[X86][FastIsel] Teach how to select float-half conversion intrinsics.

This patch teaches X86FastISel how to select intrinsic 'convert_from_fp16' and
intrinsic 'convert_to_fp16'.
If the target has F16C, we can select VCVTPS2PHrr for a float-half conversion,
and VCVTPH2PSrr for a half-float conversion.

Differential Revision: http://reviews.llvm.org/D7673

llvm-svn: 230043

2 files changed, 51 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/fast-isel-double-half-convertion.ll b/llvm/test/CodeGen/X86/fast-isel-double-half-convertion.ll
new file mode 100644
index 00000000000..ade867b7d70
--- /dev/null
+++ b/llvm/test/CodeGen/X86/fast-isel-double-half-convertion.ll
@@ -0,0 +1,23 @@
+; RUN: llc -fast-isel -fast-isel-abort -mtriple=x86_64-unknown-unknown -mattr=+f16c < %s
+
+; XFAIL: *
+
+; In the future, we might want to teach fast-isel how to expand a double-to-half
+; conversion into a double-to-float conversion immediately followed by a
+; float-to-half conversion. For now, fast-isel is expected to fail.
+
+define double @test_fp16_to_fp64(i32 %a) {
+entry:
+  %0 = trunc i32 %a to i16
+  %1 = call double @llvm.convert.from.fp16.f64(i16 %0)
+  ret float %0
+}
+
+define i16 @test_fp64_to_fp16(double %a) {
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f64(double %a)
+  ret i16 %0
+}
+
+declare i16 @llvm.convert.to.fp16.f64(double)
+declare double @llvm.convert.from.fp16.f64(i16)
diff --git a/llvm/test/CodeGen/X86/fast-isel-float-half-convertion.ll b/llvm/test/CodeGen/X86/fast-isel-float-half-convertion.ll
new file mode 100644
index 00000000000..ee89bcd2a8b
--- /dev/null
+++ b/llvm/test/CodeGen/X86/fast-isel-float-half-convertion.ll
@@ -0,0 +1,28 @@
+; RUN: llc -fast-isel -fast-isel-abort -asm-verbose=false -mtriple=x86_64-unknown-unknown -mattr=+f16c < %s | FileCheck %s
+
+; Verify that fast-isel correctly expands float-half conversions.
+
+define i16 @test_fp32_to_fp16(float %a) {
+; CHECK-LABEL: test_fp32_to_fp16:
+; CHECK: vcvtps2ph $0, %xmm0, %xmm0
+; CHECK-NEXT: vmovd %xmm0, %eax
+; CHECK-NEXT: retq
+entry:
+  %0 = call i16 @llvm.convert.to.fp16.f32(float %a)
+  ret i16 %0
+}
+
+define float @test_fp16_to_fp32(i32 %a) {
+; CHECK-LABEL: test_fp16_to_fp32:
+; CHECK: movswl %di, %eax
+; CHECK-NEXT: vmovd %eax, %xmm0
+; CHECK-NEXT: vcvtph2ps %xmm0, %xmm0
+; CHECK-NEXT: retq
+entry:
+  %0 = trunc i32 %a to i16
+  %1 = call float @llvm.convert.from.fp16.f32(i16 %0)
+  ret float %1
+}
+
+declare i16 @llvm.convert.to.fp16.f32(float)
+declare float @llvm.convert.from.fp16.f32(i16)