[ARM] Add FP16 vector insert/extract patterns

This change adds two FP16 extraction and two insertion patterns
(one per possible vector length).
Extractions are handled by copying a Q/D register into one of VFP2
class registers, where single FP32 sub-registers can be accessed. Then
the extraction of even lanes are simple sub-register extractions
(because we don't care about the top parts of registers for FP16
operations). Odd lanes need an additional VMOVX instruction.

Unfortunately, insertions cannot be handled in the same way, because:
* There is no instruction to insert FP16 into an even lane (VINS only
  works with odd lanes)
* The patterns for odd lanes will have a form of a DAG (not a tree),
  and will not be implementable in pure tablegen

Because of this insertions are handled in the same way as 16-bit
integer insertions (with conversions between FP registers and GPRs
using VMOVHR instructions).

Without these patterns the ARM backend would sometimes fail during
instruction selection.

This patch also adds patterns which combine:
* an FP16 element extraction and a store into a single VST1
  instruction
* an FP16 load and insertion into a single VLD1 instruction

Differential Revision: https://reviews.llvm.org/D62651

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@362482 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td
index effee0f..1c7bbab 100644 (file)
--- a/lib/Target/ARM/ARMInstrNEON.td
+++ b/lib/Target/ARM/ARMInstrNEON.td
@@ -1117,6 +1117,12 @@ def VLD1LNq8Pseudo  : VLD1QLNPseudo<v16i8, extloadi8>;
 def VLD1LNq16Pseudo : VLD1QLNPseudo<v8i16, extloadi16>;
 def VLD1LNq32Pseudo : VLD1QLNPseudo<v4i32, load>;
 
+def : Pat<(vector_insert (v4f16 DPR:$src),
+                         (f16 (load addrmode6:$addr)), imm:$lane),
+          (VLD1LNd16 addrmode6:$addr, DPR:$src, imm:$lane)>;
+def : Pat<(vector_insert (v8f16 QPR:$src),
+                         (f16 (load addrmode6:$addr)), imm:$lane),
+          (VLD1LNq16Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
 def : Pat<(vector_insert (v2f32 DPR:$src),
                          (f32 (load addrmode6:$addr)), imm:$lane),
           (VLD1LNd32 addrmode6:$addr, DPR:$src, imm:$lane)>;
@@ -2175,6 +2181,11 @@ def : Pat<(store (extractelt (v2f32 DPR:$src), imm:$lane), addrmode6:$addr),
 def : Pat<(store (extractelt (v4f32 QPR:$src), imm:$lane), addrmode6:$addr),
           (VST1LNq32Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
 
+def : Pat<(store (extractelt (v4f16 DPR:$src), imm:$lane), addrmode6:$addr),
+          (VST1LNd16 addrmode6:$addr, DPR:$src, imm:$lane)>;
+def : Pat<(store (extractelt (v8f16 QPR:$src), imm:$lane), addrmode6:$addr),
+          (VST1LNq16Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
+
 // ...with address register writeback:
 class VST1LNWB<bits<4> op11_8, bits<4> op7_4, string Dt, ValueType Ty,
                PatFrag StoreOp, SDNode ExtractOp, Operand AdrMode>
@@ -2504,6 +2515,13 @@ def SSubReg_f32_reg : SDNodeXForm<imm, [{
                                    MVT::i32);
 }]>;
 
+// Extract S sub-registers of Q/D registers containing a given f16 lane.
+def SSubReg_f16_reg : SDNodeXForm<imm, [{
+  assert(ARM::ssub_3 == ARM::ssub_0+3 && "Unexpected subreg numbering");
+  return CurDAG->getTargetConstant(ARM::ssub_0 + N->getZExtValue()/2, SDLoc(N),
+                                   MVT::i32);
+}]>;
+
 // Translate lane numbers from Q registers to D subregs.
 def SubReg_i8_lane  : SDNodeXForm<imm, [{
   return CurDAG->getTargetConstant(N->getZExtValue() & 7, SDLoc(N), MVT::i32);
@@ -6223,6 +6241,32 @@ def : Pat<(extractelt (v4f32 QPR:$src1), imm:$src2),
 def : Pat<(extractelt (v2f64 QPR:$src1), imm:$src2),
           (EXTRACT_SUBREG QPR:$src1, (DSubReg_f64_reg imm:$src2))>;
 
