[PowerPC] Cust lower fpext v2f32 to v2f64 from extract_subvector v4f32

This is a follow up patch from https://reviews.llvm.org/D57857 to handle
extract_subvector v4f32.  For cases where we fpext of v2f32 to v2f64 from
extract_subvector we currently generate on P9 the following:

  lxv 0, 0(3)
  xxsldwi 1, 0, 0, 1
  xscvspdpn 2, 0
  xxsldwi 3, 0, 0, 3
  xxswapd 0, 0
  xscvspdpn 1, 1
  xscvspdpn 3, 3
  xscvspdpn 0, 0
  xxmrghd 0, 0, 3
  xxmrghd 1, 2, 1
  stxv 0, 0(4)
  stxv 1, 0(5)

This patch custom lower it to the following sequence:

  lxv 0, 0(3)       # load the v4f32 <w0, w1, w2, w3>
  xxmrghw 2, 0, 0   # Produce the following vector <w0, w0, w1, w1>
  xxmrglw 3, 0, 0   # Produce the following vector <w2, w2, w3, w3>
  xvcvspdp 2, 2     # FP-extend to <d0, d1>
  xvcvspdp 3, 3     # FP-extend to <d2, d3>
  stxv 2, 0(5)      # Store <d0, d1> (%vecinit11)
  stxv 3, 0(4)      # Store <d2, d3> (%vecinit4)

Differential Revision: https://reviews.llvm.org/D61961

llvm-svn: 372029

1 files changed, 87 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/PowerPC/reduce_scalarization02.ll b/llvm/test/CodeGen/PowerPC/reduce_scalarization02.ll
new file mode 100644
index 00000000000..f7727d6f4ea
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/reduce_scalarization02.ll
@@ -0,0 +1,87 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-unknown \
+; RUN:     -mcpu=pwr9 -ppc-asm-full-reg-names \
+; RUN:     -ppc-vsr-nums-as-vr < %s | FileCheck %s
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-unknown \
+; RUN:     -mcpu=pwr9 -ppc-asm-full-reg-names \
+; RUN:     -ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=CHECK-BE
+
+; Test reduce scalarization in fpext v2f32 to v2f64 from the extract_subvector v4f32 node.
+
+define dso_local void @test(<4 x float>* nocapture readonly %a, <2 x double>* nocapture %b, <2 x double>* nocapture %c) {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxv vs0, 0(r3)
+; CHECK-NEXT:    xxmrglw vs1, vs0, vs0
+; CHECK-NEXT:    xxmrghw vs0, vs0, vs0
+; CHECK-NEXT:    xvcvspdp vs1, vs1
+; CHECK-NEXT:    xvcvspdp vs0, vs0
+; CHECK-NEXT:    stxv vs1, 0(r4)
+; CHECK-NEXT:    stxv vs0, 0(r5)
+; CHECK-NEXT:    blr
+;
+; CHECK-BE-LABEL: test:
+; CHECK-BE:       # %bb.0: # %entry
+; CHECK-BE-NEXT:    lxv vs0, 0(r3)
+; CHECK-BE-NEXT:    xxmrghw vs1, vs0, vs0
+; CHECK-BE-NEXT:    xxmrglw vs0, vs0, vs0
+; CHECK-BE-NEXT:    xvcvspdp vs1, vs1
+; CHECK-BE-NEXT:    xvcvspdp vs0, vs0
+; CHECK-BE-NEXT:    stxv vs1, 0(r4)
+; CHECK-BE-NEXT:    stxv vs0, 0(r5)
+; CHECK-BE-NEXT:    blr
+entry:
+  %0 = load <4 x float>, <4 x float>* %a, align 16
+  %shuffle = shufflevector <4 x float> %0, <4 x float> undef, <2 x i32> <i32 0, i32 1>
+  %shuffle1 = shufflevector <4 x float> %0, <4 x float> undef, <2 x i32> <i32 2, i32 3>
+  %vecinit4 = fpext <2 x float> %shuffle to <2 x double>
+  %vecinit11 = fpext <2 x float> %shuffle1 to <2 x double>
+  store <2 x double> %vecinit4, <2 x double>* %b, align 16
+  store <2 x double> %vecinit11, <2 x double>* %c, align 16
+  ret void
+}
+
+; Ensure we don't crash for wider types
+
+define dso_local void @test2(<16 x float>* nocapture readonly %a, <2 x double>* nocapture %b, <2 x double>* nocapture %c) {
+; CHECK-LABEL: test2:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lxv vs0, 0(r3)
+; CHECK-NEXT:    xxsldwi vs1, vs0, vs0, 1
+; CHECK-NEXT:    xscvspdpn f2, vs0
+; CHECK-NEXT:    xxsldwi vs3, vs0, vs0, 3
+; CHECK-NEXT:    xxswapd vs0, vs0
+; CHECK-NEXT:    xscvspdpn f1, vs1
+; CHECK-NEXT:    xscvspdpn f3, vs3
+; CHECK-NEXT:    xscvspdpn f0, vs0
+; CHECK-NEXT:    xxmrghd vs0, vs0, vs3
+; CHECK-NEXT:    xxmrghd vs1, vs2, vs1
+; CHECK-NEXT:    stxv vs0, 0(r4)
+; CHECK-NEXT:    stxv vs1, 0(r5)
+; CHECK-NEXT:    blr
+;
+; CHECK-BE-LABEL: test2:
+; CHECK-BE:       # %bb.0: # %entry
+; CHECK-BE-NEXT:    lxv vs0, 0(r3)
+; CHECK-BE-NEXT:    xxswapd vs1, vs0
+; CHECK-BE-NEXT:    xxsldwi vs2, vs0, vs0, 3
+; CHECK-BE-NEXT:    xscvspdpn f3, vs0
+; CHECK-BE-NEXT:    xxsldwi vs0, vs0, vs0, 1
+; CHECK-BE-NEXT:    xscvspdpn f1, vs1
+; CHECK-BE-NEXT:    xscvspdpn f2, vs2
+; CHECK-BE-NEXT:    xscvspdpn f0, vs0
+; CHECK-BE-NEXT:    xxmrghd vs0, vs3, vs0
+; CHECK-BE-NEXT:    xxmrghd vs1, vs1, vs2
+; CHECK-BE-NEXT:    stxv vs0, 0(r4)
+; CHECK-BE-NEXT:    stxv vs1, 0(r5)
+; CHECK-BE-NEXT:    blr
+entry:
+  %0 = load <16 x float>, <16 x float>* %a, align 16
+  %shuffle = shufflevector <16 x float> %0, <16 x float> undef, <2 x i32> <i32 0, i32 1>
+  %shuffle1 = shufflevector <16 x float> %0, <16 x float> undef, <2 x i32> <i32 2, i32 3>
+  %vecinit4 = fpext <2 x float> %shuffle to <2 x double>
+  %vecinit11 = fpext <2 x float> %shuffle1 to <2 x double>
+  store <2 x double> %vecinit4, <2 x double>* %b, align 16
+  store <2 x double> %vecinit11, <2 x double>* %c, align 16
+  ret void
+}