From 907fce7a0bf5598d8181181ce9b82786113a066c Mon Sep 17 00:00:00 2001
From: May <[email protected]>
Date: Wed, 15 Jan 2025 17:57:10 +0800
Subject: [PATCH 1/3] x86: Set preferred CPU features on the KH-40000 and
 KX-7000 Zhaoxin processors

Fix code formatting under the Zhaoxin branch and add comments for
different Zhaoxin models.

Unaligned AVX load are slower on KH-40000 and KX-7000, so disable
the AVX_Fast_Unaligned_Load.

Enable Prefer_No_VZEROUPPER and Fast_Unaligned_Load features to
use sse2_unaligned version of memset,strcpy and strcat.

Signed-off-by: May <[email protected]>
---
 sysdeps/x86/cpu-features.c | 51 ++++++++++++++++++++++++++------------
 1 file changed, 35 insertions(+), 16 deletions(-)

diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
index badf0888..43b5f562 100644
--- a/sysdeps/x86/cpu-features.c
+++ b/sysdeps/x86/cpu-features.c
@@ -907,39 +907,58 @@ https://www.intel.com/content/www/us/en/support/articles/000059422/processors.ht
 
       model += extended_model;
       if (family == 0x6)
-        {
-          if (model == 0xf || model == 0x19)
-            {
+	{
+	  /* Tuning for older Zhaoxin processors.  */
+	  if (model == 0xf || model == 0x19)
+	    {
 	      CPU_FEATURE_UNSET (cpu_features, AVX);
 	      CPU_FEATURE_UNSET (cpu_features, AVX2);
 
-              cpu_features->preferred[index_arch_Slow_SSE4_2]
-                |= bit_arch_Slow_SSE4_2;
+	      cpu_features->preferred[index_arch_Slow_SSE4_2]
+		  |= bit_arch_Slow_SSE4_2;
 
+	      /*  Unaligned AVX loads are slower.  */
 	      cpu_features->preferred[index_arch_AVX_Fast_Unaligned_Load]
-		&= ~bit_arch_AVX_Fast_Unaligned_Load;
-            }
-        }
+		  &= ~bit_arch_AVX_Fast_Unaligned_Load;
+	    }
+	}
       else if (family == 0x7)
-        {
-	  if (model == 0x1b)
+	{
+	  switch (model)
 	    {
+	      /* Wudaokou microarch tuning.  */
+	    case 0x1b:
 	      CPU_FEATURE_UNSET (cpu_features, AVX);
 	      CPU_FEATURE_UNSET (cpu_features, AVX2);
 
 	      cpu_features->preferred[index_arch_Slow_SSE4_2]
-		|= bit_arch_Slow_SSE4_2;
+		  |= bit_arch_Slow_SSE4_2;
 
 	      cpu_features->preferred[index_arch_AVX_Fast_Unaligned_Load]
-		&= ~bit_arch_AVX_Fast_Unaligned_Load;
-	    }
-	  else if (model == 0x3b)
-	    {
+		  &= ~bit_arch_AVX_Fast_Unaligned_Load;
+	      break;
+
+	      /* Lujiazui microarch tuning.  */
+	    case 0x3b:
 	      CPU_FEATURE_UNSET (cpu_features, AVX);
 	      CPU_FEATURE_UNSET (cpu_features, AVX2);
 
 	      cpu_features->preferred[index_arch_AVX_Fast_Unaligned_Load]
-		&= ~bit_arch_AVX_Fast_Unaligned_Load;
+		  &= ~bit_arch_AVX_Fast_Unaligned_Load;
+	      break;
+
+	      /* Yongfeng and Shijidadao mircoarch tuning.  */
+	    case 0x5b:
+	    case 0x6b:
+	      cpu_features->preferred[index_arch_AVX_Fast_Unaligned_Load]
+		  &= ~bit_arch_AVX_Fast_Unaligned_Load;
+
+	      /* To use sse2_unaligned versions of memset, strcpy and strcat.
+	       */
+	      cpu_features->preferred[index_arch_Prefer_No_VZEROUPPER]
+		  |= (bit_arch_Prefer_No_VZEROUPPER
+		      | bit_arch_Fast_Unaligned_Load);
+	      break;
 	    }
 	}
     }
-- 
2.27.0