Handle FMA friendly in reassoc pass

Make some changes in reassoc pass to make it more friendly to fma pass later.
Using FMA instead of mult + add reduces register pressure and insruction
retired.

There are mainly two changes
1. Put no-mult ops and mult ops alternately at the end of the queue, which is
conducive to generating more fma and reducing the loss of FMA when breaking
the chain.
2. Rewrite the rewrite_expr_tree_parallel function to try to build parallel
chains according to the given correlation width, keeping the FMA chance as
much as possible.

With the patch applied

On ICX:
507.cactuBSSN_r: Improved by 1.7% for multi-copy .
503.bwaves_r   : Improved by  0.60% for single copy .
507.cactuBSSN_r: Improved by  1.10% for single copy .
519.lbm_r      : Improved by  2.21% for single copy .
no measurable changes for other benchmarks.

On aarch64
507.cactuBSSN_r: Improved by 1.7% for multi-copy.
503.bwaves_r   : Improved by 6.00% for single-copy.
no measurable changes for other benchmarks.

TEST1:

float
foo (float a, float b, float c, float d, float *e)
{
   return  *e  + a * b + c * d ;
}

For "-Ofast -mfpmath=sse -mfma" GCC generates:
        vmulss  %xmm3, %xmm2, %xmm2
        vfmadd132ss     %xmm1, %xmm2, %xmm0
        vaddss  (%rdi), %xmm0, %xmm0
        ret

With this patch GCC generates:
        vfmadd213ss   (%rdi), %xmm1, %xmm0
        vfmadd231ss   %xmm2, %xmm3, %xmm0
        ret

TEST2:

for (int i = 0; i < N; i++)
{
  a[i] += b[i]* c[i] + d[i] * e[i] + f[i] * g[i] + h[i] * j[i] + k[i] * l[i] + m[i]* o[i] + p[i];
}

For "-Ofast -mfpmath=sse -mfma"  GCC generates:
	vmovapd e(%rax), %ymm4
	vmulpd  d(%rax), %ymm4, %ymm3
	addq    $32, %rax
	vmovapd c-32(%rax), %ymm5
	vmovapd j-32(%rax), %ymm6
	vmulpd  h-32(%rax), %ymm6, %ymm2
	vmovapd a-32(%rax), %ymm6
	vaddpd  p-32(%rax), %ymm6, %ymm0
	vmovapd g-32(%rax), %ymm7
	vfmadd231pd     b-32(%rax), %ymm5, %ymm3
	vmovapd o-32(%rax), %ymm4
	vmulpd  m-32(%rax), %ymm4, %ymm1
	vmovapd l-32(%rax), %ymm5
	vfmadd231pd     f-32(%rax), %ymm7, %ymm2
	vfmadd231pd     k-32(%rax), %ymm5, %ymm1
	vaddpd  %ymm3, %ymm0, %ymm0
	vaddpd  %ymm2, %ymm0, %ymm0
	vaddpd  %ymm1, %ymm0, %ymm0
	vmovapd %ymm0, a-32(%rax)
	cmpq    $8192, %rax
	jne     .L4
	vzeroupper
	ret

with this patch applied GCC breaks the chain with width = 2 and generates 6 fma:

	vmovapd a(%rax), %ymm2
	vmovapd c(%rax), %ymm0
	addq    $32, %rax
	vmovapd e-32(%rax), %ymm1
	vmovapd p-32(%rax), %ymm5
	vmovapd g-32(%rax), %ymm3
	vmovapd j-32(%rax), %ymm6
	vmovapd l-32(%rax), %ymm4
	vmovapd o-32(%rax), %ymm7
	vfmadd132pd     b-32(%rax), %ymm2, %ymm0
	vfmadd132pd     d-32(%rax), %ymm5, %ymm1
	vfmadd231pd     f-32(%rax), %ymm3, %ymm0
	vfmadd231pd     h-32(%rax), %ymm6, %ymm1
	vfmadd231pd     k-32(%rax), %ymm4, %ymm0
	vfmadd231pd     m-32(%rax), %ymm7, %ymm1
	vaddpd  %ymm1, %ymm0, %ymm0
	vmovapd %ymm0, a-32(%rax)
	cmpq    $8192, %rax
	jne     .L2
	vzeroupper
	ret

gcc/ChangeLog:

	PR tree-optimization/98350
	* tree-ssa-reassoc.cc
	(rewrite_expr_tree_parallel): Rewrite this function.
	(rank_ops_for_fma): New.
	(reassociate_bb): Handle new function.

gcc/testsuite/ChangeLog:

	PR tree-optimization/98350
	* gcc.dg/pr98350-1.c: New test.
	* gcc.dg/pr98350-2.c: Ditto.

0 files changed, 0 insertions, 0 deletions