[clang] [llvm] [AArch64][FMV] Add missing feature dependencies and detect at runtime. (PR #119231)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 9 08:51:47 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
@llvm/pr-subscribers-backend-aarch64
Author: Alexandros Lamprineas (labrinea)
<details>
<summary>Changes</summary>
i8mm -> simd
fp16fml -> simd
frintts -> fp
bf16 -> simd
sme -> fp16
Approved in ACLE as https://github.com/ARM-software/acle/pull/368
---
Patch is 63.25 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119231.diff
15 Files Affected:
- (modified) clang/test/CodeGen/AArch64/cpu-supports.c (+4-4)
- (modified) clang/test/CodeGen/AArch64/fmv-dependencies.c (+4-4)
- (modified) clang/test/CodeGen/AArch64/mixed-target-attributes.c (+16-16)
- (modified) clang/test/CodeGen/attr-target-clones-aarch64.c (+44-44)
- (modified) clang/test/CodeGen/attr-target-version.c (+60-60)
- (modified) clang/test/CodeGenCXX/attr-target-clones-aarch64.cpp (+12-12)
- (modified) clang/test/CodeGenCXX/attr-target-version.cpp (+10-10)
- (modified) clang/test/CodeGenCXX/fmv-namespace.cpp (+2-2)
- (modified) llvm/include/llvm/TargetParser/AArch64TargetParser.h (+3)
- (modified) llvm/lib/Target/AArch64/AArch64Features.td (+6-5)
- (modified) llvm/lib/TargetParser/AArch64TargetParser.cpp (+15-7)
- (modified) llvm/test/CodeGen/AArch64/sve-streaming-mode-cvt-fp-int-fp.ll (-16)
- (modified) llvm/test/MC/AArch64/SME/streaming-mode-neon-negative.s (+2-2)
- (modified) llvm/test/MC/AArch64/SME/streaming-sve-feature.s (+1-1)
- (modified) llvm/test/MC/AArch64/armv8a-fpmul.s (+1-27)
``````````diff
diff --git a/clang/test/CodeGen/AArch64/cpu-supports.c b/clang/test/CodeGen/AArch64/cpu-supports.c
index 76fcea0be31581..406201781d4803 100644
--- a/clang/test/CodeGen/AArch64/cpu-supports.c
+++ b/clang/test/CodeGen/AArch64/cpu-supports.c
@@ -18,8 +18,8 @@
// CHECK-NEXT: br label [[RETURN:%.*]]
// CHECK: if.end:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 17867063951360
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 17867063951360
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 17936857268992
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 17936857268992
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[IF_THEN1:%.*]], label [[IF_END2:%.*]]
// CHECK: if.then1:
@@ -27,8 +27,8 @@
// CHECK-NEXT: br label [[RETURN]]
// CHECK: if.end2:
// CHECK-NEXT: [[TMP8:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 171136785840078848
-// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 171136785840078848
+// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 171141184020873984
+// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 171141184020873984
// CHECK-NEXT: [[TMP11:%.*]] = and i1 true, [[TMP10]]
// CHECK-NEXT: br i1 [[TMP11]], label [[IF_THEN3:%.*]], label [[IF_END4:%.*]]
// CHECK: if.then3:
diff --git a/clang/test/CodeGen/AArch64/fmv-dependencies.c b/clang/test/CodeGen/AArch64/fmv-dependencies.c
index f74b7aa32c7dca..3a524b89496e04 100644
--- a/clang/test/CodeGen/AArch64/fmv-dependencies.c
+++ b/clang/test/CodeGen/AArch64/fmv-dependencies.c
@@ -183,10 +183,10 @@ int caller() {
// CHECK: attributes #[[sha2]] = { {{.*}} "target-features"="+fmv,+fp-armv8,+neon,+outline-atomics,+sha2,+v8a"
// CHECK: attributes #[[sha3]] = { {{.*}} "target-features"="+fmv,+fp-armv8,+neon,+outline-atomics,+sha2,+sha3,+v8a"
// CHECK: attributes #[[sm4]] = { {{.*}} "target-features"="+fmv,+fp-armv8,+neon,+outline-atomics,+sm4,+v8a"
-// CHECK: attributes #[[sme]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+neon,+outline-atomics,+sme,+v8a"
-// CHECK: attributes #[[sme_f64f64]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+neon,+outline-atomics,+sme,+sme-f64f64,+v8a"
-// CHECK: attributes #[[sme_i16i64]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+neon,+outline-atomics,+sme,+sme-i16i64,+v8a"
-// CHECK: attributes #[[sme2]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+neon,+outline-atomics,+sme,+sme2,+v8a"
+// CHECK: attributes #[[sme]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sme,+v8a"
+// CHECK: attributes #[[sme_f64f64]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sme,+sme-f64f64,+v8a"
+// CHECK: attributes #[[sme_i16i64]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sme,+sme-i16i64,+v8a"
+// CHECK: attributes #[[sme2]] = { {{.*}} "target-features"="+bf16,+fmv,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sme,+sme2,+v8a"
// CHECK: attributes #[[ssbs]] = { {{.*}} "target-features"="+fmv,+fp-armv8,+neon,+outline-atomics,+ssbs,+v8a"
// CHECK: attributes #[[sve]] = { {{.*}} "target-features"="+fmv,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+v8a"
// CHECK: attributes #[[sve2]] = { {{.*}} "target-features"="+fmv,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve2,+v8a"
diff --git a/clang/test/CodeGen/AArch64/mixed-target-attributes.c b/clang/test/CodeGen/AArch64/mixed-target-attributes.c
index bb6fb7eb8862a2..1ccb0c6177c8c5 100644
--- a/clang/test/CodeGen/AArch64/mixed-target-attributes.c
+++ b/clang/test/CodeGen/AArch64/mixed-target-attributes.c
@@ -66,24 +66,24 @@ __attribute__((target_version("jscvt"))) int default_def_with_version_decls(void
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1048576
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1048576
