* [PATCH 1/2] Re-format zen memcpy/memset costs.
@ 2020-06-01 11:35 Martin Liška
2020-07-29 15:42 ` Jan Hubicka
0 siblings, 1 reply; 2+ messages in thread
From: Martin Liška @ 2020-06-01 11:35 UTC (permalink / raw)
To: gcc-patches; +Cc: amonakov, ubizjak
The patch improves readability of the memcpy and memset
expansion strategies.
gcc/ChangeLog:
* config/i386/x86-tune-costs.h: Change code formatting.
---
gcc/config/i386/x86-tune-costs.h | 38 +++++++++++++++++++++++---------
1 file changed, 28 insertions(+), 10 deletions(-)
diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
index c73917e5a62..1169178433f 100644
--- a/gcc/config/i386/x86-tune-costs.h
+++ b/gcc/config/i386/x86-tune-costs.h
@@ -1311,14 +1311,23 @@ const struct processor_costs bdver_cost = {
very small blocks it is better to use loop. For large blocks, libcall
can do nontemporary accesses and beat inline considerably. */
static stringop_algs znver1_memcpy[2] = {
- {libcall, {{6, loop, false}, {14, unrolled_loop, false},
+ /* 32-bit tuning. */
+ {libcall, {{6, loop, false},
+ {14, unrolled_loop, false},
{-1, rep_prefix_4_byte, false}}},
- {libcall, {{16, loop, false}, {8192, rep_prefix_8_byte, false},
+ /* 64-bit tuning. */
+ {libcall, {{16, loop, false},
+ {8192, rep_prefix_8_byte, false},
{-1, libcall, false}}}};
static stringop_algs znver1_memset[2] = {
- {libcall, {{8, loop, false}, {24, unrolled_loop, false},
- {2048, rep_prefix_4_byte, false}, {-1, libcall, false}}},
- {libcall, {{48, unrolled_loop, false}, {8192, rep_prefix_8_byte, false},
+ /* 32-bit tuning. */
+ {libcall, {{8, loop, false},
+ {24, unrolled_loop, false},
+ {2048, rep_prefix_4_byte, false},
+ {-1, libcall, false}}},
+ /* 64-bit tuning. */
+ {libcall, {{48, unrolled_loop, false},
+ {8192, rep_prefix_8_byte, false},
{-1, libcall, false}}}};
struct processor_costs znver1_cost = {
{
@@ -1448,14 +1457,23 @@ struct processor_costs znver1_cost = {
very small blocks it is better to use loop. For large blocks, libcall
can do nontemporary accesses and beat inline considerably. */
static stringop_algs znver2_memcpy[2] = {
- {libcall, {{6, loop, false}, {14, unrolled_loop, false},
+ /* 32-bit tuning. */
+ {libcall, {{6, loop, false},
+ {14, unrolled_loop, false},
{-1, rep_prefix_4_byte, false}}},
- {libcall, {{16, loop, false}, {64, rep_prefix_4_byte, false},
+ /* 64-bit tuning. */
+ {libcall, {{16, loop, false},
+ {64, rep_prefix_4_byte, false},
{-1, libcall, false}}}};
static stringop_algs znver2_memset[2] = {
- {libcall, {{8, loop, false}, {24, unrolled_loop, false},
- {2048, rep_prefix_4_byte, false}, {-1, libcall, false}}},
- {libcall, {{24, rep_prefix_4_byte, false}, {128, rep_prefix_8_byte, false},
+ /* 32-bit tuning. */
+ {libcall, {{8, loop, false},
+ {24, unrolled_loop, false},
+ {2048, rep_prefix_4_byte, false}
+ {-1, libcall, false}}},
+ /* 64-bit tuning. */
+ {libcall, {{24, rep_prefix_4_byte, false},
+ {128, rep_prefix_8_byte, false},
{-1, libcall, false}}}};
struct processor_costs znver2_cost = {
--
2.26.2
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH 1/2] Re-format zen memcpy/memset costs.
