[v1.06][ARM] Add support for Amlogic A311D (#268)

src/arm/soc.c

@@ -947,7 +947,6 @@ bool match_dt(struct system_on_chip* soc, char* dt, int filelen, char* expected_
 // substring.
 // TODO: Implement this by going trough NULL-separated fields rather than
 // using strstr.
-// https://trac.gateworks.com/wiki/linux/devicetree
 struct system_on_chip* guess_soc_from_devtree(struct system_on_chip* soc) {
   int len;
   char* dt = get_devtree_compatible(&len);
@@ -971,16 +970,10 @@ struct system_on_chip* guess_soc_from_devtree(struct system_on_chip* soc) {
   DT_EQ(dt, len, soc, "apple,t6030", "M3 Pro",   SOC_APPLE_M3_PRO,   3)
   DT_EQ(dt, len, soc, "apple,t6031", "M3 Max",   SOC_APPLE_M3_MAX,   3)
   DT_EQ(dt, len, soc, "apple,t6034", "M3 Max",   SOC_APPLE_M3_MAX,   3)
-  // grep -oR -h --color -E '"fsl,.*' *.dtsi | sort | uniq | cut -d ',' -f1-2 | grep -v '-'
-  // https://elixir.bootlin.com/linux/v6.10.6/source/arch/arm64/boot/dts/freescale    
-  DT_EQ(dt, len, soc, "fsl,imx8qm",  "i.MX 8QuadMax",   SOC_NXP_IMX8QM,  28) // https://www.nxp.com/docs/en/fact-sheet/IMX8FAMFS.pdf  
-  DT_EQ(dt, len, soc, "fsl,imx8qp",  "i.MX 8QuadPlus",  SOC_NXP_IMX8QP,  28) // Actually not in dtsi, compatible string is just a guess
-  DT_EQ(dt, len, soc, "fsl,imx8mp",  "i.MX 8M Plus",    SOC_NXP_IMX8MP,  14) // https://www.nxp.com/docs/en/fact-sheet/IMX8MPLUSFS.pdf https://github.com/Dr-Noob/cpufetch/issues/261
-  DT_EQ(dt, len, soc, "fsl,imx8mn",  "i.MX 8M Nano",    SOC_NXP_IMX8MN,  NA)
-  DT_EQ(dt, len, soc, "fsl,imx8mm",  "i.MX 8M Mini",    SOC_NXP_IMX8MM,  NA) // https://www.nxp.com/docs/en/fact-sheet/IMX8MMINIFS.pdf
-  DT_EQ(dt, len, soc, "fsl,imx8dxp", "i.MX 8DualXPlus", SOC_NXP_IMX8DXP, NA)
-  DT_EQ(dt, len, soc, "fsl,imx8qxp", "i.MX 8QuadXPlus", SOC_NXP_IMX8QXP, NA)
-  DT_EQ(dt, len, soc, "fsl,imx93",   "i.MX 93",         SOC_NXP_IMX93,   NA)  
+  // TODO: Add more NXP SoCs: https://elixir.bootlin.com/linux/v6.10.6/source/arch/arm64/boot/dts/freescale
+  // https://github.com/Dr-Noob/cpufetch/issues/261
+  // https://www.nxp.com/docs/en/fact-sheet/IMX8MPLUSFS.pdf
+  DT_EQ(dt, len, soc, "imx8mp-nitrogen8mp", "i.MX 8M Plus", SOC_NXP_IMX8MP, 14)
   // TODO: Add more Amlogic SoCs: https://elixir.bootlin.com/linux/v6.10.6/source/arch/arm64/boot/dts/amlogic
   // https://github.com/Dr-Noob/cpufetch/issues/268
   // https://www.amlogic.com/#Products/393/index.html

