[llvm-branch-commits] [clang] [llvm] release/19.x: [AArch64] Make apple-m4 armv8.7-a again (from armv9.2-a). (PR #106599)

[Tobias Hieta via llvm-branch-commits]

https://github.com/tru updated https://github.com/llvm/llvm-project/pull/106599

>From eba1ef5a1b7a84ed1954797dcd6d6f073b1f1a56 Mon Sep 17 00:00:00 2001
From: Ahmed Bougacha <ahmed at bougacha.org>
Date: Thu, 29 Aug 2024 09:50:44 -0700
Subject: [PATCH] [AArch64] Make apple-m4 armv8.7-a again (from armv9.2-a). 
 (#106312)

This is a partial revert of c66e1d6f3429.  Even though that
allowed us to declare v9.2-a support without picking up SVE2
in both the backend and the driver, the frontend itself still
enabled SVE via the arch version's default extensions.

Avoid that by reverting back to v8.7-a while we look into
longer-term solutions.

(cherry picked from commit e5e38ddf1b8043324175868831da21e941c00aff)
---
 clang/test/CodeGen/aarch64-targetattr.c          | 9 +++++++++
 llvm/lib/Target/AArch64/AArch64Processors.td     | 7 ++++++-
 llvm/unittests/TargetParser/TargetParserTest.cpp | 2 +-
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/clang/test/CodeGen/aarch64-targetattr.c b/clang/test/CodeGen/aarch64-targetattr.c
index d6227be2ebef83..a5f94b46cbb172 100644
--- a/clang/test/CodeGen/aarch64-targetattr.c
+++ b/clang/test/CodeGen/aarch64-targetattr.c
@@ -191,6 +191,14 @@ __attribute__((target("no-v9.3a")))
 //
 void minusarch() {}
 
+__attribute__((target("cpu=apple-m4")))
+// CHECK-LABEL: define {{[^@]+}}@applem4
+// CHECK-SAME: () #[[ATTR18:[0-9]+]] {
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    ret void
+//
+void applem4() {}
+
 //.
 // CHECK: attributes #[[ATTR0]] = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+crc,+fp-armv8,+lse,+neon,+ras,+rdm,+v8.1a,+v8.2a,+v8a" }
 // CHECK: attributes #[[ATTR1]] = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+crc,+fp-armv8,+fullfp16,+lse,+neon,+ras,+rdm,+sve,+v8.1a,+v8.2a,+v8a" }
@@ -210,6 +218,7 @@ void minusarch() {}
 // CHECK: attributes #[[ATTR15]] = { noinline nounwind optnone "branch-target-enforcement" "guarded-control-stack" "no-trapping-math"="true" "sign-return-address"="non-leaf" "sign-return-address-key"="a_key" "stack-protector-buffer-size"="8" "target-cpu"="neoverse-n1" "target-features"="+aes,+bf16,+bti,+ccidx,+complxnum,+crc,+dit,+dotprod,+flagm,+fp-armv8,+fullfp16,+i8mm,+jsconv,+lse,+neon,+pauth,+perfmon,+predres,+ras,+rcpc,+rdm,+sb,+sha2,+spe,+ssbs,+sve,+sve2,+v8.1a,+v8.2a,+v8.3a,+v8.4a,+v8.5a,+v8.6a,+v8a" "tune-cpu"="cortex-a710" }
 // CHECK: attributes #[[ATTR16]] = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
 // CHECK: attributes #[[ATTR17]] = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="-v9.3a" }
+// CHECK: attributes #[[ATTR18]] = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="apple-m4" "target-features"="+aes,+bf16,+bti,+ccidx,+complxnum,+crc,+dit,+dotprod,+flagm,+fp-armv8,+fp16fml,+fullfp16,+i8mm,+jsconv,+lse,+neon,+pauth,+perfmon,+predres,+ras,+rcpc,+rdm,+sb,+sha2,+sha3,+sme,+sme-f64f64,+sme-i16i64,+sme2,+ssbs,+v8.1a,+v8.2a,+v8.3a,+v8.4a,+v8.5a,+v8.6a,+v8.7a,+v8a,+wfxt" }
 //.
 // CHECK: [[META0:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
 // CHECK: [[META1:![0-9]+]] = !{!"{{.*}}clang version {{.*}}"}
diff --git a/llvm/lib/Target/AArch64/AArch64Processors.td b/llvm/lib/Target/AArch64/AArch64Processors.td
index 6df87fc6a815f7..410b53e14de22e 100644
--- a/llvm/lib/Target/AArch64/AArch64Processors.td
+++ b/llvm/lib/Target/AArch64/AArch64Processors.td
@@ -895,7 +895,12 @@ def ProcessorFeatures {
                                      FeatureLSE, FeaturePAuth,
                                      FeatureRAS, FeatureRCPC, FeatureRDM,
                                      FeatureBF16, FeatureDotProd, FeatureMatMulInt8, FeatureSSBS];
-  list<SubtargetFeature> AppleM4 = [HasV9_2aOps, FeatureSHA2, FeatureFPARMv8,
+  // Technically apple-m4 is v9.2a, but we can't use that here.
+  // Historically, llvm defined v9.0a as requiring SVE, but it's optional
+  // according to the Arm ARM, and not supported by the core.  We decoupled the
+  // two in the clang driver and in the backend subtarget features, but it's
+  // still an issue in the clang frontend.  v8.7a is the next closest choice.
+  list<SubtargetFeature> AppleM4 = [HasV8_7aOps, FeatureSHA2, FeatureFPARMv8,
                                     FeatureNEON, FeaturePerfMon, FeatureSHA3,
                                     FeatureFullFP16, FeatureFP16FML,
                                     FeatureAES, FeatureBF16,
diff --git a/llvm/unittests/TargetParser/TargetParserTest.cpp b/llvm/unittests/TargetParser/TargetParserTest.cpp
index dcbbc68332c799..11a28603674137 100644
--- a/llvm/unittests/TargetParser/TargetParserTest.cpp
+++ b/llvm/unittests/TargetParser/TargetParserTest.cpp
@@ -1638,7 +1638,7 @@ INSTANTIATE_TEST_SUITE_P(
              AArch64::AEK_I8MM,    AArch64::AEK_JSCVT,   AArch64::AEK_FCMA,
              AArch64::AEK_PAUTH,   AArch64::AEK_PERFMON, AArch64::AEK_HCX,
              AArch64::AEK_SSBS}),
-        AArch64CPUTestParams("apple-m4", "armv9.2-a",
+        AArch64CPUTestParams("apple-m4", "armv8.7-a",
                              {AArch64::AEK_CRC,       AArch64::AEK_AES,
                               AArch64::AEK_SHA2,      AArch64::AEK_SHA3,
                               AArch64::AEK_FP,        AArch64::AEK_SIMD,