summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPirama Arumuga Nainar <pirama@google.com>2015-04-20 20:15:36 +0000
committerPirama Arumuga Nainar <pirama@google.com>2015-04-20 20:15:36 +0000
commit9d1b182f81ace33ef41120726501de04aada023a (patch)
treee5d61accddd915d5f89b24cf5bcce8c767f3e711
parent4eccd9814fbb8303d5d2817843a2d7038d5f1167 (diff)
[MIPS] OperationAction for FP_TO_FP16, FP16_TO_FP
Summary: Set operation action for FP16 conversion opcodes, so the Op legalizer can choose the gnu_* libcalls for Mips. Set LoadExtAction and TruncStoreAction for f16 scalars and vectors to prevent (fpext (load )) and (store (fptrunc)) from getting combined into unsupported operations. Added test cases to test that these operations are handled correctly for f16 scalars and vectors. This patch depends on http://reviews.llvm.org/D8755. Reviewers: srhines Subscribers: llvm-commits, ab Differential Revision: http://reviews.llvm.org/D8804 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@235341 91177308-0d34-0410-b5e6-96231b3b80d8
-rw-r--r--lib/Target/Mips/MipsISelLowering.cpp24
-rw-r--r--test/CodeGen/Mips/fp16-promote.ll96
2 files changed, 118 insertions, 2 deletions
diff --git a/lib/Target/Mips/MipsISelLowering.cpp b/lib/Target/Mips/MipsISelLowering.cpp
index f37737dfc00..c78b79fcf1a 100644
--- a/lib/Target/Mips/MipsISelLowering.cpp
+++ b/lib/Target/Mips/MipsISelLowering.cpp
@@ -221,9 +221,23 @@ MipsTargetLowering::MipsTargetLowering(const MipsTargetMachine &TM,
setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i1, Promote);
}
- // MIPS doesn't have extending float->double load/store
- for (MVT VT : MVT::fp_valuetypes())
+ // MIPS doesn't have extending float->double load/store. Set LoadExtAction
+ // for f32, f16
+ for (MVT VT : MVT::fp_valuetypes()) {
setLoadExtAction(ISD::EXTLOAD, VT, MVT::f32, Expand);
+ setLoadExtAction(ISD::EXTLOAD, VT, MVT::f16, Expand);
+ }
+
+ // Set LoadExtAction for f16 vectors to Expand
+ for (MVT VT : MVT::fp_vector_valuetypes()) {
+ MVT F16VT = MVT::getVectorVT(MVT::f16, VT.getVectorNumElements());
+ if (F16VT.isValid())
+ setLoadExtAction(ISD::EXTLOAD, VT, F16VT, Expand);
+ }
+
+ setTruncStoreAction(MVT::f32, MVT::f16, Expand);
+ setTruncStoreAction(MVT::f64, MVT::f16, Expand);
+
setTruncStoreAction(MVT::f64, MVT::f32, Expand);
// Used by legalize types to correctly generate the setcc result.