src/arm/socs.h

@@ -383,14 +383,7 @@ enum {
   // ALTRA
   SOC_AMPERE_ALTRA,
   // NXP
-  SOC_NXP_IMX8QM,
-  SOC_NXP_IMX8QP,
   SOC_NXP_IMX8MP,
-  SOC_NXP_IMX8MN,
-  SOC_NXP_IMX8MM,
-  SOC_NXP_IMX8DXP,
-  SOC_NXP_IMX8QXP,
-  SOC_NXP_IMX93,
   // AMLOGIC
   SOC_AMLOGIC_A311D,
   // UNKNOWN
@@ -410,7 +403,7 @@ inline static VENDOR get_soc_vendor_from_soc(SOC soc) {
   else if(soc >= SOC_GOOGLE_TENSOR && soc <= SOC_GOOGLE_TENSOR_G3) return SOC_VENDOR_GOOGLE;
   else if(soc >= SOC_TEGRA_X1 && soc <= SOC_TEGRA_X1) return SOC_VENDOR_NVIDIA;
   else if(soc >= SOC_AMPERE_ALTRA && soc <= SOC_AMPERE_ALTRA) return SOC_VENDOR_AMPERE;
-  else if(soc >= SOC_NXP_IMX8QM && soc <= SOC_NXP_IMX93) return SOC_VENDOR_NXP;
+  else if(soc >= SOC_NXP_IMX8MP && soc <= SOC_NXP_IMX8MP) return SOC_VENDOR_NXP;
   else if(soc >= SOC_AMLOGIC_A311D && soc <= SOC_AMLOGIC_A311D) return SOC_VENDOR_AMLOGIC;
   return SOC_VENDOR_UNKNOWN;
 }

src/arm/uarch.c

@@ -34,8 +34,7 @@ enum {
   ISA_ARMv8_4_A,
   ISA_ARMv8_5_A,
   ISA_ARMv8_6_A,
-  ISA_ARMv9_A,
-  ISA_ARMv9_2_A
+  ISA_ARMv9_A
 };
 
 static const ISA isas_uarch[] = {
@@ -63,26 +62,15 @@ static const ISA isas_uarch[] = {
   [UARCH_CORTEX_A76]   = ISA_ARMv8_2_A,
   [UARCH_CORTEX_A77]   = ISA_ARMv8_2_A,
   [UARCH_CORTEX_A78]   = ISA_ARMv8_2_A,
-  [UARCH_CORTEX_A78C]  = ISA_ARMv8_2_A,
-  [UARCH_CORTEX_A78AE] = ISA_ARMv8_2_A,
   [UARCH_CORTEX_A510]   = ISA_ARMv9_A,
-  [UARCH_CORTEX_A520]  = ISA_ARMv9_2_A,
   [UARCH_CORTEX_A710]   = ISA_ARMv9_A,
   [UARCH_CORTEX_A715]  = ISA_ARMv9_A,
-  [UARCH_CORTEX_A720]  = ISA_ARMv9_2_A,
-  [UARCH_CORTEX_A725]  = ISA_ARMv9_2_A,
   [UARCH_CORTEX_X1]    = ISA_ARMv8_2_A,
-  [UARCH_CORTEX_X1C]   = ISA_ARMv8_2_A, // Assuming same as X1
   [UARCH_CORTEX_X2]    = ISA_ARMv9_A,
   [UARCH_CORTEX_X3]    = ISA_ARMv9_A,
-  [UARCH_CORTEX_X4]    = ISA_ARMv9_2_A,
-  [UARCH_CORTEX_X925]  = ISA_ARMv9_2_A,
   [UARCH_NEOVERSE_N1]  = ISA_ARMv8_2_A,
-  [UARCH_NEOVERSE_N2]  = ISA_ARMv9_A,
   [UARCH_NEOVERSE_E1]  = ISA_ARMv8_2_A,
   [UARCH_NEOVERSE_V1]  = ISA_ARMv8_4_A,
-  [UARCH_NEOVERSE_V2]  = ISA_ARMv9_A,
-  [UARCH_NEOVERSE_V3]  = ISA_ARMv9_2_A,
   [UARCH_BRAHMA_B15]   = ISA_ARMv7_A,   // Same as Cortex-A15
   [UARCH_BRAHMA_B53]   = ISA_ARMv8_A,   // Same as Cortex-A53
   [UARCH_THUNDERX]     = ISA_ARMv8_A,
@@ -128,8 +116,7 @@ static char* isas_string[] = {
   [ISA_ARMv8_4_A] = "ARMv8.4",
   [ISA_ARMv8_5_A] = "ARMv8.5",
   [ISA_ARMv8_6_A] = "ARMv8.6",
-  [ISA_ARMv9_A] = "ARMv9",
-  [ISA_ARMv9_2_A] = "ARMv9.2",
+  [ISA_ARMv9_A] = "ARMv9"
 };
 
