From: Noah Goldstein <goldstein.w.n@gmail.com>
To: libc-alpha@sourceware.org
Cc: goldstein.w.n@gmail.com, hjl.tools@gmail.com, carlos@systemhalted.org
Subject: [PATCH v5 2/3] x86: Refactor Intel `init_cpu_features`
Date: Mon, 8 May 2023 22:13:12 -0500 [thread overview]
Message-ID: <20230509031313.3497001-2-goldstein.w.n@gmail.com> (raw)
In-Reply-To: <20230509031313.3497001-1-goldstein.w.n@gmail.com>
This patch should have no affect on existing functionality.
The current code, which has a single switch for model detection and
setting prefered features, is difficult to follow/extend. The cases
use magic numbers and many microarchitectures are missing. This makes
it difficult to reason about what is implemented so far and/or
how/where to add support for new features.
This patch splits the model detection and preference setting stages so
that CPU preferences can be set based on a complete list of available
microarchitectures, rather than based on model magic numbers.
---
sysdeps/x86/cpu-features.c | 401 +++++++++++++++++++++++++++++--------
1 file changed, 316 insertions(+), 85 deletions(-)
diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
index 5bff8ec0b4..bec70c3c49 100644
--- a/sysdeps/x86/cpu-features.c
+++ b/sysdeps/x86/cpu-features.c
@@ -417,6 +417,217 @@ _Static_assert (((index_arch_Fast_Unaligned_Load
== index_arch_Fast_Copy_Backward)),
"Incorrect index_arch_Fast_Unaligned_Load");
+
+/* Intel Family-6 microarch list. */
+enum
+{
+ /* Atom processors. */
+ INTEL_ATOM_BONNELL,
+ INTEL_ATOM_SALTWELL,
+ INTEL_ATOM_SILVERMONT,
+ INTEL_ATOM_AIRMONT,
+ INTEL_ATOM_GOLDMONT,
+ INTEL_ATOM_GOLDMONT_PLUS,
+ INTEL_ATOM_SIERRAFOREST,
+ INTEL_ATOM_GRANDRIDGE,
+ INTEL_ATOM_TREMONT,
+
+ /* Bigcore processors. */
+ INTEL_BIGCORE_MEROM,
+ INTEL_BIGCORE_PENRYN,
+ INTEL_BIGCORE_DUNNINGTON,
+ INTEL_BIGCORE_NEHALEM,
+ INTEL_BIGCORE_WESTMERE,
+ INTEL_BIGCORE_SANDYBRIDGE,
+ INTEL_BIGCORE_IVYBRIDGE,
+ INTEL_BIGCORE_HASWELL,
+ INTEL_BIGCORE_BROADWELL,
+ INTEL_BIGCORE_SKYLAKE,
+ INTEL_BIGCORE_AMBERLAKE,
+ INTEL_BIGCORE_COFFEELAKE,
+ INTEL_BIGCORE_WHISKEYLAKE,
+ INTEL_BIGCORE_KABYLAKE,
+ INTEL_BIGCORE_COMETLAKE,
+ INTEL_BIGCORE_SKYLAKE_AVX512,
+ INTEL_BIGCORE_CANNONLAKE,
+ INTEL_BIGCORE_CASCADELAKE,
+ INTEL_BIGCORE_COOPERLAKE,
+ INTEL_BIGCORE_ICELAKE,
+ INTEL_BIGCORE_TIGERLAKE,
+ INTEL_BIGCORE_ROCKETLAKE,
+ INTEL_BIGCORE_SAPPHIRERAPIDS,
+ INTEL_BIGCORE_RAPTORLAKE,
+ INTEL_BIGCORE_EMERALDRAPIDS,
+ INTEL_BIGCORE_METEORLAKE,
+ INTEL_BIGCORE_LUNARLAKE,
+ INTEL_BIGCORE_ARROWLAKE,
+ INTEL_BIGCORE_GRANITERAPIDS,
+
+ /* Mixed (bigcore + atom SOC). */
+ INTEL_MIXED_LAKEFIELD,
+ INTEL_MIXED_ALDERLAKE,
+
+ /* KNL. */
+ INTEL_KNIGHTS_MILL,
+ INTEL_KNIGHTS_LANDING,
+
+ /* Unknown. */
+ INTEL_UNKNOWN,
+};
+
+static unsigned int
+intel_get_fam6_microarch (unsigned int model, unsigned int stepping)
