[X86] Add missing features for ivybridge, sandybridge and knl in X86TargetParser.def.

[FreddyYe]

Summary

This is also a pre-commit change for D151696

[RKSimon]

llvm/include/llvm/TargetParser/X86TargetParser.def

262

In X86.td westmere and silvermont also have FeaturePCLMUL

[FreddyYe]

llvm/include/llvm/TargetParser/X86TargetParser.def

262

Yeah, that's what I wanted to mean. The miss for these two are also true, but no tests influenced yet.

[craig.topper]

llvm/include/llvm/TargetParser/X86TargetParser.def

275

double comma before +pclmul

[FreddyYe]

Address comment, thanks review!

[RKSimon]

LGTM - but it would be good to fix silvermont / westmere cases as well with suitable test coverage

[FreddyYe]

In D154209#4466304, @RKSimon wrote:

LGTM - but it would be good to fix silvermont / westmere cases as well with suitable test coverage

Thanks review! After D151696 landed, they can be both fixed and there will be more tests cover such missing like clang/test/Preprocessor/predefined-arch-macros.c. And about cpu_specific test coverage, I'll consider a way to refine.

clang/test/CodeGen/attr-cpuspecific.c

 // LINUX: define{{.*}} void @SingleVersion.S() #[[S:[0-9]+]]
 // WINDOWS: define dso_local void @SingleVersion.S() #[[S:[0-9]+]]
 
 ATTR(cpu_dispatch(ivybridge))
 void SingleVersion(void);
 // LINUX: define weak_odr ptr @SingleVersion.resolver()
 // LINUX: call void @__cpu_indicator_init
 // LINUX: %[[FEAT_INIT:.+]] = load i32, ptr getelementptr inbounds ({ i32, i32, i32, [1 x i32] }, ptr @__cpu_model, i32 0, i32 3, i32 0), align 4
-// LINUX: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 1023
-// LINUX: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 1023
+// LINUX: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 525311
+// LINUX: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 525311
 // LINUX: ret ptr @SingleVersion.S
 // LINUX: call void @llvm.trap
 // LINUX: unreachable
 
 // WINDOWS: define weak_odr dso_local void @SingleVersion() comdat
 // WINDOWS: call void @__cpu_indicator_init()
 // WINDOWS: %[[FEAT_INIT:.+]] = load i32, ptr getelementptr inbounds ({ i32, i32, i32, [1 x i32] }, ptr @__cpu_model, i32 0, i32 3, i32 0), align 4
-// WINDOWS: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 1023
-// WINDOWS: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 1023
+// WINDOWS: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 525311
+// WINDOWS: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 525311
 // WINDOWS: call void @SingleVersion.S()
 // WINDOWS-NEXT: ret void
 // WINDOWS: call void @llvm.trap
 // WINDOWS: unreachable
 
 ATTR(cpu_specific(ivybridge))
 void NotCalled(void){}
 // LINUX: define{{.*}} void @NotCalled.S() #[[S]]
 // WINDOWS: define dso_local void @NotCalled.S() #[[S:[0-9]+]]
 
 // Done before any of the implementations.  Also has an undecorated forward
 // declaration.
 void TwoVersions(void);
 
 ATTR(cpu_dispatch(ivybridge, knl))
 void TwoVersions(void);
 // LINUX: define weak_odr ptr @TwoVersions.resolver()
 // LINUX: call void @__cpu_indicator_init
 // LINUX: %[[FEAT_INIT:.+]] = load i32, ptr getelementptr inbounds ({ i32, i32, i32, [1 x i32] }, ptr @__cpu_model, i32 0, i32 3, i32 0), align 4
-// LINUX: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 58836991
-// LINUX: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 58836991
+// LINUX: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 59754495
+// LINUX: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 59754495
 // LINUX: ret ptr @TwoVersions.Z
 // LINUX: ret ptr @TwoVersions.S
 // LINUX: call void @llvm.trap
 // LINUX: unreachable
 
 // WINDOWS: define weak_odr dso_local void @TwoVersions() comdat
 // WINDOWS: call void @__cpu_indicator_init()
 // WINDOWS: %[[FEAT_INIT:.+]] = load i32, ptr getelementptr inbounds ({ i32, i32, i32, [1 x i32] }, ptr @__cpu_model, i32 0, i32 3, i32 0), align 4
-// WINDOWS: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 58836991
-// WINDOWS: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 58836991
+// WINDOWS: %[[FEAT_JOIN:.+]] = and i32 %[[FEAT_INIT]], 59754495
+// WINDOWS: %[[FEAT_CHECK:.+]] = icmp eq i32 %[[FEAT_JOIN]], 59754495
 // WINDOWS: call void @TwoVersions.Z()
 // WINDOWS-NEXT: ret void
 // WINDOWS: call void @TwoVersions.S()
 // WINDOWS-NEXT: ret void
 // WINDOWS: call void @llvm.trap
 // WINDOWS: unreachable
 
 ATTR(cpu_specific(ivybridge))