 #define UARCH_START if (false) {}
@@ -201,24 +188,13 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
   CHECK_UARCH(arch, cpu, 'A', 0xD0E, NA, NA, "Cortex-A76",            UARCH_CORTEX_A76,   CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD40, NA, NA, "Neoverse V1",           UARCH_NEOVERSE_V1,  CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD41, NA, NA, "Cortex-A78",            UARCH_CORTEX_A78,   CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD42, NA, NA, "Cortex-A78AE",          UARCH_CORTEX_A78AE, CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD44, NA, NA, "Cortex-X1",             UARCH_CORTEX_X1,    CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD46, NA, NA, "Cortex‑A510",           UARCH_CORTEX_A510,  CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD47, NA, NA, "Cortex‑A710",           UARCH_CORTEX_A710,  CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD48, NA, NA, "Cortex-X2",             UARCH_CORTEX_X2,    CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD49, NA, NA, "Neoverse N2",           UARCH_NEOVERSE_N2,  CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD4A, NA, NA, "Neoverse E1",           UARCH_NEOVERSE_E1,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD4B, NA, NA, "Cortex-A78C",           UARCH_CORTEX_A78C,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD4C, NA, NA, "Cortex-X1C",            UARCH_CORTEX_X1C,   CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD4D, NA, NA, "Cortex-A715",           UARCH_CORTEX_A715,  CPU_VENDOR_ARM)
   CHECK_UARCH(arch, cpu, 'A', 0xD4E, NA, NA, "Cortex-X3",             UARCH_CORTEX_X3,    CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD4F, NA, NA, "Neoverse V2",           UARCH_NEOVERSE_V2,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD80, NA, NA, "Cortex-A520",           UARCH_CORTEX_A520,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD81, NA, NA, "Cortex-A720",           UARCH_CORTEX_A720,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD82, NA, NA, "Cortex-X4",             UARCH_CORTEX_X4,    CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD84, NA, NA, "Neoverse V3",           UARCH_NEOVERSE_V3,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD85, NA, NA, "Cortex-X925",           UARCH_CORTEX_X925,  CPU_VENDOR_ARM)
-  CHECK_UARCH(arch, cpu, 'A', 0xD87, NA, NA, "Cortex-A725",           UARCH_CORTEX_A725,  CPU_VENDOR_ARM)
 
   CHECK_UARCH(arch, cpu, 'B', 0x00F, NA, NA, "Brahma B15",            UARCH_BRAHMA_B15,   CPU_VENDOR_BROADCOM)
   CHECK_UARCH(arch, cpu, 'B', 0x100, NA, NA, "Brahma B53",            UARCH_BRAHMA_B53,   CPU_VENDOR_BROADCOM)
@@ -292,7 +268,15 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
 }
 
 bool is_ARMv8_or_newer(struct cpuInfo* cpu) {
-  return cpu->arch->isa >= ISA_ARMv8_A;
+  return cpu->arch->isa == ISA_ARMv8_A         ||
+         cpu->arch->isa == ISA_ARMv8_A_AArch32 ||
+         cpu->arch->isa == ISA_ARMv8_1_A       ||
+         cpu->arch->isa == ISA_ARMv8_2_A       ||
+         cpu->arch->isa == ISA_ARMv8_3_A       ||
+         cpu->arch->isa == ISA_ARMv8_4_A       ||
+         cpu->arch->isa == ISA_ARMv8_5_A       ||
+         cpu->arch->isa == ISA_ARMv8_6_A       ||
+         cpu->arch->isa == ISA_ARMv9_A;
 }
 
 bool has_fma_support(struct cpuInfo* cpu) {
@@ -305,13 +289,18 @@ int get_vpus_width(struct cpuInfo* cpu) {
   // If the CPU has NEON, width can be 64 or 128 [1].
   // In >= ARMv8, NEON are 128 bits width [2]
   // If the CPU has SVE/SVE2, width can be between 128-2048 [3],
-  // so we get the exact value from cntb [4]
+  // so we must check the exact width depending on
+  // the exact chip (Neoverse V1 uses 256b implementations.)
   //
   // [1] https://en.wikipedia.org/wiki/ARM_architecture_family#Advanced_SIMD_(Neon)
   // [2] https://developer.arm.com/documentation/102474/0100/Fundamentals-of-Armv8-Neon-technology
   // [3] https://www.anandtech.com/show/16640/arm-announces-neoverse-v1-n2-platforms-cpus-cmn700-mesh/5
-  // [4] https://developer.arm.com/documentation/ddi0596/2020-12/SVE-Instructions/CNTB--CNTD--CNTH--CNTW--Set-scalar-to-multiple-of-predicate-constraint-element-count-
 