+{
+ switch (model)
+ {
+ case 0x1C:
+ case 0x26:
+ return INTEL_ATOM_BONNELL;
+ case 0x27:
+ case 0x35:
+ case 0x36:
+ return INTEL_ATOM_SALTWELL;
+ case 0x37:
+ case 0x4A:
+ case 0x4D:
+ case 0x5D:
+ return INTEL_ATOM_SILVERMONT;
+ case 0x4C:
+ case 0x5A:
+ case 0x75:
+ return INTEL_ATOM_AIRMONT;
+ case 0x5C:
+ case 0x5F:
+ return INTEL_ATOM_GOLDMONT;
+ case 0x7A:
+ return INTEL_ATOM_GOLDMONT_PLUS;
+ case 0xAF:
+ return INTEL_ATOM_SIERRAFOREST;
+ case 0xB6:
+ return INTEL_ATOM_GRANDRIDGE;
+ case 0x86:
+ case 0x96:
+ case 0x9C:
+ return INTEL_ATOM_TREMONT;
+ case 0x0F:
+ case 0x16:
+ return INTEL_BIGCORE_MEROM;
+ case 0x17:
+ return INTEL_BIGCORE_PENRYN;
+ case 0x1D:
+ return INTEL_BIGCORE_DUNNINGTON;
+ case 0x1A:
+ case 0x1E:
+ case 0x1F:
+ case 0x2E:
+ return INTEL_BIGCORE_NEHALEM;
+ case 0x25:
+ case 0x2C:
+ case 0x2F:
+ return INTEL_BIGCORE_WESTMERE;
+ case 0x2A:
+ case 0x2D:
+ return INTEL_BIGCORE_SANDYBRIDGE;
+ case 0x3A:
+ case 0x3E:
+ return INTEL_BIGCORE_IVYBRIDGE;
+ case 0x3C:
+ case 0x3F:
+ case 0x45:
+ case 0x46:
+ return INTEL_BIGCORE_HASWELL;
+ case 0x3D:
+ case 0x47:
+ case 0x4F:
+ case 0x56:
+ return INTEL_BIGCORE_BROADWELL;
+ case 0x4E:
+ case 0x5E:
+ return INTEL_BIGCORE_SKYLAKE;
+ case 0x8E:
+ switch (stepping)
+ {
+ case 0x09:
+ return INTEL_BIGCORE_AMBERLAKE;
+ case 0x0A:
+ return INTEL_BIGCORE_COFFEELAKE;
+ case 0x0B:
+ case 0x0C:
+ return INTEL_BIGCORE_WHISKEYLAKE;
+ default:
+ return INTEL_BIGCORE_KABYLAKE;
+ }
+ case 0x9E:
+ switch (stepping)
+ {
+ case 0x0A:
+ case 0x0B:
+ case 0x0C:
+ case 0x0D:
+ return INTEL_BIGCORE_COFFEELAKE;
+ default:
+ return INTEL_BIGCORE_KABYLAKE;
+ }
+ case 0xA5:
+ case 0xA6:
+ return INTEL_BIGCORE_COMETLAKE;
+ case 0x66:
+ return INTEL_BIGCORE_CANNONLAKE;
+ case 0x55:
+ switch (stepping)
+ {
+ case 0x06:
+ case 0x07:
+ return INTEL_BIGCORE_CASCADELAKE;
+ case 0x0b:
+ return INTEL_BIGCORE_COOPERLAKE;
+ default:
+ return INTEL_BIGCORE_SKYLAKE_AVX512;
+ }
+ case 0x6A:
+ case 0x6C:
+ case 0x7D:
+ case 0x7E:
+ case 0x9D:
+ return INTEL_BIGCORE_ICELAKE;
+ case 0x8C:
+ case 0x8D:
+ return INTEL_BIGCORE_TIGERLAKE;
+ case 0xA7:
+ return INTEL_BIGCORE_ROCKETLAKE;
+ case 0x8F:
+ return INTEL_BIGCORE_SAPPHIRERAPIDS;
+ case 0xB7:
+ case 0xBA:
+ case 0xBF:
+ return INTEL_BIGCORE_RAPTORLAKE;
+ case 0xCF:
+ return INTEL_BIGCORE_EMERALDRAPIDS;
+ case 0xAA:
+ case 0xAC:
+ return INTEL_BIGCORE_METEORLAKE;
+ case 0xbd:
+ return INTEL_BIGCORE_LUNARLAKE;
+ case 0xc6:
+ return INTEL_BIGCORE_ARROWLAKE;
+ case 0xAD:
+ case 0xAE:
+ return INTEL_BIGCORE_GRANITERAPIDS;
+ case 0x8A:
+ return INTEL_MIXED_LAKEFIELD;
+ case 0x97:
+ case 0x9A:
+ case 0xBE:
+ return INTEL_MIXED_ALDERLAKE;
+ case 0x85:
+ return INTEL_KNIGHTS_MILL;
+ case 0x57:
+ return INTEL_KNIGHTS_LANDING;
+ default:
+ return INTEL_UNKNOWN;
+ }
+}
+
