x86: Update -mtune=tremont
Commit Message
Hi Uros,
This patch is to update mtune for tremont.
Bootstrap is ok, and no regressions for i386/x86-64 testsuite.
OK for master?
Silvermont has a special handle in add_stmt_cost function, because it has in
order SIMD pipeline. But for Tremont, its SIMD pipeline is out of order,
remove Tremont from this special handle.
gcc/ChangeLog
* config/i386/i386.c (ix86_vector_costs::add_stmt_cost): Remove Tremont.
---
gcc/config/i386/i386.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
Comments
On Thu, Dec 9, 2021 at 7:59 AM Cui,Lili <lili.cui@intel.com> wrote:
>
> Hi Uros,
>
> This patch is to update mtune for tremont.
>
> Bootstrap is ok, and no regressions for i386/x86-64 testsuite.
>
> OK for master?
OK.
Thanks,
Uros.
>
>
> Silvermont has a special handle in add_stmt_cost function, because it has in
> order SIMD pipeline. But for Tremont, its SIMD pipeline is out of order,
> remove Tremont from this special handle.
>
> gcc/ChangeLog
>
> * config/i386/i386.c (ix86_vector_costs::add_stmt_cost): Remove Tremont.
> ---
> gcc/config/i386/i386.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index f1e41fd55f9..9f4ed34ffd5 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -23144,8 +23144,7 @@ ix86_vector_costs::add_stmt_cost (int count, vect_cost_for_stmt kind,
> for Silvermont as it has out of order integer pipeline and can execute
> 2 scalar instruction per tick, but has in order SIMD pipeline. */
> if ((TARGET_CPU_P (SILVERMONT) || TARGET_CPU_P (GOLDMONT)
> - || TARGET_CPU_P (GOLDMONT_PLUS) || TARGET_CPU_P (TREMONT)
> - || TARGET_CPU_P (INTEL))
> + || TARGET_CPU_P (GOLDMONT_PLUS) || TARGET_CPU_P (INTEL))
> && stmt_info && stmt_info->stmt)
> {
> tree lhs_op = gimple_get_lhs (stmt_info->stmt);
> --
> 2.17.1
>
> Thanks,
> Lili.
@@ -23144,8 +23144,7 @@ ix86_vector_costs::add_stmt_cost (int count, vect_cost_for_stmt kind,
for Silvermont as it has out of order integer pipeline and can execute
2 scalar instruction per tick, but has in order SIMD pipeline. */
if ((TARGET_CPU_P (SILVERMONT) || TARGET_CPU_P (GOLDMONT)
- || TARGET_CPU_P (GOLDMONT_PLUS) || TARGET_CPU_P (TREMONT)
- || TARGET_CPU_P (INTEL))
+ || TARGET_CPU_P (GOLDMONT_PLUS) || TARGET_CPU_P (INTEL))
&& stmt_info && stmt_info->stmt)
{
tree lhs_op = gimple_get_lhs (stmt_info->stmt);