Add PPC FP rounding instructions fri[mnpz]

These instructions are available on the P5x (and later) and on the A2. They
implement the standard floating-point rounding operations (floor, trunc, etc.).
One caveat: frin (round to nearest) does not implement "ties to even", and so
is only enabled in fast-math mode.

llvm-svn: 178337

2 files changed, 126 insertions, 18 deletions

diff --git a/llvm/test/CodeGen/PowerPC/rounding-ops.ll b/llvm/test/CodeGen/PowerPC/rounding-ops.ll
new file mode 100644
index 00000000000..8177a48a60c
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/rounding-ops.ll
@@ -0,0 +1,108 @@
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 | FileCheck %s
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -enable-unsafe-fp-math | FileCheck -check-prefix=CHECK-FM %s
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define float @test1(float %x) nounwind  {
+  %call = tail call float @floorf(float %x) nounwind readnone
+  ret float %call
+
+; CHECK: test1:
+; CHECK: frim 1, 1
+
+; CHECK-FM: test1:
+; CHECK-FM: frim 1, 1
+}
+
+declare float @floorf(float) nounwind readnone
+
+define double @test2(double %x) nounwind  {
+  %call = tail call double @floor(double %x) nounwind readnone
+  ret double %call
+
+; CHECK: test2:
+; CHECK: frim 1, 1
+
+; CHECK-FM: test2:
+; CHECK-FM: frim 1, 1
+}
+
+declare double @floor(double) nounwind readnone
+
+define float @test3(float %x) nounwind  {
+  %call = tail call float @nearbyintf(float %x) nounwind readnone
+  ret float %call
+
+; CHECK: test3:
+; CHECK-NOT: frin
+
+; CHECK-FM: test3:
+; CHECK-FM: frin 1, 1
+}
+
+declare float @nearbyintf(float) nounwind readnone
+
+define double @test4(double %x) nounwind  {
+  %call = tail call double @nearbyint(double %x) nounwind readnone
+  ret double %call
+
+; CHECK: test4:
+; CHECK-NOT: frin
+
+; CHECK-FM: test4:
+; CHECK-FM: frin 1, 1
+}
+
+declare double @nearbyint(double) nounwind readnone
+
+define float @test5(float %x) nounwind  {
+  %call = tail call float @ceilf(float %x) nounwind readnone
+  ret float %call
+
+; CHECK: test5:
+; CHECK: frip 1, 1
+
+; CHECK-FM: test5:
+; CHECK-FM: frip 1, 1
+}
+
+declare float @ceilf(float) nounwind readnone
+
+define double @test6(double %x) nounwind  {
+  %call = tail call double @ceil(double %x) nounwind readnone
+  ret double %call
+
+; CHECK: test6:
+; CHECK: frip 1, 1
+
+; CHECK-FM: test6:
+; CHECK-FM: frip 1, 1
+}
+
+declare double @ceil(double) nounwind readnone
+
+define float @test9(float %x) nounwind  {
+  %call = tail call float @truncf(float %x) nounwind readnone
+  ret float %call
+
+; CHECK: test9:
+; CHECK: friz 1, 1
+
+; CHECK-FM: test9:
+; CHECK-FM: friz 1, 1
+}
+
+declare float @truncf(float) nounwind readnone
+
+define double @test10(double %x) nounwind  {
+  %call = tail call double @trunc(double %x) nounwind readnone
+  ret double %call
+
+; CHECK: test10:
+; CHECK: friz 1, 1
+
+; CHECK-FM: test10:
+; CHECK-FM: friz 1, 1
+}
+
+declare double @trunc(double) nounwind readnone
diff --git a/llvm/test/CodeGen/PowerPC/vec_rounding.ll b/llvm/test/CodeGen/PowerPC/vec_rounding.ll
index f41faa0339a..7c55638620a 100644
--- a/llvm/test/CodeGen/PowerPC/vec_rounding.ll
+++ b/llvm/test/CodeGen/PowerPC/vec_rounding.ll
@@ -13,8 +13,8 @@ define <2 x double> @floor_v2f64(<2 x double> %p)
   ret <2 x double> %t
 }
 ; CHECK: floor_v2f64:
-; CHECK: bl floor
-; CHECK: bl floor
+; CHECK: frim
+; CHECK: frim
 
 declare <4 x double> @llvm.floor.v4f64(<4 x double> %p)
 define <4 x double> @floor_v4f64(<4 x double> %p)
@@ -23,10 +23,10 @@ define <4 x double> @floor_v4f64(<4 x double> %p)
   ret <4 x double> %t
 }
 ; CHECK: floor_v4f64:
-; CHECK: bl floor
-; CHECK: bl floor
-; CHECK: bl floor
-; CHECK: bl floor
+; CHECK: frim
+; CHECK: frim
+; CHECK: frim
+; CHECK: frim
 
 declare <2 x double> @llvm.ceil.v2f64(<2 x double> %p)
 define <2 x double> @ceil_v2f64(<2 x double> %p)
@@ -35,8 +35,8 @@ define <2 x double> @ceil_v2f64(<2 x double> %p)
   ret <2 x double> %t
 }
 ; CHECK: ceil_v2f64:
-; CHECK: bl ceil
-; CHECK: bl ceil
+; CHECK: frip
+; CHECK: frip
 
 declare <4 x double> @llvm.ceil.v4f64(<4 x double> %p)
 define <4 x double> @ceil_v4f64(<4 x double> %p)
@@ -45,10 +45,10 @@ define <4 x double> @ceil_v4f64(<4 x double> %p)
   ret <4 x double> %t
 }
 ; CHECK: ceil_v4f64:
-; CHECK: bl ceil
-; CHECK: bl ceil
-; CHECK: bl ceil
-; CHECK: bl ceil
+; CHECK: frip
+; CHECK: frip
+; CHECK: frip
+; CHECK: frip
 
 declare <2 x double> @llvm.trunc.v2f64(<2 x double> %p)
 define <2 x double> @trunc_v2f64(<2 x double> %p)
@@ -57,8 +57,8 @@ define <2 x double> @trunc_v2f64(<2 x double> %p)
   ret <2 x double> %t
 }
 ; CHECK: trunc_v2f64:
-; CHECK: bl trunc
-; CHECK: bl trunc
+; CHECK: friz
+; CHECK: friz
 
 declare <4 x double> @llvm.trunc.v4f64(<4 x double> %p)
 define <4 x double> @trunc_v4f64(<4 x double> %p)
@@ -67,10 +67,10 @@ define <4 x double> @trunc_v4f64(<4 x double> %p)
   ret <4 x double> %t
 }
 ; CHECK: trunc_v4f64:
-; CHECK: bl trunc
-; CHECK: bl trunc
-; CHECK: bl trunc
-; CHECK: bl trunc
+; CHECK: friz
+; CHECK: friz
+; CHECK: friz
+; CHECK: friz
 
 declare <2 x double> @llvm.nearbyint.v2f64(<2 x double> %p)
 define <2 x double> @nearbyint_v2f64(<2 x double> %p)