[PATCH] D91596: [PowerPC] [Clang] Fix alignment of 128-bit floating types

[Qiu Chaofan via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG6b1341eb5bb7: [PowerPC] [Clang] Fix alignment of 128-bit float types (authored by qiucf).

Changed prior to commit:
  https://reviews.llvm.org/D91596?vs=305692&id=306315#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D91596/new/

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
===================================================================
--- /dev/null
+++ 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;
+}
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -5051,6 +5051,11 @@
     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


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D91596.306315.patch
Type: text/x-patch
Size: 3148 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20201119/bd3c4023/attachment.bin>