static inline void
init_cpu_features (struct cpu_features *cpu_features)
{
@@ -453,129 +664,149 @@ init_cpu_features (struct cpu_features *cpu_features)
if (family == 0x06)
{
model += extended_model;
- switch (model)
+ unsigned int microarch
+ = intel_get_fam6_microarch (model, stepping);
+
+ switch (microarch)
{
- case 0x1c:
- case 0x26:
- /* BSF is slow on Atom. */
+ /* Atom / KNL tuning. */
+ case INTEL_ATOM_BONNELL:
+ /* BSF is slow on Bonnell. */
cpu_features->preferred[index_arch_Slow_BSF]
- |= bit_arch_Slow_BSF;
+ |= bit_arch_Slow_BSF;
break;
- case 0x57:
- /* Knights Landing. Enable Silvermont optimizations. */
-
- case 0x7a:
- /* Unaligned load versions are faster than SSSE3
- on Goldmont Plus. */
-
- case 0x5c:
- case 0x5f:
/* Unaligned load versions are faster than SSSE3
- on Goldmont. */
+ on Airmont, Silvermont, Goldmont, and Goldmont Plus. */
+ case INTEL_ATOM_AIRMONT:
+ case INTEL_ATOM_SILVERMONT:
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_PLUS:
- case 0x4c:
- case 0x5a:
- case 0x75:
- /* Airmont is a die shrink of Silvermont. */
+ /* Knights Landing. Enable Silvermont optimizations. */
+ case INTEL_KNIGHTS_LANDING:
- case 0x37:
- case 0x4a:
- case 0x4d:
- case 0x5d:
- /* Unaligned load versions are faster than SSSE3
- on Silvermont. */
cpu_features->preferred[index_arch_Fast_Unaligned_Load]
- |= (bit_arch_Fast_Unaligned_Load
- | bit_arch_Fast_Unaligned_Copy
- | bit_arch_Prefer_PMINUB_for_stringop
- | bit_arch_Slow_SSE4_2);
+ |= (bit_arch_Fast_Unaligned_Load
+ | bit_arch_Fast_Unaligned_Copy
+ | bit_arch_Prefer_PMINUB_for_stringop
+ | bit_arch_Slow_SSE4_2);
break;
- case 0x86:
- case 0x96:
- case 0x9c:
+ case INTEL_ATOM_TREMONT:
/* Enable rep string instructions, unaligned load, unaligned
- copy, pminub and avoid SSE 4.2 on Tremont. */
+ copy, pminub and avoid SSE 4.2 on Tremont. */
cpu_features->preferred[index_arch_Fast_Rep_String]
- |= (bit_arch_Fast_Rep_String
- | bit_arch_Fast_Unaligned_Load
- | bit_arch_Fast_Unaligned_Copy
- | bit_arch_Prefer_PMINUB_for_stringop
- | bit_arch_Slow_SSE4_2);
+ |= (bit_arch_Fast_Rep_String | bit_arch_Fast_Unaligned_Load
+ | bit_arch_Fast_Unaligned_Copy
+ | bit_arch_Prefer_PMINUB_for_stringop
+ | bit_arch_Slow_SSE4_2);
+ break;
+
+ /* Untuned KNL microarch. */
+ case INTEL_KNIGHTS_MILL:
+ /* Untuned atom microarch. */
+ case INTEL_ATOM_SIERRAFOREST:
+ case INTEL_ATOM_GRANDRIDGE:
+ case INTEL_ATOM_SALTWELL:
break;
+ /* Bigcore Tuning. */
+ case INTEL_UNKNOWN:
default:
/* Unknown family 0x06 processors. Assuming this is one
of Core i3/i5/i7 processors if AVX is available. */
if (!CPU_FEATURES_CPU_P (cpu_features, AVX))
break;
- /* Fall through. */
-
- case 0x1a:
- case 0x1e:
- case 0x1f:
- case 0x25:
- case 0x2c:
- case 0x2e:
- case 0x2f:
+ case INTEL_BIGCORE_NEHALEM:
+ case INTEL_BIGCORE_WESTMERE:
