[X86] -march=cooperlake (llvm)

[skan]

Summary

Support intel -march=cooperlake in llvm

[craig.topper]

LGTM

llvm/trunk/include/llvm/Support/X86TargetParser.def

 X86_CPU_SUBTYPE_COMPAT("cascadelake",    INTEL_COREI7_CASCADELAKE,    "cascadelake")
 // Entries below this are not in libgcc/compiler-rt.
 X86_CPU_SUBTYPE       ("core2",          INTEL_CORE2_65)
 X86_CPU_SUBTYPE       ("penryn",         INTEL_CORE2_45)
 X86_CPU_SUBTYPE       ("k6",             AMDPENTIUM_K6)
 X86_CPU_SUBTYPE       ("k6-2",           AMDPENTIUM_K62)
 X86_CPU_SUBTYPE       ("k6-3",           AMDPENTIUM_K63)
 X86_CPU_SUBTYPE       ("geode",          AMDPENTIUM_GEODE)
+X86_CPU_SUBTYPE       ("cooperlake",     INTEL_COREI7_COOPERLAKE)
 #undef X86_CPU_SUBTYPE_COMPAT
 #undef X86_CPU_SUBTYPE
 
 
 // This macro is used for cpu types present in compiler-rt/libgcc.
 #ifndef X86_FEATURE_COMPAT
 #define X86_FEATURE_COMPAT(VAL, ENUM, STR) X86_FEATURE(VAL, ENUM)
 #endif

 X86_FEATURE_COMPAT(34, FEATURE_AVX512VNNI,      "avx512vnni")
 X86_FEATURE_COMPAT(35, FEATURE_AVX512BITALG,    "avx512bitalg")
 // Features below here are not in libgcc/compiler-rt.
 X86_FEATURE       (64, FEATURE_MOVBE)
 X86_FEATURE       (65, FEATURE_ADX)
 X86_FEATURE       (66, FEATURE_EM64T)
 X86_FEATURE       (67, FEATURE_CLFLUSHOPT)
 X86_FEATURE       (68, FEATURE_SHA)
+X86_FEATURE       (69, FEATURE_AVX512BF16)
 #undef X86_FEATURE_COMPAT
 #undef X86_FEATURE

llvm/trunk/lib/Support/Host.cpp

case 6:
     case 0x9e:              // Kaby Lake desktop
       *Type = X86::INTEL_COREI7; // "skylake"
       *Subtype = X86::INTEL_COREI7_SKYLAKE;
       break;
 
     // Skylake Xeon:
     case 0x55:
       *Type = X86::INTEL_COREI7;
-      if (Features2 & (1 << (X86::FEATURE_AVX512VNNI - 32)))
+      if (Features3 & (1 << (X86::FEATURE_AVX512BF16 - 64)))
+        *Subtype = X86::INTEL_COREI7_COOPERLAKE; // "cooperlake"
+      else if (Features2 & (1 << (X86::FEATURE_AVX512VNNI - 32)))
         *Subtype = X86::INTEL_COREI7_CASCADELAKE; // "cascadelake"
       else
         *Subtype = X86::INTEL_COREI7_SKYLAKE_AVX512; // "skylake-avx512"
       break;
 
     // Cannonlake:
     case 0x66:
       *Type = X86::INTEL_COREI7;
default: // Unknown family 6 CPU, try to guess.
       }
 
       if (Features & (1 << X86::FEATURE_AVX512VBMI)) {
         *Type = X86::INTEL_COREI7;
         *Subtype = X86::INTEL_COREI7_CANNONLAKE;
         break;
       }
 
+      if (Features3 & (1 << (X86::FEATURE_AVX512BF16 - 64))) {
+        *Type = X86::INTEL_COREI7;
+        *Subtype = X86::INTEL_COREI7_COOPERLAKE;
+        break;
+      }
+
       if (Features2 & (1 << (X86::FEATURE_AVX512VNNI - 32))) {
         *Type = X86::INTEL_COREI7;
         *Subtype = X86::INTEL_COREI7_CASCADELAKE;
         break;
       }
 
       if (Features & (1 << X86::FEATURE_AVX512VL)) {
         *Type = X86::INTEL_COREI7;

llvm/trunk/lib/Target/X86/X86.td

def ProcessorFeatures {
   list<SubtargetFeature> CLXAdditionalFeatures = [FeatureVNNI];
   list<SubtargetFeature> CLXSpecificFeatures = [FeatureHasFastGather,
                                                 FeaturePOPCNTFalseDeps];
   list<SubtargetFeature> CLXInheritableFeatures =
     !listconcat(SKXInheritableFeatures, CLXAdditionalFeatures);
   list<SubtargetFeature> CLXFeatures =
     !listconcat(CLXInheritableFeatures, CLXSpecificFeatures);
 
+  // Cooperlake
+  list<SubtargetFeature> CPXAdditionalFeatures = [FeatureBF16];
+  list<SubtargetFeature> CPXSpecificFeatures = [FeatureHasFastGather,
+                                                FeaturePOPCNTFalseDeps];
+  list<SubtargetFeature> CPXInheritableFeatures =
+    !listconcat(CLXInheritableFeatures, CPXAdditionalFeatures);
+  list<SubtargetFeature> CPXFeatures =
+    !listconcat(CPXInheritableFeatures, CPXSpecificFeatures);
+
   // Cannonlake
   list<SubtargetFeature> CNLAdditionalFeatures = [FeatureAVX512,
                                                   FeatureCDI,
                                                   FeatureDQI,
                                                   FeatureBWI,
                                                   FeatureVLX,
                                                   FeaturePKU,
                                                   FeatureVBMI,

 def : ProcessorModel<"knm", HaswellModel, ProcessorFeatures.KNMFeatures>;
 
 foreach P = ["skylake-avx512", "skx"] in {
   def : ProcessorModel<P, SkylakeServerModel, ProcessorFeatures.SKXFeatures>;
 }
 
 def : ProcessorModel<"cascadelake", SkylakeServerModel,
                      ProcessorFeatures.CLXFeatures>;
+def : ProcessorModel<"cooperlake", SkylakeServerModel,
+                     ProcessorFeatures.CPXFeatures>;
 def : ProcessorModel<"cannonlake", SkylakeServerModel,
                      ProcessorFeatures.CNLFeatures>;
 def : ProcessorModel<"icelake-client", SkylakeServerModel,
                      ProcessorFeatures.ICLFeatures>;
 def : ProcessorModel<"icelake-server", SkylakeServerModel,
                      ProcessorFeatures.ICXFeatures>;
 
 // AMD CPUs.

llvm/trunk/test/CodeGen/X86/cpus-intel.ll

 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=core-avx-i 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=haswell 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=core-avx2 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=broadwell 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=skylake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=skylake-avx512 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=skx 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=cascadelake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
+; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=cooperlake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=cannonlake 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=icelake-client 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=icelake-server 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=atom 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=bonnell 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=silvermont 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=slm 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=goldmont 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=goldmont-plus 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=tremont 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=knl 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 ; RUN: llc < %s -o /dev/null -mtriple=x86_64-unknown-unknown -mcpu=knm 2>&1 | FileCheck %s --check-prefix=CHECK-NO-ERROR --allow-empty
 
 define void @foo() {
   ret void
 }