	(%rdi), %xmm1
	movsd	(%rsi), %xmm0
	comisd	%xmm1, %xmm0
	jbe	.L2
	movapd	%xmm1, %xmm2
	movapd	%xmm0, %xmm1
	movapd	%xmm2, %xmm0
.L2:
	movsd	%xmm1, (%rsi)
	movsd	%xmm0, (%rdi)
	ret

gcc/ChangeLog:

	PR target/110170
	* config/i386/i386.md (movdf_internal): Disparage slightly for
	2 alternatives (r,v) and (v,r) by adding constraint modifier
	'?'.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr110170-3.c: New test.
This commit is contained in:
liuhongt 2023-07-05 13:45:11 +08:00
parent 1669fad496
commit 37a231cc75
2 changed files with 13 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
gcc/config/i386/i386.md
View file

@ -3915,9 +3915,9 @@
;; Possible store forwarding (partial memory) stall in alternatives 4, 6 and 7.
(define_insn "*movdf_internal"
[(set (match_operand:DF 0 "nonimmediate_operand"
"=Yf*f,m ,Yf*f,?r ,!o,?*r ,!o,!o,?r,?m,?r,?r,v,v,v,m,*x,*x,*x,m ,r ,v,r ,o ,r ,m")
"=Yf*f,m ,Yf*f,?r ,!o,?*r ,!o,!o,?r,?m,?r,?r,v,v,v,m,*x,*x,*x,m ,?r,?v,r ,o ,r ,m")
(match_operand:DF 1 "general_operand"
"Yf*fm,Yf*f,G ,roF,r ,*roF,*r,F ,rm,rC,C ,F ,C,v,m,v,C ,*x,m ,*x,v,r ,roF,rF,rmF,rC"))]
"Yf*fm,Yf*f,G ,roF,r ,*roF,*r,F ,rm,rC,C ,F ,C,v,m,v,C ,*x,m ,*x, v, r,roF,rF,rmF,rC"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (lra_in_progress || reload_completed
|| !CONST_DOUBLE_P (operands[1])

11
gcc/testsuite/gcc.target/i386/pr110170-3.c Normal file
View file

@ -0,0 +1,11 @@
/* { dg-do compile { target { ! ia32 } } } */
/* { dg-options "-O2 -fno-if-conversion -fno-if-conversion2" } */
/* { dg-final { scan-assembler-not {(?n)movq.*r} } } */
void __cond_swap(double* __x, double* __y) {
_Bool __r = (*__x < *__y);
double __tmp = __r ? *__x : *__y;
*__y = __r ? *__y : *__x;
*__x = __tmp;
}