[clang] 6b1341e - [PowerPC] [Clang] Fix alignment of 128-bit float types

[Qiu Chaofan via cfe-commits]

Author: Qiu Chaofan
Date: 2020-11-19T14:22:14+08:00
New Revision: 6b1341eb5bb71a1ce4547165a247b23bb30ef44e

URL: https://github.com/llvm/llvm-project/commit/6b1341eb5bb71a1ce4547165a247b23bb30ef44e
DIFF: https://github.com/llvm/llvm-project/commit/6b1341eb5bb71a1ce4547165a247b23bb30ef44e.diff

LOG: [PowerPC] [Clang] Fix alignment of 128-bit float types

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 PowerPC.

This patch will fix incorrectness of IEEE 128-bit float argument in
va_arg cases.

Reviewed By: rjmccall

Differential Revision: https://reviews.llvm.org/D91596

Added: 
    clang/test/CodeGen/ppc64le-varargs-f128.c

Modified: 
    clang/lib/CodeGen/TargetInfo.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index a98e4095b074..64240b1bde20 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -5051,6 +5051,11 @@ CharUnits PPC64_SVR4_ABIInfo::getParamTypeAlignment(QualType Ty) const {
     return CharUnits::fromQuantity(16);
   } else if (Ty->isVectorType()) {
     return CharUnits::fromQuantity(getContext().getTypeSize(Ty) == 128 ? 16 : 8);
+  } else if (Ty->isRealFloatingType() && getContext().getTypeSize(Ty) == 128) {
+    // 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(16);
   }
 
   // For single-element float/vector structs, we consider the whole type

diff  --git a/clang/test/CodeGen/ppc64le-varargs-f128.c b/clang/test/CodeGen/ppc64le-varargs-f128.c
new file mode 100644
index 000000000000..6562fe6f8fe4
--- /dev/null
+++ b/clang/test/CodeGen/ppc64le-varargs-f128.c
@@ -0,0 +1,49 @@
+// RUN: %clang_cc1 -triple powerpc64le-unknown-linux-gnu -emit-llvm \
+// RUN:   -target-cpu pwr9 -target-feature +float128 -mabi=ieeelongdouble \
+// RUN:   -o - %s | FileCheck %s -check-prefix=IEEE
+// RUN: %clang_cc1 -triple powerpc64le-unknown-linux-gnu -emit-llvm \
+// RUN:   -target-cpu pwr9 -target-feature +float128 \
+// RUN:   -o - %s | FileCheck %s -check-prefix=IBM
+
+#include <stdarg.h>
+
+// IEEE-LABEL: define fp128 @f128(i32 signext %n, ...)
+// IEEE: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
+// 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;
+  va_start(ap, n);
+  __float128 x = va_arg(ap, __float128);
+  va_end(ap);
+  return x;
+}
+
+// IEEE-LABEL: define fp128 @long_double(i32 signext %n, ...)
+// IEEE: call void @llvm.va_start(i8* %{{[0-9a-zA-Z_.]+}})
+// 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: %[[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;
+  va_start(ap, n);
+  long double x = va_arg(ap, long double);
+  va_end(ap);
+  return x;
+}