2020-06-01 11:35 [PATCH 1/2] Re-format zen memcpy/memset costs Martin Liška
@ 2020-07-29 15:42 ` Jan Hubicka
0 siblings, 0 replies; 2+ messages in thread
From: Jan Hubicka @ 2020-07-29 15:42 UTC (permalink / raw)
To: Martin Liška; +Cc: gcc-patches, amonakov, ubizjak
> The patch improves readability of the memcpy and memset
> expansion strategies.
>
> gcc/ChangeLog:
>
> * config/i386/x86-tune-costs.h: Change code formatting.
OK,
thanks!
Honza
> ---
> gcc/config/i386/x86-tune-costs.h | 38 +++++++++++++++++++++++---------
> 1 file changed, 28 insertions(+), 10 deletions(-)
>
> diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
> index c73917e5a62..1169178433f 100644
> --- a/gcc/config/i386/x86-tune-costs.h
> +++ b/gcc/config/i386/x86-tune-costs.h
> @@ -1311,14 +1311,23 @@ const struct processor_costs bdver_cost = {
> very small blocks it is better to use loop. For large blocks, libcall
> can do nontemporary accesses and beat inline considerably. */
> static stringop_algs znver1_memcpy[2] = {
> - {libcall, {{6, loop, false}, {14, unrolled_loop, false},
> + /* 32-bit tuning. */
> + {libcall, {{6, loop, false},
> + {14, unrolled_loop, false},
> {-1, rep_prefix_4_byte, false}}},
> - {libcall, {{16, loop, false}, {8192, rep_prefix_8_byte, false},
> + /* 64-bit tuning. */
> + {libcall, {{16, loop, false},
> + {8192, rep_prefix_8_byte, false},
> {-1, libcall, false}}}};
> static stringop_algs znver1_memset[2] = {
> - {libcall, {{8, loop, false}, {24, unrolled_loop, false},
> - {2048, rep_prefix_4_byte, false}, {-1, libcall, false}}},
> - {libcall, {{48, unrolled_loop, false}, {8192, rep_prefix_8_byte, false},
> + /* 32-bit tuning. */
> + {libcall, {{8, loop, false},
> + {24, unrolled_loop, false},
> + {2048, rep_prefix_4_byte, false},
> + {-1, libcall, false}}},
> + /* 64-bit tuning. */
> + {libcall, {{48, unrolled_loop, false},
> + {8192, rep_prefix_8_byte, false},
> {-1, libcall, false}}}};
> struct processor_costs znver1_cost = {
> {
> @@ -1448,14 +1457,23 @@ struct processor_costs znver1_cost = {
> very small blocks it is better to use loop. For large blocks, libcall
> can do nontemporary accesses and beat inline considerably. */
> static stringop_algs znver2_memcpy[2] = {
> - {libcall, {{6, loop, false}, {14, unrolled_loop, false},
> + /* 32-bit tuning. */
> + {libcall, {{6, loop, false},
> + {14, unrolled_loop, false},
> {-1, rep_prefix_4_byte, false}}},
> - {libcall, {{16, loop, false}, {64, rep_prefix_4_byte, false},
> + /* 64-bit tuning. */
> + {libcall, {{16, loop, false},
> + {64, rep_prefix_4_byte, false},
> {-1, libcall, false}}}};
> static stringop_algs znver2_memset[2] = {
> - {libcall, {{8, loop, false}, {24, unrolled_loop, false},
> - {2048, rep_prefix_4_byte, false}, {-1, libcall, false}}},
> - {libcall, {{24, rep_prefix_4_byte, false}, {128, rep_prefix_8_byte, false},
> + /* 32-bit tuning. */
> + {libcall, {{8, loop, false},
> + {24, unrolled_loop, false},
> + {2048, rep_prefix_4_byte, false}
> + {-1, libcall, false}}},
> + /* 64-bit tuning. */
> + {libcall, {{24, rep_prefix_4_byte, false},
> + {128, rep_prefix_8_byte, false},
> {-1, libcall, false}}}};
> struct processor_costs znver2_cost = {
> --
> 2.26.2
>
>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2020-07-29 15:42 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-06-01 11:35 [PATCH 1/2] Re-format zen memcpy/memset costs Martin Liška
2020-07-29 15:42 ` Jan Hubicka
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).