/* Rep string instructions, unaligned load, unaligned copy,
and pminub are fast on Intel Core i3, i5 and i7. */
cpu_features->preferred[index_arch_Fast_Rep_String]
- |= (bit_arch_Fast_Rep_String
- | bit_arch_Fast_Unaligned_Load
- | bit_arch_Fast_Unaligned_Copy
- | bit_arch_Prefer_PMINUB_for_stringop);
+ |= (bit_arch_Fast_Rep_String | bit_arch_Fast_Unaligned_Load
+ | bit_arch_Fast_Unaligned_Copy
+ | bit_arch_Prefer_PMINUB_for_stringop);
+ break;
+
+ /* Untuned Bigcore microarch. */
+ case INTEL_BIGCORE_SANDYBRIDGE:
+ case INTEL_BIGCORE_IVYBRIDGE:
+ case INTEL_BIGCORE_HASWELL:
+ case INTEL_BIGCORE_BROADWELL:
+ case INTEL_BIGCORE_SKYLAKE:
+ case INTEL_BIGCORE_AMBERLAKE:
+ case INTEL_BIGCORE_COFFEELAKE:
+ case INTEL_BIGCORE_WHISKEYLAKE:
+ case INTEL_BIGCORE_KABYLAKE:
+ case INTEL_BIGCORE_COMETLAKE:
+ case INTEL_BIGCORE_SKYLAKE_AVX512:
+ case INTEL_BIGCORE_CASCADELAKE:
+ case INTEL_BIGCORE_COOPERLAKE:
+ case INTEL_BIGCORE_CANNONLAKE:
+ case INTEL_BIGCORE_ICELAKE:
+ case INTEL_BIGCORE_TIGERLAKE:
+ case INTEL_BIGCORE_ROCKETLAKE:
+ case INTEL_BIGCORE_RAPTORLAKE:
+ case INTEL_BIGCORE_METEORLAKE:
+ case INTEL_BIGCORE_LUNARLAKE:
+ case INTEL_BIGCORE_ARROWLAKE:
+ case INTEL_BIGCORE_SAPPHIRERAPIDS:
+ case INTEL_BIGCORE_EMERALDRAPIDS:
+ case INTEL_BIGCORE_GRANITERAPIDS:
+ break;
+
+ /* Untuned Mixed (bigcore + atom SOC). */
+ case INTEL_MIXED_LAKEFIELD:
+ case INTEL_MIXED_ALDERLAKE:
break;
}
- /* Disable TSX on some processors to avoid TSX on kernels that
- weren't updated with the latest microcode package (which
- disables broken feature by default). */
- switch (model)
+ /* Disable TSX on some processors to avoid TSX on kernels that
+ weren't updated with the latest microcode package (which
+ disables broken feature by default). */
+ switch (microarch)
{
- case 0x55:
- if (stepping <= 5)
+ case INTEL_BIGCORE_SKYLAKE_AVX512:
+ /* 0x55 && stepping <= 5 is SKYLAKE_AVX512. Cascadelake and
+ Cooperlake also have model == 0x55 so double check the
+ stepping to be safe. */
+ if (model == 0x55 && stepping <= 5)
goto disable_tsx;
break;
- case 0x8e:
- /* NB: Although the errata documents that for model == 0x8e,
- only 0xb stepping or lower are impacted, the intention of
- the errata was to disable TSX on all client processors on
- all steppings. Include 0xc stepping which is an Intel
- Core i7-8665U, a client mobile processor. */
- case 0x9e:
- if (stepping > 0xc)
+
+ case INTEL_BIGCORE_SKYLAKE:
+ case INTEL_BIGCORE_AMBERLAKE:
+ case INTEL_BIGCORE_COFFEELAKE:
+ case INTEL_BIGCORE_WHISKEYLAKE:
+ case INTEL_BIGCORE_KABYLAKE:
+ /* NB: Although the errata documents that for model == 0x8e
+ (skylake client), only 0xb stepping or lower are impacted,
+ the intention of the errata was to disable TSX on all client
+ processors on all steppings. Include 0xc stepping which is
