qiucf created this revision.
qiucf added reviewers: jsji, nemanjai, uweigand, PowerPC, steven.zhang,
rjmccall.
Herald added subscribers: cfe-commits, shchenz, kbarton.
Herald added a project: clang.
qiucf requested review of this revision.
According to ELF v2 ABI, both IEEE 128-bit and IBM extended floating point
variables should be quad-word (16 bytes) aligned. Previously, only vector types
are considered aligned as quad-word on Power.
Without this fix, IEEE 128-bit fp will be passed incorrectly in va_arg cases.
(the patch is not patchable since I generated it for easier review, the case is
a new file)
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D91596
Files:
clang/lib/CodeGen/TargetInfo.cpp
clang/test/CodeGen/ppc64le-varargs-f128.c
Index: clang/test/CodeGen/ppc64le-varargs-f128.c
===================================================================
--- clang/test/CodeGen/ppc64le-varargs-f128.c
+++ clang/test/CodeGen/ppc64le-varargs-f128.c
@@ -9,8 +9,11 @@
// IEEE-LABEL: define fp128 @f128(i32 signext %n, ...)
// IEEE: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
-// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %{{[0-9a-zA-Z_.]+}} to fp128*
-// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 8
+// IEEE: %[[P1:[0-9a-zA-Z_.]+]] = add i64 %{{[0-9a-zA-Z_.]+}}, 15
+// IEEE: %[[P2:[0-9a-zA-Z_.]+]] = and i64 %[[P1]], -16
+// IEEE: %[[P3:[0-9a-zA-Z_.]+]] = inttoptr i64 %[[P2]] to i8*
+// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %[[P3]] to fp128*
+// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 16
// IEEE: call void @llvm.va_end(i8* %{{[0-9a-zA-Z_.]+}})
__float128 f128(int n, ...) {
va_list ap;
@@ -22,14 +25,20 @@
// IEEE-LABEL: define fp128 @long_double(i32 signext %n, ...)
// IEEE: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
-// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %{{[0-9a-zA-Z_.]+}} to fp128*
-// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 8
+// IEEE: %[[P1:[0-9a-zA-Z_.]+]] = add i64 %{{[0-9a-zA-Z_.]+}}, 15
+// IEEE: %[[P2:[0-9a-zA-Z_.]+]] = and i64 %[[P1]], -16
+// IEEE: %[[P3:[0-9a-zA-Z_.]+]] = inttoptr i64 %[[P2]] to i8*
+// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %[[P3]] to fp128*
+// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 16
// IEEE: call void @llvm.va_end(i8* %{{[0-9a-zA-Z_.]+}})
// IBM-LABEL: define ppc_fp128 @long_double(i32 signext %n, ...)
// IBM: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
-// IBM: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %{{[0-9a-zA-Z_.]+}} to ppc_fp128*
-// IBM: %{{[0-9a-zA-Z_.]+}} = load ppc_fp128, ppc_fp128* %[[P4]], align 8
+// IBM: %[[P1:[0-9a-zA-Z_.]+]] = add i64 %{{[0-9a-zA-Z_.]+}}, 15
+// IBM: %[[P2:[0-9a-zA-Z_.]+]] = and i64 %[[P1]], -16
+// IBM: %[[P3:[0-9a-zA-Z_.]+]] = inttoptr i64 %[[P2]] to i8*
+// IBM: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %[[P3]] to ppc_fp128*
+// IBM: %{{[0-9a-zA-Z_.]+}} = load ppc_fp128, ppc_fp128* %[[P4]], align 16
// IBM: call void @llvm.va_end(i8* %{{[0-9a-zA-Z_.]+}})
long double long_double(int n, ...) {
va_list ap;
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -5049,7 +5049,10 @@
return CharUnits::fromQuantity(32);
return CharUnits::fromQuantity(16);
- } else if (Ty->isVectorType()) {
+ } else if (Ty->isVectorType() || Ty->isRealFloatingType()) {
+ // IEEE 128-bit floating numbers are also stored in vector registers.
