From 56a5661c60d2a5b9713c3416b15e048d43e34a27 Mon Sep 17 00:00:00 2001
From: Andrea Di Biagio <Andrea_DiBiagio@sn.scee.net>
Date: Thu, 14 May 2015 18:01:48 +0000
Subject: [PATCH] [ConstantFolding] Fix wrong folding of intrinsic
 'convert.from.fp16'.

Function 'ConstantFoldScalarCall' (in ConstantFolding.cpp) works under the
wrong assumption that a call to 'convert.from.fp16' returns a value of
type 'float'.
However, intrinsic 'convert.from.fp16' can be overloaded; for example, we
can call 'convert.from.fp16.f64' to convert from half to double; etc.

Before this patch, the following example would have triggered an assertion
failure in opt (with -constprop):

```
define double @foo() {
entry:
  %0 = call double @llvm.convert.from.fp16.f64(i16 0)
  ret double %0
}
```

This patch fixes the problem in ConstantFolding.cpp. When folding a call to
convert.from.fp16, we perform a different kind of conversion based on the call
return type.

Added test 'Transform/ConstProp/convert-from-fp16.ll'.

Differential Revision: http://reviews.llvm.org/D9771


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237377 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Analysis/ConstantFolding.cpp              |  4 +-
 .../Transforms/ConstProp/convert-from-fp16.ll | 97 +++++++++++++++++++
 2 files changed, 99 insertions(+), 2 deletions(-)
 create mode 100644 test/Transforms/ConstProp/convert-from-fp16.ll

diff --git a/lib/Analysis/ConstantFolding.cpp b/lib/Analysis/ConstantFolding.cpp
index 85a66331108..2f4c6a92f9a 100644
--- a/lib/Analysis/ConstantFolding.cpp
+++ b/lib/Analysis/ConstantFolding.cpp
@@ -1543,8 +1543,8 @@ static Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID,
         APFloat Val(APFloat::IEEEhalf, Op->getValue());
 
         bool lost = false;
-        APFloat::opStatus status =
-          Val.convert(APFloat::IEEEsingle, APFloat::rmNearestTiesToEven, &lost);
+        APFloat::opStatus status = Val.convert(
+            Ty->getFltSemantics(), APFloat::rmNearestTiesToEven, &lost);
 
         // Conversion is always precise.
         (void)status;
diff --git a/test/Transforms/ConstProp/convert-from-fp16.ll b/test/Transforms/ConstProp/convert-from-fp16.ll
new file mode 100644
index 00000000000..bb903231317
--- /dev/null
+++ b/test/Transforms/ConstProp/convert-from-fp16.ll
@@ -0,0 +1,97 @@
+; RUN: opt -constprop -S < %s | FileCheck %s
+
+; Verify that we don't crash with an assertion failure when constant folding
+; a call to intrinsic 'convert.from.fp16' if the return type is not 'float'.
+
+define float @fold_from_fp16_to_fp32() {
+; CHECK-LABEL: @fold_from_fp16_to_fp32
+; CHECK: ret float 0.000000e+00
+entry:
+  %0 = call float @llvm.convert.from.fp16.f32(i16 0)
+  ret float %0
+}
+
+define double @fold_from_fp16_to_fp64() {
+; CHECK-LABEL: @fold_from_fp16_to_fp64
+; CHECK: ret double 0.000000e+00
+entry:
+  %0 = call double @llvm.convert.from.fp16.f64(i16 0)
+  ret double %0
+}
+
+define x86_fp80 @fold_from_fp16_to_fp80() {
+; CHECK-LABEL: @fold_from_fp16_to_fp80
+; CHECK: ret x86_fp80 0xK00000000000000000000
+entry:
+  %0 = call x86_fp80 @llvm.convert.from.fp16.f80(i16 0)
+  ret x86_fp80 %0
+}
+
+define fp128 @fold_from_fp16_to_fp128() {
+; CHECK-LABEL: @fold_from_fp16_to_fp128
+; CHECK: ret fp128 0xL00000000000000000000000000000000
+entry:
+  %0 = call fp128 @llvm.convert.from.fp16.f128(i16 0)
+  ret fp128 %0
+}
+
+define ppc_fp128 @fold_from_fp16_to_ppcfp128() {
+; CHECK-LABEL: @fold_from_fp16_to_ppcfp128
+; CHECK: ret ppc_fp128 0xM00000000000000000000000000000000
+entry:
+  %0 = call ppc_fp128 @llvm.convert.from.fp16.ppcf128(i16 0)
+  ret ppc_fp128 %0
+}
+
+define float @fold_from_fp16_to_fp32_b() {
+; CHECK-LABEL: @fold_from_fp16_to_fp32_b
+; CHECK: ret float 4.000000e+00
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
+  %1 = call float @llvm.convert.from.fp16.f32(i16 %0)
+  ret float %1
+}
+
+define double @fold_from_fp16_to_fp64_b() {
+; CHECK-LABEL: @fold_from_fp16_to_fp64_b
+; CHECK: ret double 4.000000e+00
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
+  %1 = call double @llvm.convert.from.fp16.f64(i16 %0)
+  ret double %1
+}
+
+define x86_fp80 @fold_from_fp16_to_fp80_b() {
+; CHECK-LABEL: @fold_from_fp16_to_fp80_b
+; CHECK: ret x86_fp80 0xK40018000000000000000
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
+  %1 = call x86_fp80 @llvm.convert.from.fp16.f80(i16 %0)
+  ret x86_fp80 %1
+}
+
+define fp128 @fold_from_fp16_to_fp128_b() {
+; CHECK-LABEL: @fold_from_fp16_to_fp128_b
+; CHECK: ret fp128 0xL00000000000000004001000000000000
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
+  %1 = call fp128 @llvm.convert.from.fp16.f128(i16 %0)
+  ret fp128 %1
+}
+
+define ppc_fp128 @fold_from_fp16_to_ppcfp128_b() {
+; CHECK-LABEL: @fold_from_fp16_to_ppcfp128_b
+; CHECK: ret ppc_fp128 0xM40100000000000000000000000000000
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f64(double 4.0)
+  %1 = call ppc_fp128 @llvm.convert.from.fp16.ppcf128(i16 %0)
+  ret ppc_fp128 %1
+}
+
+
+declare i16 @llvm.convert.to.fp16.f64(double)
+declare float @llvm.convert.from.fp16.f32(i16)
+declare double @llvm.convert.from.fp16.f64(i16)
+declare x86_fp80 @llvm.convert.from.fp16.f80(i16)
+declare fp128 @llvm.convert.from.fp16.f128(i16)
+declare ppc_fp128 @llvm.convert.from.fp16.ppcf128(i16)
-- 
2.34.1