+ an Intel Core i7-8665U, a client mobile processor. */
+ if ((model == 0x8e || model == 0x9e) && stepping > 0xc)
break;
- /* Fall through. */
- case 0x4e:
- case 0x5e:
- {
+
/* Disable Intel TSX and enable RTM_ALWAYS_ABORT for
processors listed in:
https://www.intel.com/content/www/us/en/support/articles/000059422/processors.html
*/
-disable_tsx:
+ disable_tsx:
CPU_FEATURE_UNSET (cpu_features, HLE);
CPU_FEATURE_UNSET (cpu_features, RTM);
CPU_FEATURE_SET (cpu_features, RTM_ALWAYS_ABORT);
- }
- break;
- case 0x3f:
- /* Xeon E7 v3 with stepping >= 4 has working TSX. */
- if (stepping >= 4)
break;
- /* Fall through. */
- case 0x3c:
- case 0x45:
- case 0x46:
- /* Disable Intel TSX on Haswell processors (except Xeon E7 v3
- with stepping >= 4) to avoid TSX on kernels that weren't
- updated with the latest microcode package (which disables
- broken feature by default). */
- CPU_FEATURE_UNSET (cpu_features, RTM);
- break;
+
+ case INTEL_BIGCORE_HASWELL:
+ /* Xeon E7 v3 (model == 0x3f) with stepping >= 4 has working
+ TSX. Haswell also include other model numbers that have
+ working TSX. */
+ if (model == 0x3f && stepping >= 4)
+ break;
+
+ CPU_FEATURE_UNSET (cpu_features, RTM);
+ break;
}
}
--
2.34.1
next prev parent reply other threads:[~2023-05-09 3:13 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-24 5:03 [PATCH v1] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 2` Noah Goldstein
2023-04-24 18:09 ` H.J. Lu
2023-04-24 18:34 ` Noah Goldstein
2023-04-24 20:44 ` H.J. Lu
2023-04-24 22:30 ` Noah Goldstein
2023-04-24 22:30 ` [PATCH v2] " Noah Goldstein
2023-04-24 22:48 ` H.J. Lu
2023-04-25 2:05 ` Noah Goldstein
2023-04-25 2:55 ` H.J. Lu
2023-04-25 3:43 ` Noah Goldstein
2023-04-25 3:43 ` [PATCH v3] " Noah Goldstein
2023-04-25 17:42 ` H.J. Lu
2023-04-25 21:45 ` Noah Goldstein
2023-04-25 21:45 ` [PATCH v4] " Noah Goldstein
2023-04-26 15:59 ` H.J. Lu
2023-04-26 17:15 ` Noah Goldstein
2023-05-04 3:28 ` Noah Goldstein
2023-05-05 18:06 ` H.J. Lu
2023-05-09 3:14 ` Noah Goldstein
2023-05-09 3:13 ` [PATCH v5 1/3] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Noah Goldstein
2023-05-09 3:13 ` Noah Goldstein [this message]
2023-05-09 21:58 ` [PATCH v5 2/3] x86: Refactor Intel `init_cpu_features` H.J. Lu
2023-05-10 0:33 ` Noah Goldstein
2023-05-09 3:13 ` [PATCH v5 3/3] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-05-10 0:33 ` [PATCH v6 1/4] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Noah Goldstein
2023-05-10 0:33 ` [PATCH v6 2/4] x86: Refactor Intel `init_cpu_features` Noah Goldstein
2023-05-10 22:13 ` H.J. Lu
2023-05-10 23:17 ` Noah Goldstein
2023-05-11 21:36 ` H.J. Lu
2023-05-12 5:11 ` Noah Goldstein
2023-05-10 0:33 ` [PATCH v6 3/4] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-05-10 0:33 ` [PATCH v6 4/4] x86: Tune 'Saltwell' microarch the same was a 'Bonnell' Noah Goldstein