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1048832
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1048832
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @explicit_default._Mjscvt
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 64
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 64
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 832
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 832
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
// CHECK-NEXT: ret ptr @explicit_default._Mrdm
// CHECK: resolver_else2:
// CHECK-NEXT: [[TMP8:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 16
-// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 16
+// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 784
+// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 784
// CHECK-NEXT: [[TMP11:%.*]] = and i1 true, [[TMP10]]
// CHECK-NEXT: br i1 [[TMP11]], label [[RESOLVER_RETURN3:%.*]], label [[RESOLVER_ELSE4:%.*]]
// CHECK: resolver_return3:
@@ -140,24 +140,24 @@ __attribute__((target_version("jscvt"))) int default_def_with_version_decls(void
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1048576
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1048576
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1048832
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1048832
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @implicit_default._Mjscvt
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 64
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 64
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 832
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 832
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
// CHECK-NEXT: ret ptr @implicit_default._Mrdm
// CHECK: resolver_else2:
// CHECK-NEXT: [[TMP8:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 16
-// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 16
+// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 784
+// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 784
// CHECK-NEXT: [[TMP11:%.*]] = and i1 true, [[TMP10]]
// CHECK-NEXT: br i1 [[TMP11]], label [[RESOLVER_RETURN3:%.*]], label [[RESOLVER_ELSE4:%.*]]
// CHECK: resolver_return3:
@@ -207,16 +207,16 @@ __attribute__((target_version("jscvt"))) int default_def_with_version_decls(void
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1048576
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1048576
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1048832
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1048832
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @default_def_with_version_decls._Mjscvt
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 16
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 16
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 784
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 784
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
diff --git a/clang/test/CodeGen/attr-target-clones-aarch64.c b/clang/test/CodeGen/attr-target-clones-aarch64.c
index 961279424754d5..6b7acbbd4fc597 100644
--- a/clang/test/CodeGen/attr-target-clones-aarch64.c
+++ b/clang/test/CodeGen/attr-target-clones-aarch64.c
@@ -64,16 +64,16 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 32896
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 32896
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 33664
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 33664
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @ftc._MaesMlse
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 68719476736
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 68719476736
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 69793284352
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 69793284352
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
@@ -100,16 +100,16 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 17592186048512
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 17592186048512
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 17592186049280
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 17592186049280
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @ftc_def._MmemtagMsha2
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 4096
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 4096
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 4864
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 4864
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
@@ -129,8 +129,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 4096
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 4096
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 4864
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 4864
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
@@ -157,8 +157,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1040
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1040
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 1808
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 1808
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
@@ -310,16 +310,16 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 549757911040
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 549757911040
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 619551195904