+def imm_even : ImmLeaf<i32, [{ return (Imm & 1) == 0; }]>;
+def imm_odd : ImmLeaf<i32, [{ return (Imm & 1) == 1; }]>;
+
+def : Pat<(extractelt (v4f16 DPR:$src), imm_even:$lane),
+            (EXTRACT_SUBREG
+                (v2f32 (COPY_TO_REGCLASS (v4f16 DPR:$src), DPR_VFP2)),
+                (SSubReg_f16_reg imm_even:$lane))>;
+
+def : Pat<(extractelt (v4f16 DPR:$src), imm_odd:$lane),
+            (COPY_TO_REGCLASS
+              (VMOVH (EXTRACT_SUBREG
+                  (v2f32 (COPY_TO_REGCLASS (v4f16 DPR:$src), DPR_VFP2)),
+                  (SSubReg_f16_reg imm_odd:$lane))),
+              HPR)>;
+
+def : Pat<(extractelt (v8f16 QPR:$src), imm_even:$lane),
+            (EXTRACT_SUBREG
+                (v4f32 (COPY_TO_REGCLASS (v8f16 QPR:$src), QPR_VFP2)),
+                (SSubReg_f16_reg imm_even:$lane))>;
+
+def : Pat<(extractelt (v8f16 QPR:$src), imm_odd:$lane),
+            (COPY_TO_REGCLASS
+              (VMOVH (EXTRACT_SUBREG
+                  (v4f32 (COPY_TO_REGCLASS (v8f16 QPR:$src), QPR_VFP2)),
+                  (SSubReg_f16_reg imm_odd:$lane))),
+              HPR)>;
 
 //   VMOV     : Vector Set Lane (move ARM core register to scalar)
 
@@ -6281,6 +6325,15 @@ def : Pat<(v4f32 (insertelt QPR:$src1, SPR:$src2, imm:$src3)),
           (INSERT_SUBREG (v4f32 (COPY_TO_REGCLASS QPR:$src1, QPR_VFP2)),
                                 SPR:$src2, (SSubReg_f32_reg imm:$src3))>;
 
+def : Pat<(insertelt (v4f16 DPR:$src1), HPR:$src2, imm:$lane),
+          (v4f16 (VSETLNi16 DPR:$src1, (VMOVRH $src2), imm:$lane))>;
+def : Pat<(insertelt (v8f16 QPR:$src1), HPR:$src2, imm:$lane),
+          (v8f16 (INSERT_SUBREG QPR:$src1,
+                   (v4i16 (VSETLNi16 (v4i16 (EXTRACT_SUBREG QPR:$src1,
+                                      (DSubReg_i16_reg imm:$lane))),
+                             (VMOVRH $src2), (SubReg_i16_lane imm:$lane))),
+                   (DSubReg_i16_reg imm:$lane)))>;
+
 //def : Pat<(v2i64 (insertelt QPR:$src1, DPR:$src2, imm:$src3)),
 //          (INSERT_SUBREG QPR:$src1, DPR:$src2, (DSubReg_f64_reg imm:$src3))>;
 def : Pat<(v2f64 (insertelt QPR:$src1, DPR:$src2, imm:$src3)),

diff --git a/test/CodeGen/ARM/fp16-insert-extract.ll b/test/CodeGen/ARM/fp16-insert-extract.ll
new file mode 100644 (file)
index 0000000..617a4df
--- /dev/null
+++ b/test/CodeGen/ARM/fp16-insert-extract.ll
@@ -0,0 +1,72 @@
+; RUN: llc -mtriple=arm-eabi -mattr=+armv8.2-a,+fullfp16,+neon -float-abi=hard -O1 < %s | FileCheck %s
+; RUN: llc -mtriple=arm-eabi -mattr=+armv8.2-a,+fullfp16,+neon -float-abi=soft -O1 < %s | FileCheck %s
+
+define float @test_vget_lane_f16_1(<4 x half> %a) nounwind {
+; CHECK-LABEL: test_vget_lane_f16_1:
+; CHECK:      vmovx.f16 s0, s0
+; CHECK-NEXT: vcvtb.f32.f16 s0, s0
+entry:
+  %elt = extractelement <4 x half> %a, i32 1
+  %conv = fpext half %elt to float
+  ret float %conv
+}
+
+define float @test_vget_lane_f16_2(<4 x half> %a) nounwind {
+; CHECK-LABEL: test_vget_lane_f16_2:
+; CHECK-NOT:  vmovx.f16
+; CHECK:      vcvtb.f32.f16 s0, s1
+entry:
+  %elt = extractelement <4 x half> %a, i32 2
+  %conv = fpext half %elt to float
+  ret float %conv
+}
+
+define float @test_vget_laneq_f16_6(<8 x half> %a) nounwind {
+; CHECK-LABEL: test_vget_laneq_f16_6:
+; CHECK-NOT:  vmovx.f16
+; CHECK:      vcvtb.f32.f16 s0, s3
+entry:
+  %elt = extractelement <8 x half> %a, i32 6
+  %conv = fpext half %elt to float
+  ret float %conv
+}
+
+define float @test_vget_laneq_f16_7(<8 x half> %a) nounwind {
+; CHECK-LABEL: test_vget_laneq_f16_7:
+; CHECK:      vmovx.f16 s0, s3
+; CHECK:      vcvtb.f32.f16 s0, s0
+entry:
+  %elt = extractelement <8 x half> %a, i32 7
+  %conv = fpext half %elt to float
+  ret float %conv
+}
+
+define <4 x half> @test_vset_lane_f16(<4 x half> %a, float %fb) nounwind {
+; CHECK-LABEL: test_vset_lane_f16:
+; CHECK: vmov.f16 r[[GPR:[0-9]+]], s{{[0-9]+}}
+; CHECK: vmov.16  d{{[0-9]+}}[3], r[[GPR]]
+entry:
+  %b = fptrunc float %fb to half
+  %x = insertelement <4 x half> %a, half %b, i32 3
+  ret <4 x half> %x
+}
+
+define <8 x half> @test_vset_laneq_f16_1(<8 x half> %a, float %fb) nounwind {
+; CHECK-LABEL: test_vset_laneq_f16_1:
+; CHECK: vmov.f16 r[[GPR:[0-9]+]], s{{[0-9]+}}
+; CHECK: vmov.16  d{{[0-9]+}}[1], r[[GPR]]
+entry:
+  %b = fptrunc float %fb to half
+  %x = insertelement <8 x half> %a, half %b, i32 1
+  ret <8 x half> %x
+}
+
+define <8 x half> @test_vset_laneq_f16_7(<8 x half> %a, float %fb) nounwind {
+; CHECK-LABEL: test_vset_laneq_f16_7:
+; CHECK: vmov.f16 r[[GPR:[0-9]+]], s{{[0-9]+}}
+; CHECK: vmov.16  d{{[0-9]+}}[3], r[[GPR]]
+entry:
+  %b = fptrunc float %fb to half
+  %x = insertelement <8 x half> %a, half %b, i32 7
+  ret <8 x half> %x
+}