@@ -339,6 +353,12 @@ MipsTargetLowering::MipsTargetLowering(const MipsTargetMachine &TM,
setOperationAction(ISD::FREM, MVT::f32, Expand);
setOperationAction(ISD::FREM, MVT::f64, Expand);
+ // Lower f16 conversion operations into library calls
+ setOperationAction(ISD::FP16_TO_FP, MVT::f32, Expand);
+ setOperationAction(ISD::FP_TO_FP16, MVT::f32, Expand);
+ setOperationAction(ISD::FP16_TO_FP, MVT::f64, Expand);
+ setOperationAction(ISD::FP_TO_FP16, MVT::f64, Expand);
+
setOperationAction(ISD::EH_RETURN, MVT::Other, Custom);
setOperationAction(ISD::VASTART, MVT::Other, Custom);
diff --git a/test/CodeGen/Mips/fp16-promote.ll b/test/CodeGen/Mips/fp16-promote.ll
new file mode 100644
index 00000000000..410352fded5
--- /dev/null
+++ b/test/CodeGen/Mips/fp16-promote.ll
@@ -0,0 +1,96 @@
+; RUN: llc -asm-verbose=false -mtriple=mipsel-linux-gnueabi < %s | FileCheck %s -check-prefix=CHECK-LIBCALL
+
+; CHECK-LIBCALL-LABEL: test_fadd:
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL-DAG: add.s
+; CHECK-LIBCALL-DAG: %call16(__gnu_f2h_ieee)
+define void @test_fadd(half* %p, half* %q) #0 {
+ %a = load half, half* %p, align 2
+ %b = load half, half* %q, align 2
+ %r = fadd half %a, %b
+ store half %r, half* %p
+ ret void
+}
+
+; CHECK-LIBCALL-LABEL: test_fpext_float:
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+define float @test_fpext_float(half* %p) {
+ %a = load half, half* %p, align 2
+ %r = fpext half %a to float
+ ret float %r
+}
+
+; CHECK-LIBCALL-LABEL: test_fpext_double:
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL: cvt.d.s
+define double @test_fpext_double(half* %p) {
+ %a = load half, half* %p, align 2
+ %r = fpext half %a to double
+ ret double %r
+}
+
+; CHECK-LIBCALL-LABEL: test_fptrunc_float:
+; CHECK-LIBCALL: %call16(__gnu_f2h_ieee)
+define void @test_fptrunc_float(float %f, half* %p) #0 {
+ %a = fptrunc float %f to half
+ store half %a, half* %p
+ ret void
+}
+
+; CHECK-LIBCALL-LABEL: test_fptrunc_double:
+; CHECK-LIBCALL: %call16(__truncdfhf2)
+define void @test_fptrunc_double(double %d, half* %p) #0 {
+ %a = fptrunc double %d to half
+ store half %a, half* %p
+ ret void
+}
+
+; CHECK-LIBCALL-LABEL: test_vec_fpext_float:
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL: %call16(__gnu_h2f_ieee)
+define <4 x float> @test_vec_fpext_float(<4 x half>* %p) #0 {
+ %a = load <4 x half>, <4 x half>* %p, align 8
+ %b = fpext <4 x half> %a to <4 x float>
+ ret <4 x float> %b
+}
+
+; CHECK-LIBCALL-LABEL: test_vec_fpext_double:
+; CHECK-LIBCALL-DAG: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL-DAG: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL-DAG: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL-DAG: %call16(__gnu_h2f_ieee)
+; CHECK-LIBCALL-DAG: cvt.d.s
+; CHECK-LIBCALL-DAG: cvt.d.s
+; CHECK-LIBCALL-DAG: cvt.d.s
+; CHECK-LIBCALL: cvt.d.s
+define <4 x double> @test_vec_fpext_double(<4 x half>* %p) #0 {
+ %a = load <4 x half>, <4 x half>* %p, align 8
+ %b = fpext <4 x half> %a to <4 x double>
+ ret <4 x double> %b
+}
+
+; CHECK-LIBCALL-LABEL: test_vec_fptrunc_float:
+; CHECK-LIBCALL: %call16(__gnu_f2h_ieee)
+; CHECK-LIBCALL: %call16(__gnu_f2h_ieee)
+; CHECK-LIBCALL: %call16(__gnu_f2h_ieee)
+; CHECK-LIBCALL: %call16(__gnu_f2h_ieee)
+define void @test_vec_fptrunc_float(<4 x float> %a, <4 x half>* %p) #0 {
+ %b = fptrunc <4 x float> %a to <4 x half>
+ store <4 x half> %b, <4 x half>* %p, align 8
+ ret void
+}
+
+; CHECK-LIBCALL-LABEL: test_vec_fptrunc_double:
+; CHECK-LIBCALL: %call16(__truncdfhf2)
+; CHECK-LIBCALL: %call16(__truncdfhf2)
+; CHECK-LIBCALL: %call16(__truncdfhf2)
+; CHECK-LIBCALL: %call16(__truncdfhf2)
+define void @test_vec_fptrunc_double(<4 x double> %a, <4 x half>* %p) #0 {
+ %b = fptrunc <4 x double> %a to <4 x half>
+ store <4 x half> %b, <4 x half>* %p, align 8
+ ret void
+}
+