+  MICROARCH ua = cpu->arch->uarch;
+  switch(ua) {
+    case UARCH_NEOVERSE_V1:
+      return 256;
+    default:
       if (cpu->feat->SVE && cpu->feat->cntb > 0) {
         return cpu->feat->cntb * 8;
       }
@@ -326,25 +315,20 @@ int get_vpus_width(struct cpuInfo* cpu) {
       else {
         return 32;
       }
+  }
 }
 
 int get_number_of_vpus(struct cpuInfo* cpu) {
   MICROARCH ua = cpu->arch->uarch;
 
   switch(ua) {
-    case UARCH_CORTEX_X925: // [https://www.anandtech.com/show/21399/arm-unveils-2024-cpu-core-designs-cortex-x925-a725-and-a520-arm-v9-2-redefined-for-3nm-/2]
-      return 6;
     case UARCH_EVEREST:     // Just a guess, needs confirmation.
     case UARCH_FIRESTORM:   // [https://dougallj.github.io/applecpu/firestorm-simd.html]
     case UARCH_AVALANCHE:   // [https://en.wikipedia.org/wiki/Comparison_of_ARM_processors]
     case UARCH_CORTEX_X1:   // [https://www.anandtech.com/show/15813/arm-cortex-a78-cortex-x1-cpu-ip-diverging/3]
-    case UARCH_CORTEX_X1C:  // Assuming same as X1
     case UARCH_CORTEX_X2:   // [https://www.anandtech.com/show/16693/arm-announces-mobile-armv9-cpu-microarchitectures-cortexx2-cortexa710-cortexa510/2]
     case UARCH_CORTEX_X3:   // [https://www.hwcooling.net/en/cortex-x3-the-new-fastest-arm-core-architecture-analysis: "The FPU and SIMD unit of the core still has four pipelines"]
-    case UARCH_CORTEX_X4:   // [https://www.anandtech.com/show/18871/arm-unveils-armv92-mobile-architecture-cortex-x4-a720-and-a520-64bit-exclusive/2]: "Cortex-X4: Out-of-Order Core"
     case UARCH_NEOVERSE_V1: // [https://en.wikichip.org/wiki/arm_holdings/microarchitectures/neoverse_v1]
-    case UARCH_NEOVERSE_V2: // [https://chipsandcheese.com/2023/09/11/hot-chips-2023-arms-neoverse-v2/]
-    case UARCH_NEOVERSE_V3: // Assuming same as V2
       return 4;
     case UARCH_SAWTOOTH:    // Needs confirmation, rn this is the best we know: https://mastodon.social/@dougall/111118317031041336
     case UARCH_EXYNOS_M3:   // [https://www.anandtech.com/show/12361/samsung-exynos-m3-architecture]
@@ -363,22 +347,16 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
     case UARCH_CORTEX_A76:  // [https://www.anandtech.com/show/12785/arm-cortex-a76-cpu-unveiled-7nm-powerhouse/3]
     case UARCH_CORTEX_A77:  // [https://fuse.wikichip.org/news/2339/arm-unveils-cortex-a77-emphasizes-single-thread-performance]
     case UARCH_CORTEX_A78:  // [https://fuse.wikichip.org/news/3536/arm-unveils-the-cortex-a78-when-less-is-more]
-    case UARCH_CORTEX_A78C: // Assuming same as A78
-    case UARCH_CORTEX_A78AE:// Assuming same as A78
     case UARCH_EXYNOS_M1:   // [https://www.anandtech.com/show/12361/samsung-exynos-m3-architecture]
     case UARCH_EXYNOS_M2:   // [https://www.anandtech.com/show/12361/samsung-exynos-m3-architecture]
     case UARCH_NEOVERSE_N1: // [https://en.wikichip.org/wiki/arm_holdings/microarchitectures/neoverse_n1#Individual_Core]
-    case UARCH_NEOVERSE_N2: // [https://chipsandcheese.com/2023/08/18/arms-neoverse-n2-cortex-a710-for-servers/]
     case UARCH_CORTEX_A710: // [https://chipsandcheese.com/2023/08/11/arms-cortex-a710-winning-by-default/]: Fig in Core Overview. Table in Instruction Scheduling and Execution
     case UARCH_CORTEX_A715: // [https://www.hwcooling.net/en/arm-introduces-new-cortex-a715-core-architecture-analysis/]: "the numbers of ALU and FPU execution units themselves >
-    case UARCH_CORTEX_A720: // Assuming same as A715: https://www.anandtech.com/show/18871/arm-unveils-armv92-mobile-architecture-cortex-x4-a720-and-a520-64bit-exclusive/3
-    case UARCH_CORTEX_A725: // Assuming same as A720
       return 2;
     case UARCH_NEOVERSE_E1: // [https://www.anandtech.com/show/13959/arm-announces-neoverse-n1-platform/5]
     // A510 is integrated as part of a Complex. Normally, each complex would incorporate two Cortex-A510 cores.
     // Each complex incorporates a single VPU with 2 ports, so for each A510 there is theoretically 1 port.
     case UARCH_CORTEX_A510: // [https://en.wikichip.org/wiki/arm_holdings/microarchitectures/cortex-a510#Vector_Processing_Unit_.28VPU.29]
-    case UARCH_CORTEX_A520: // Assuming same as A50: https://www.anandtech.com/show/18871/arm-unveils-armv92-mobile-architecture-cortex-x4-a720-and-a520-64bit-exclusive/4
       return 1;
     default:
       // ARMv6