+ // And both IEEE quad-precision and IBM extended double (ppc_fp128) should
+ // be quad-word aligned.
return CharUnits::fromQuantity(getContext().getTypeSize(Ty) == 128 ? 16 :
8);
}
Index: clang/test/CodeGen/ppc64le-varargs-f128.c
===================================================================
--- clang/test/CodeGen/ppc64le-varargs-f128.c
+++ clang/test/CodeGen/ppc64le-varargs-f128.c
@@ -9,8 +9,11 @@
// IEEE-LABEL: define fp128 @f128(i32 signext %n, ...)
// IEEE: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
-// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %{{[0-9a-zA-Z_.]+}} to fp128*
-// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 8
+// IEEE: %[[P1:[0-9a-zA-Z_.]+]] = add i64 %{{[0-9a-zA-Z_.]+}}, 15
+// IEEE: %[[P2:[0-9a-zA-Z_.]+]] = and i64 %[[P1]], -16
+// IEEE: %[[P3:[0-9a-zA-Z_.]+]] = inttoptr i64 %[[P2]] to i8*
+// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %[[P3]] to fp128*
+// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 16
// IEEE: call void @llvm.va_end(i8* %{{[0-9a-zA-Z_.]+}})
__float128 f128(int n, ...) {
va_list ap;
@@ -22,14 +25,20 @@
// IEEE-LABEL: define fp128 @long_double(i32 signext %n, ...)
// IEEE: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
-// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %{{[0-9a-zA-Z_.]+}} to fp128*
-// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 8
+// IEEE: %[[P1:[0-9a-zA-Z_.]+]] = add i64 %{{[0-9a-zA-Z_.]+}}, 15
+// IEEE: %[[P2:[0-9a-zA-Z_.]+]] = and i64 %[[P1]], -16
+// IEEE: %[[P3:[0-9a-zA-Z_.]+]] = inttoptr i64 %[[P2]] to i8*
+// IEEE: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %[[P3]] to fp128*
+// IEEE: %{{[0-9a-zA-Z_.]+}} = load fp128, fp128* %[[P4]], align 16
// IEEE: call void @llvm.va_end(i8* %{{[0-9a-zA-Z_.]+}})
// IBM-LABEL: define ppc_fp128 @long_double(i32 signext %n, ...)
// IBM: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
-// IBM: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %{{[0-9a-zA-Z_.]+}} to ppc_fp128*
-// IBM: %{{[0-9a-zA-Z_.]+}} = load ppc_fp128, ppc_fp128* %[[P4]], align 8
+// IBM: %[[P1:[0-9a-zA-Z_.]+]] = add i64 %{{[0-9a-zA-Z_.]+}}, 15
+// IBM: %[[P2:[0-9a-zA-Z_.]+]] = and i64 %[[P1]], -16
+// IBM: %[[P3:[0-9a-zA-Z_.]+]] = inttoptr i64 %[[P2]] to i8*
+// IBM: %[[P4:[0-9a-zA-Z_.]+]] = bitcast i8* %[[P3]] to ppc_fp128*
+// IBM: %{{[0-9a-zA-Z_.]+}} = load ppc_fp128, ppc_fp128* %[[P4]], align 16
// IBM: call void @llvm.va_end(i8* %{{[0-9a-zA-Z_.]+}})
long double long_double(int n, ...) {
va_list ap;
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -5049,7 +5049,10 @@
return CharUnits::fromQuantity(32);
return CharUnits::fromQuantity(16);
- } else if (Ty->isVectorType()) {
+ } else if (Ty->isVectorType() || Ty->isRealFloatingType()) {
+ // IEEE 128-bit floating numbers are also stored in vector registers.
+ // And both IEEE quad-precision and IBM extended double (ppc_fp128) should
+ // be quad-word aligned.
return CharUnits::fromQuantity(getContext().getTypeSize(Ty) == 128 ? 16 : 8);
}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
