[llvm] 64186e9 - [X86] Add test showing failure to expand <2 x float> fpow without widening to <4 x float>

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2022-05-24T10:45:20+01:00
New Revision: 64186e9b351a000123f253557f4f607c33405413

URL: https://github.com/llvm/llvm-project/commit/64186e9b351a000123f253557f4f607c33405413
DIFF: https://github.com/llvm/llvm-project/commit/64186e9b351a000123f253557f4f607c33405413.diff

LOG: [X86] Add test showing failure to expand <2 x float> fpow without widening to <4 x float>

Similar to D125988 (and I have a pending follow up patch to handle fpow).

Added: 
    llvm/test/CodeGen/X86/pow-libcall.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/X86/pow-libcall.ll b/llvm/test/CodeGen/X86/pow-libcall.ll
new file mode 100644
index 0000000000000..e90155e5978cf
--- /dev/null
+++ b/llvm/test/CodeGen/X86/pow-libcall.ll
@@ -0,0 +1,53 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=x86_64-linux-gnu < %s  | FileCheck %s
+
+; FIXME: Ensure vectorized FPOWs are not widened/unrolled such that they get lowered
+; into libcalls on undef elements.
+
+define float @test_fpow_v2f32_multiuse(<2 x float> %a0, <2 x float> %a1, <2 x float> *%p3) nounwind {
+; CHECK-LABEL: test_fpow_v2f32_multiuse:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    subq $64, %rsp
+; CHECK-NEXT:    movq %rdi, %rbx
+; CHECK-NEXT:    movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
+; CHECK-NEXT:    shufps {{.*#+}} xmm1 = xmm1[3,3,3,3]
+; CHECK-NEXT:    callq powf at PLT
+; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    movhlps {{.*#+}} xmm0 = xmm0[1,1]
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    movhlps {{.*#+}} xmm1 = xmm1[1,1]
+; CHECK-NEXT:    callq powf at PLT
+; CHECK-NEXT:    unpcklps (%rsp), %xmm0 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
+; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    callq powf at PLT
+; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,1,1,1]
+; CHECK-NEXT:    callq powf at PLT
+; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
+; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; CHECK-NEXT:    unpcklpd (%rsp), %xmm1 # 16-byte Folded Reload
+; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
+; CHECK-NEXT:    addss %xmm1, %xmm0
+; CHECK-NEXT:    movlps %xmm1, (%rbx)
+; CHECK-NEXT:    addq $64, %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    retq
+  %fp = call <2 x float> @llvm.pow.v2f32(<2 x float> %a0, <2 x float> %a1)
+  %fp0 = extractelement <2 x float> %fp, i32 0
+  %fp1 = extractelement <2 x float> %fp, i32 1
+  %res = fadd float %fp0, %fp1
+  store <2 x float> %fp, <2 x float> *%p3
+  ret float %res
+}
+declare <2 x float> @llvm.pow.v2f32(<2 x float>, <2 x float>)
+