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 619551195904
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @ftc_inline2._MfcmaMsve2-bitperm
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 65536
-// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 65536
+// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 65792
+// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 65792
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
@@ -360,8 +360,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 18014673387388928
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 18014673387388928
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 18014743180706560
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 18014743180706560
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
@@ -376,8 +376,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: ret ptr @ftc_inline1._MpredresMrcpc
// CHECK: resolver_else2:
// CHECK-NEXT: [[TMP8:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 513
-// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 513
+// CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP8]], 769
+// CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 769
// CHECK-NEXT: [[TMP11:%.*]] = and i1 true, [[TMP10]]
// CHECK-NEXT: br i1 [[TMP11]], label [[RESOLVER_RETURN3:%.*]], label [[RESOLVER_ELSE4:%.*]]
// CHECK: resolver_return3:
@@ -411,8 +411,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 70369817919488
-// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 70369817919488
+// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 70369817985280
+// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 70369817985280
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
@@ -521,16 +521,16 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-MTE-BTI-NEXT: resolver_entry:
// CHECK-MTE-BTI-NEXT: call void @__init_cpu_features_resolver()
// CHECK-MTE-BTI-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-MTE-BTI-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 32896
-// CHECK-MTE-BTI-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 32896
+// CHECK-MTE-BTI-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 33664
+// CHECK-MTE-BTI-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 33664
// CHECK-MTE-BTI-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-MTE-BTI-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK-MTE-BTI: resolver_return:
// CHECK-MTE-BTI-NEXT: ret ptr @ftc._MaesMlse
// CHECK-MTE-BTI: resolver_else:
// CHECK-MTE-BTI-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-MTE-BTI-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 68719476736
-// CHECK-MTE-BTI-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 68719476736
+// CHECK-MTE-BTI-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 69793284352
+// CHECK-MTE-BTI-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 69793284352
// CHECK-MTE-BTI-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-MTE-BTI-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK-MTE-BTI: resolver_return1:
@@ -557,16 +557,16 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-MTE-BTI-NEXT: resolver_entry:
// CHECK-MTE-BTI-NEXT: call void @__init_cpu_features_resolver()
// CHECK-MTE-BTI-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-MTE-BTI-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 17592186048512
-// CHECK-MTE-BTI-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 17592186048512
+// CHECK-MTE-BTI-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 17592186049280
+// CHECK-MTE-BTI-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 17592186049280
// CHECK-MTE-BTI-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-MTE-BTI-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK-MTE-BTI: resolver_return:
// CHECK-MTE-BTI-NEXT: ret ptr @ftc_def._MmemtagMsha2
// CHECK-MTE-BTI: resolver_else:
// CHECK-MTE-BTI-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-MTE-BTI-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 4096
-// CHECK-MTE-BTI-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 4096
+// CHECK-MTE-BTI-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 4864
+// CHECK-MTE-BTI-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 4864
// CHECK-MTE-BTI-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-MTE-BTI-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK-MTE-BTI: resolver_return1:
@@ -586,8 +586,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "default"))
// CHECK-MTE-BTI-NEXT: resolver_entry:
// CHECK-MTE-BTI-NEXT: call void @__init_cpu_features_resolver()
// CHECK-MTE-BTI-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
-// CHECK-MTE-BTI-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 4096
-// CHECK-MTE-BTI-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 4096
+// CHECK-MTE-BTI-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 4864
+// CHECK-MTE-BTI-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 4864
// CHECK-MTE-BTI-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-MTE-BTI-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK-MTE-BTI: resolver_return:
@@ -614,8 +614,8 @@ inline int __attribute__((target_clones("fp16", "sve2-bitperm+fcma", "d...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/119231
More information about the llvm-commits
mailing list