 // LINUX: ret i32 1
 
 // WINDOWS: define dso_local i32 @DispatchFirst.B
 // WINDOWS: ret i32 1
 
 ATTR(cpu_specific(knl))
 void OrderDispatchUsageSpecific(void) {}
 
-// CHECK: attributes #[[S]] = {{.*}}"target-features"="+avx,+cmov,+crc32,+cx8,+f16c,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
+// CHECK: attributes #[[S]] = {{.*}}"target-features"="+avx,+cmov,+crc32,+cx8,+f16c,+mmx,+pclmul,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
 // CHECK-SAME: "tune-cpu"="ivybridge"
-// CHECK: attributes #[[K]] = {{.*}}"target-features"="+adx,+avx,+avx2,+avx512cd,+avx512er,+avx512f,+avx512pf,+bmi,+cmov,+crc32,+cx8,+f16c,+fma,+lzcnt,+mmx,+movbe,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
+// CHECK: attributes #[[K]] = {{.*}}"target-features"="+adx,+aes,+avx,+avx2,+avx512cd,+avx512er,+avx512f,+avx512pf,+bmi,+bmi2,+cmov,+crc32,+cx8,+f16c,+fma,+lzcnt,+mmx,+movbe,+pclmul,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave"
 // CHECK-SAME: "tune-cpu"="knl"
 // CHECK: attributes #[[O]] = {{.*}}"target-features"="+cmov,+cx8,+mmx,+movbe,+sse,+sse2,+sse3,+ssse3,+x87"
 // CHECK-SAME: "tune-cpu"="atom"

llvm/include/llvm/TargetParser/X86TargetParser.def

 CPU_SPECIFIC("pentium_4", "pentium4", 'J', "+cmov,+mmx,+sse,+sse2")
 CPU_SPECIFIC("pentium_m", "pentium-m", 'K', "+cmov,+mmx,+sse,+sse2")
 CPU_SPECIFIC("pentium_4_sse3", "prescott", 'L', "+cmov,+mmx,+sse,+sse2,+sse3")
 CPU_SPECIFIC("core_2_duo_ssse3", "core2", 'M', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3")
 CPU_SPECIFIC("core_2_duo_sse4_1", "penryn", 'N', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1")
 CPU_SPECIFIC("atom", "atom", 'O', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+movbe")
 CPU_SPECIFIC("atom_sse4_2", "silvermont", 'c', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt")
 CPU_SPECIFIC("core_i7_sse4_2", "nehalem", 'P', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt")
 CPU_SPECIFIC("core_aes_pclmulqdq", "westmere", 'Q', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt")
 CPU_SPECIFIC("atom_sse4_2_movbe", "silvermont", 'd', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt")
 CPU_SPECIFIC("goldmont", "goldmont", 'i', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt")
-CPU_SPECIFIC("sandybridge", "sandybridge", 'R', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt,+avx")
+CPU_SPECIFIC("sandybridge", "sandybridge", 'R', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt,+avx,+pclmul")
 CPU_SPECIFIC_ALIAS("core_2nd_gen_avx", "sandybridge", "sandybridge")
-CPU_SPECIFIC("ivybridge", "ivybridge", 'S', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt,+f16c,+avx")
+CPU_SPECIFIC("ivybridge", "ivybridge", 'S', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+popcnt,+f16c,+avx,+pclmul")
 CPU_SPECIFIC_ALIAS("core_3rd_gen_avx", "ivybridge", "ivybridge")
 CPU_SPECIFIC("haswell", "haswell", 'V', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2")
 CPU_SPECIFIC_ALIAS("core_4th_gen_avx", "haswell", "haswell")
 CPU_SPECIFIC("core_4th_gen_avx_tsx", "haswell", 'W', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2")
 CPU_SPECIFIC("broadwell", "broadwell", 'X', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+adx")
 CPU_SPECIFIC_ALIAS("core_5th_gen_avx", "broadwell", "broadwell")
 CPU_SPECIFIC("core_5th_gen_avx_tsx", "broadwell", 'Y', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+adx")
-CPU_SPECIFIC("knl", "knl", 'Z', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+avx512f,+adx,+avx512er,+avx512pf,+avx512cd")
+CPU_SPECIFIC("knl", "knl", 'Z', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+avx512f,+adx,+avx512er,+avx512pf,+avx512cd,+pclmul,+bmi2,+aes")
 CPU_SPECIFIC_ALIAS("mic_avx512", "knl", "knl")
 CPU_SPECIFIC("skylake", "skylake", 'b', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+adx,+mpx")
 CPU_SPECIFIC( "skylake_avx512", "skylake-avx512", 'a', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+avx512dq,+avx512f,+adx,+avx512cd,+avx512bw,+avx512vl,+clwb")
 CPU_SPECIFIC("cannonlake", "cannonlake", 'e', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+avx512dq,+avx512f,+adx,+avx512ifma,+avx512cd,+avx512bw,+avx512vl,+avx512vbmi")
 CPU_SPECIFIC("knm", "knm", 'j', "+cmov,+mmx,+sse,+sse2,+sse3,+ssse3,+sse4.1,+sse4.2,+movbe,+popcnt,+f16c,+avx,+fma,+bmi,+lzcnt,+avx2,+avx512f,+adx,+avx512er,+avx512pf,+avx512cd,+avx5124fmaps,+avx5124vnniw,+avx512vpopcntdq")
 
 #undef CPU_SPECIFIC_ALIAS
 #undef CPU_SPECIFIC