; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+sve2 -o - | FileCheck %s
target triple = "aarch64"
; Expected to transform
define <vscale x 2 x i64> @complex_mul_v2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: complex_mul_v2i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov z2.d, #0 // =0x0
; CHECK-NEXT: cmla z2.d, z1.d, z0.d, #0
; CHECK-NEXT: cmla z2.d, z1.d, z0.d, #90
; CHECK-NEXT: mov z0.d, z2.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> %a)
%a.real = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %a.deinterleaved, 1
%b.deinterleaved = tail call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> %b)
%b.real = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %b.deinterleaved, 1
%0 = mul <vscale x 1 x i64> %b.imag, %a.real
%1 = mul <vscale x 1 x i64> %b.real, %a.imag
%2 = add <vscale x 1 x i64> %1, %0
%3 = mul <vscale x 1 x i64> %b.real, %a.real
%4 = mul <vscale x 1 x i64> %a.imag, %b.imag
%5 = sub <vscale x 1 x i64> %3, %4
%interleaved.vec = tail call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> %5, <vscale x 1 x i64> %2)
ret <vscale x 2 x i64> %interleaved.vec
}
; Expected to transform
define <vscale x 4 x i64> @complex_mul_v4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b) {
; CHECK-LABEL: complex_mul_v4i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov z4.d, #0 // =0x0
; CHECK-NEXT: mov z5.d, z4.d
; CHECK-NEXT: cmla z4.d, z3.d, z1.d, #0
; CHECK-NEXT: cmla z5.d, z2.d, z0.d, #0
; CHECK-NEXT: cmla z4.d, z3.d, z1.d, #90
; CHECK-NEXT: cmla z5.d, z2.d, z0.d, #90
; CHECK-NEXT: mov z1.d, z4.d
; CHECK-NEXT: mov z0.d, z5.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> %a)
%a.real = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %a.deinterleaved, 1
%b.deinterleaved = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> %b)
%b.real = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %b.deinterleaved, 1
%0 = mul <vscale x 2 x i64> %b.imag, %a.real
%1 = mul <vscale x 2 x i64> %b.real, %a.imag
%2 = add <vscale x 2 x i64> %1, %0
%3 = mul <vscale x 2 x i64> %b.real, %a.real
%4 = mul <vscale x 2 x i64> %a.imag, %b.imag
%5 = sub <vscale x 2 x i64> %3, %4
%interleaved.vec = tail call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> %5, <vscale x 2 x i64> %2)
ret <vscale x 4 x i64> %interleaved.vec
}
; Expected to transform
define <vscale x 8 x i64> @complex_mul_v8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) {
; CHECK-LABEL: complex_mul_v8i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov z24.d, #0 // =0x0
; CHECK-NEXT: mov z25.d, z24.d
; CHECK-NEXT: mov z26.d, z24.d
; CHECK-NEXT: mov z27.d, z24.d
; CHECK-NEXT: cmla z24.d, z7.d, z3.d, #0
; CHECK-NEXT: cmla z25.d, z4.d, z0.d, #0
; CHECK-NEXT: cmla z26.d, z5.d, z1.d, #0
; CHECK-NEXT: cmla z27.d, z6.d, z2.d, #0
; CHECK-NEXT: cmla z24.d, z7.d, z3.d, #90
; CHECK-NEXT: cmla z25.d, z4.d, z0.d, #90
; CHECK-NEXT: cmla z26.d, z5.d, z1.d, #90
; CHECK-NEXT: cmla z27.d, z6.d, z2.d, #90
; CHECK-NEXT: mov z3.d, z24.d
; CHECK-NEXT: mov z0.d, z25.d
; CHECK-NEXT: mov z1.d, z26.d
; CHECK-NEXT: mov z2.d, z27.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %a)
%a.real = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %a.deinterleaved, 1
%b.deinterleaved = tail call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %b)
%b.real = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %b.deinterleaved, 1
%0 = mul <vscale x 4 x i64> %b.imag, %a.real
%1 = mul <vscale x 4 x i64> %b.real, %a.imag
%2 = add <vscale x 4 x i64> %1, %0
%3 = mul <vscale x 4 x i64> %b.real, %a.real
%4 = mul <vscale x 4 x i64> %a.imag, %b.imag
%5 = sub <vscale x 4 x i64> %3, %4
%interleaved.vec = tail call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> %5, <vscale x 4 x i64> %2)
ret <vscale x 8 x i64> %interleaved.vec
}
; Expected to transform
define <vscale x 8 x i64> @complex_minus_mul_v8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) {
; CHECK-LABEL: complex_minus_mul_v8i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov z24.d, #0 // =0x0
; CHECK-NEXT: mov z25.d, z24.d
; CHECK-NEXT: mov z26.d, z24.d
; CHECK-NEXT: mov z27.d, z24.d
; CHECK-NEXT: cmla z24.d, z7.d, z3.d, #270
; CHECK-NEXT: cmla z25.d, z4.d, z0.d, #270
; CHECK-NEXT: cmla z26.d, z5.d, z1.d, #270
; CHECK-NEXT: cmla z27.d, z6.d, z2.d, #270
; CHECK-NEXT: cmla z24.d, z7.d, z3.d, #180
; CHECK-NEXT: cmla z25.d, z4.d, z0.d, #180
; CHECK-NEXT: cmla z26.d, z5.d, z1.d, #180
; CHECK-NEXT: cmla z27.d, z6.d, z2.d, #180
; CHECK-NEXT: mov z3.d, z24.d
; CHECK-NEXT: mov z0.d, z25.d
; CHECK-NEXT: mov z1.d, z26.d
; CHECK-NEXT: mov z2.d, z27.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %a)
%a.real = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %a.deinterleaved, 1
%0 = sub <vscale x 4 x i64> zeroinitializer, %a.real
%b.deinterleaved = tail call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %b)
%b.real = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %b.deinterleaved, 1
%1 = mul <vscale x 4 x i64> %b.real, %0
%2 = mul <vscale x 4 x i64> %b.imag, %a.imag
%3 = add <vscale x 4 x i64> %2, %1
%4 = mul <vscale x 4 x i64> %b.real, %a.imag
%5 = mul <vscale x 4 x i64> %b.imag, %0
%6 = sub <vscale x 4 x i64> %5, %4
%interleaved.vec = tail call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> %3, <vscale x 4 x i64> %6)
ret <vscale x 8 x i64> %interleaved.vec
}
declare { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
declare { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64>)
declare <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64>)
declare <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
Codebase Browser
llvm