2023-05-10 22:04 ` H.J. Lu
2023-05-10 22:12 ` Noah Goldstein
2023-05-10 15:55 ` [PATCH v6 1/4] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` H.J. Lu
2023-05-10 16:07 ` Noah Goldstein
2023-05-10 22:12 ` [PATCH v7 2/4] x86: Refactor Intel `init_cpu_features` Noah Goldstein
2023-05-10 22:12 ` [PATCH v7 3/4] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-05-10 22:12 ` [PATCH v7 4/4] x86: Tune 'Saltwell' microarch the same was a 'Bonnell' Noah Goldstein
2023-05-12 5:12 ` Noah Goldstein
2023-05-12 5:10 ` [PATCH v8 1/3] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Noah Goldstein
2023-05-12 5:10 ` [PATCH v8 2/3] x86: Refactor Intel `init_cpu_features` Noah Goldstein
2023-05-12 22:17 ` H.J. Lu
2023-05-13 5:18 ` Noah Goldstein
2023-05-12 22:03 ` [PATCH v8 3/3] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-05-13 5:19 ` [PATCH v9 1/3] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Noah Goldstein
2023-05-13 5:19 ` [PATCH v9 2/3] x86: Refactor Intel `init_cpu_features` Noah Goldstein
2023-05-15 20:57 ` H.J. Lu
2023-05-26 3:34 ` DJ Delorie
2023-05-27 18:46 ` Noah Goldstein
2023-05-13 5:19 ` [PATCH v9 3/3] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-05-26 3:34 ` DJ Delorie
2023-05-27 18:46 ` Noah Goldstein
2023-05-15 18:29 ` [PATCH v9 1/3] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Noah Goldstein
2023-05-17 12:00 ` Carlos O'Donell
2023-05-26 3:34 ` DJ Delorie
2023-05-27 18:46 ` [PATCH v10 " Noah Goldstein
2023-05-27 18:46 ` [PATCH v10 2/3] x86: Refactor Intel `init_cpu_features` Noah Goldstein
2023-05-27 18:46 ` [PATCH v10 3/3] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-05-31 2:33 ` DJ Delorie
2023-07-10 5:23 ` Sajan Karumanchi
2023-07-10 15:58 ` Noah Goldstein
2023-07-14 2:21 ` Re: Noah Goldstein
2023-07-14 7:39 ` Re: sajan karumanchi
2023-06-07 0:15 ` [PATCH v10 1/3] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Carlos O'Donell
2023-06-07 18:18 ` Noah Goldstein
2023-06-07 18:18 ` [PATCH v11 " Noah Goldstein
2023-06-07 18:18 ` [PATCH v11 2/3] x86: Refactor Intel `init_cpu_features` Noah Goldstein
2023-06-07 18:18 ` [PATCH v11 3/3] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Noah Goldstein
2023-06-07 18:19 ` [PATCH v11 1/3] x86: Increase `non_temporal_threshold` to roughly `sizeof_L3 / 4` Noah Goldstein
2023-08-14 23:00 ` Noah Goldstein
2023-08-22 15:11 ` Noah Goldstein
2023-08-24 17:06 ` Noah Goldstein
2023-08-28 20:02 ` Noah Goldstein
2023-09-05 15:37 ` Noah Goldstein
2023-09-12 3:50 ` Noah Goldstein
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230509031313.3497001-2-goldstein.w.n@gmail.com \
--to=goldstein.w.n@gmail.com \
--cc=carlos@systemhalted.org \
--cc=hjl.tools@gmail.com \
--cc=libc-alpha@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).