diff --git a/test/CodeGen/ARM/fp16-vldlane-vstlane.ll b/test/CodeGen/ARM/fp16-vldlane-vstlane.ll
new file mode 100644 (file)
index 0000000..2a73583
--- /dev/null
+++ b/test/CodeGen/ARM/fp16-vldlane-vstlane.ll
@@ -0,0 +1,56 @@
+; RUN: llc -mtriple=arm-eabi -mattr=+armv8.2-a,+fullfp16,+neon -float-abi=hard -O1 < %s | FileCheck %s
+; RUN: llc -mtriple=arm-eabi -mattr=+armv8.2-a,+fullfp16,+neon -float-abi=soft -O1 < %s | FileCheck %s
+
+define <4 x half> @vld1d_lane_f16(half* %pa, <4 x half> %v4) nounwind {
+; CHECK-LABEL: vld1d_lane_f16:
+; CHECK: vld1.16 {d{{[0-9]+}}[3]}, [r0:16]
+entry:
+  %a = load half, half* %pa
+  %res = insertelement <4 x half> %v4, half %a, i32 3
+  ret <4 x half> %res
+}
+
+define <8 x half> @vld1q_lane_f16_1(half* %pa, <8 x half> %v8) nounwind {
+; CHECK-LABEL: vld1q_lane_f16_1:
+; CHECK: vld1.16 {d{{[0-9]+}}[1]}, [r0:16]
+entry:
+  %a = load half, half* %pa
+  %res = insertelement <8 x half> %v8, half %a, i32 1
+  ret <8 x half> %res
+}
+
+define <8 x half> @vld1q_lane_f16_7(half* %pa, <8 x half> %v8) nounwind {
+; CHECK-LABEL: vld1q_lane_f16_7:
+; CHECK: vld1.16 {d{{[0-9]+}}[3]}, [r0:16]
+entry:
+  %a = load half, half* %pa
+  %res = insertelement <8 x half> %v8, half %a, i32 7
+  ret <8 x half> %res
+}
+
+define void @vst1d_lane_f16(half* %pa, <4 x half> %v4) nounwind {
+; CHECK-LABEL: vst1d_lane_f16:
+; CHECK: vst1.16 {d{{[0-9]+}}[3]}, [r0:16]
+entry:
+  %a = extractelement <4 x half> %v4, i32 3
+  store half %a, half* %pa
+  ret void
+}
+
+define void @vst1q_lane_f16_7(half* %pa, <8 x half> %v8) nounwind {
+; CHECK-LABEL: vst1q_lane_f16_7:
+; CHECK: vst1.16 {d{{[0-9]+}}[3]}, [r0:16]
+entry:
+  %a = extractelement <8 x half> %v8, i32 7
+  store half %a, half* %pa
+  ret void
+}
+
+define void @vst1q_lane_f16_1(half* %pa, <8 x half> %v8) nounwind {
+; CHECK-LABEL: vst1q_lane_f16_1:
+; CHECK: vst1.16 {d{{[0-9]+}}[1]}, [r0:16]
+entry:
+  %a = extractelement <8 x half> %v8, i32 1
+  store half %a, half* %pa
+  ret void
+}