src/arm/uarch.h

@@ -34,26 +34,15 @@ enum {
   UARCH_CORTEX_A76,
   UARCH_CORTEX_A77,
   UARCH_CORTEX_A78,
-  UARCH_CORTEX_A78AE,
-  UARCH_CORTEX_A78C,
   UARCH_CORTEX_A510,
-  UARCH_CORTEX_A520,
   UARCH_CORTEX_A710,
   UARCH_CORTEX_A715,
-  UARCH_CORTEX_A720,
-  UARCH_CORTEX_A725,
   UARCH_CORTEX_X1,
-  UARCH_CORTEX_X1C,
   UARCH_CORTEX_X2,
   UARCH_CORTEX_X3,
-  UARCH_CORTEX_X4,
-  UARCH_CORTEX_X925,
   UARCH_NEOVERSE_N1,
-  UARCH_NEOVERSE_N2,
   UARCH_NEOVERSE_E1,
   UARCH_NEOVERSE_V1,
-  UARCH_NEOVERSE_V2,
-  UARCH_NEOVERSE_V3,
   UARCH_SCORPION,
   UARCH_KRAIT,
   UARCH_KYRO,

src/x86/uarch.c

@@ -119,9 +119,7 @@ enum {
   UARCH_ZEN3,
   UARCH_ZEN3_PLUS,
   UARCH_ZEN4,
-  UARCH_ZEN4C,
-  UARCH_ZEN5,
-  UARCH_ZEN5C,
+  UARCH_ZEN4C
 };
 
 struct uarch {
@@ -412,12 +410,6 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
   CHECK_UARCH(arch, 10, 15,  8, NA, NA, "Zen 4",       UARCH_ZEN4,         5) // instlatx64 (AMD MI300C)
   CHECK_UARCH(arch, 10, 15,  9, NA, NA, "Zen 4",       UARCH_ZEN4,         5) // instlatx64 (AMD MI300A)
   CHECK_UARCH(arch, 10, 15, 10, NA, NA, "Zen 4c",      UARCH_ZEN4C,        5) // instlatx64
-  CHECK_UARCH(arch, 11, 15,  0, NA, NA, "Zen 5",       UARCH_ZEN5,         4) // Turin/EPYC (instlatx64)
-  CHECK_UARCH(arch, 11, 15,  1, NA, NA, "Zen 5c",      UARCH_ZEN5C,        3) // Zen5c EPYC (instlatx64, https://en.wikipedia.org/wiki/Zen_5#cite_note-10)
-  CHECK_UARCH(arch, 11, 15,  2, NA, NA, "Zen 5",       UARCH_ZEN5,         4) // Strix Point (instlatx64)
-  CHECK_UARCH(arch, 11, 15,  4, NA, NA, "Zen 5",       UARCH_ZEN5,         4) // Granite Ridge (instlatx64)
-  CHECK_UARCH(arch, 11, 15,  6, NA, NA, "Zen 5",       UARCH_ZEN5,         4) // Krackan Point (instlatx64)
-  CHECK_UARCH(arch, 11, 15,  7, NA, NA, "Zen 5",       UARCH_ZEN5,         4) // Strix Halo (instlatx64)
   UARCH_END
 
   return arch;
@@ -560,8 +552,6 @@ char* infer_cpu_name_from_uarch(struct uarch* arch) {
 }
 
 bool vpus_are_AVX512(struct cpuInfo* cpu) {
-  // Zen5 actually has 2 x AVX512 units
-  // https://www.anandtech.com/show/21469/amd-details-ryzen-ai-300-series-for-mobile-strix-point-with-rdna-35-igpu-xdna-2-npu
   return cpu->arch->uarch != UARCH_ICE_LAKE &&
          cpu->arch->uarch != UARCH_TIGER_LAKE &&
          cpu->arch->uarch != UARCH_ZEN4 &&
@@ -602,8 +592,6 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
       case UARCH_ZEN3_PLUS:
       case UARCH_ZEN4:
       case UARCH_ZEN4C:
-      case UARCH_ZEN5:
-      case UARCH_ZEN5C:
         return 2;
       default:
         return 1;