Page MenuHomePhabricator

Please use GitHub pull requests for new patches. Avoid migrating existing patches. Phabricator shutdown timeline

Differential D129066 Diff 449950 llvm/test/CodeGen/AArch64/complex-arithmetic-f64-mul.ll

Changeset View

Standalone View

View Options

llvm/test/CodeGen/AArch64/complex-arithmetic-f64-mul.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16 -o - | FileCheck %s ; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16 -o - | FileCheck %s
target triple = "aarch64-arm-none-eabi" target triple = "aarch64-arm-none-eabi"
define <2 x double> @complex_mul_v2f64(<2 x double> %a, <2 x double> %b) { define <2 x double> @complex_mul_v2f64(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: complex_mul_v2f64: ; CHECK-LABEL: complex_mul_v2f64:
; CHECK: // %bb.0: // %entry ; CHECK: // %bb.0: // %entry
; CHECK-NEXT: ext v2.16b, v0.16b, v0.16b, #8 ; CHECK-NEXT: movi v2.2d, #0000000000000000
; CHECK-NEXT: ext v3.16b, v1.16b, v1.16b, #8 ; CHECK-NEXT: fcmla v2.2d, v0.2d, v1.2d, #0
; CHECK-NEXT: fmul d4, d3, d0 ; CHECK-NEXT: fcmla v2.2d, v0.2d, v1.2d, #90
; CHECK-NEXT: fmul d3, d2, d3 ; CHECK-NEXT: mov v0.16b, v2.16b
; CHECK-NEXT: fmadd d2, d1, d2, d4
; CHECK-NEXT: fnmsub d0, d1, d0, d3
; CHECK-NEXT: mov v0.d[1], v2.d[0]
; CHECK-NEXT: ret ; CHECK-NEXT: ret
entry: entry:
%a.real = shufflevector <2 x double> %a, <2 x double> poison, <1 x i32> <i32 0> %a.real = shufflevector <2 x double> %a, <2 x double> poison, <1 x i32> <i32 0>
%a.imag = shufflevector <2 x double> %a, <2 x double> poison, <1 x i32> <i32 1> %a.imag = shufflevector <2 x double> %a, <2 x double> poison, <1 x i32> <i32 1>
%b.real = shufflevector <2 x double> %b, <2 x double> poison, <1 x i32> <i32 0> %b.real = shufflevector <2 x double> %b, <2 x double> poison, <1 x i32> <i32 0>
%b.imag = shufflevector <2 x double> %b, <2 x double> poison, <1 x i32> <i32 1> %b.imag = shufflevector <2 x double> %b, <2 x double> poison, <1 x i32> <i32 1>
%0 = fmul fast <1 x double> %b.imag, %a.real %0 = fmul fast <1 x double> %b.imag, %a.real
%1 = fmul fast <1 x double> %b.real, %a.imag %1 = fmul fast <1 x double> %b.real, %a.imag
%2 = fadd fast <1 x double> %1, %0 %2 = fadd fast <1 x double> %1, %0
%3 = fmul fast <1 x double> %b.real, %a.real %3 = fmul fast <1 x double> %b.real, %a.real
%4 = fmul fast <1 x double> %a.imag, %b.imag %4 = fmul fast <1 x double> %a.imag, %b.imag
%5 = fsub fast <1 x double> %3, %4 %5 = fsub fast <1 x double> %3, %4
%interleaved.vec = shufflevector <1 x double> %5, <1 x double> %2, <2 x i32> <i32 0, i32 1> %interleaved.vec = shufflevector <1 x double> %5, <1 x double> %2, <2 x i32> <i32 0, i32 1>
ret <2 x double> %interleaved.vec ret <2 x double> %interleaved.vec
} }
define <4 x double> @complex_mul_v4f64(<4 x double> %a, <4 x double> %b) { define <4 x double> @complex_mul_v4f64(<4 x double> %a, <4 x double> %b) {
; CHECK-LABEL: complex_mul_v4f64: ; CHECK-LABEL: complex_mul_v4f64:
; CHECK: // %bb.0: // %entry ; CHECK: // %bb.0: // %entry
; CHECK-NEXT: zip2 v4.2d, v2.2d, v3.2d ; CHECK-NEXT: movi v4.2d, #0000000000000000
; CHECK-NEXT: zip2 v5.2d, v0.2d, v1.2d ; CHECK-NEXT: movi v5.2d, #0000000000000000
; CHECK-NEXT: zip1 v0.2d, v0.2d, v1.2d ; CHECK-NEXT: fcmla v4.2d, v0.2d, v2.2d, #0
; CHECK-NEXT: zip1 v2.2d, v2.2d, v3.2d ; CHECK-NEXT: fcmla v5.2d, v1.2d, v3.2d, #0
; CHECK-NEXT: fmul v1.2d, v5.2d, v4.2d ; CHECK-NEXT: fcmla v4.2d, v0.2d, v2.2d, #90
; CHECK-NEXT: fmul v3.2d, v4.2d, v0.2d ; CHECK-NEXT: fcmla v5.2d, v1.2d, v3.2d, #90
; CHECK-NEXT: fneg v1.2d, v1.2d ; CHECK-NEXT: mov v0.16b, v4.16b
; CHECK-NEXT: fmla v3.2d, v5.2d, v2.2d ; CHECK-NEXT: mov v1.16b, v5.16b
; CHECK-NEXT: fmla v1.2d, v0.2d, v2.2d
; CHECK-NEXT: zip1 v0.2d, v1.2d, v3.2d
; CHECK-NEXT: zip2 v1.2d, v1.2d, v3.2d
; CHECK-NEXT: ret ; CHECK-NEXT: ret
entry: entry:
%a.real = shufflevector <4 x double> %a, <4 x double> poison, <2 x i32> <i32 0, i32 2> %a.real = shufflevector <4 x double> %a, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%a.imag = shufflevector <4 x double> %a, <4 x double> poison, <2 x i32> <i32 1, i32 3> %a.imag = shufflevector <4 x double> %a, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%b.real = shufflevector <4 x double> %b, <4 x double> poison, <2 x i32> <i32 0, i32 2> %b.real = shufflevector <4 x double> %b, <4 x double> poison, <2 x i32> <i32 0, i32 2>
%b.imag = shufflevector <4 x double> %b, <4 x double> poison, <2 x i32> <i32 1, i32 3> %b.imag = shufflevector <4 x double> %b, <4 x double> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x double> %b.imag, %a.real %0 = fmul fast <2 x double> %b.imag, %a.real
%1 = fmul fast <2 x double> %b.real, %a.imag %1 = fmul fast <2 x double> %b.real, %a.imag
%2 = fadd fast <2 x double> %1, %0 %2 = fadd fast <2 x double> %1, %0
%3 = fmul fast <2 x double> %b.real, %a.real %3 = fmul fast <2 x double> %b.real, %a.real
%4 = fmul fast <2 x double> %a.imag, %b.imag %4 = fmul fast <2 x double> %a.imag, %b.imag
%5 = fsub fast <2 x double> %3, %4 %5 = fsub fast <2 x double> %3, %4
%interleaved.vec = shufflevector <2 x double> %5, <2 x double> %2, <4 x i32> <i32 0, i32 2, i32 1, i32 3> %interleaved.vec = shufflevector <2 x double> %5, <2 x double> %2, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x double> %interleaved.vec ret <4 x double> %interleaved.vec
} }
define <8 x double> @complex_mul_v8f64(<8 x double> %a, <8 x double> %b) { define <8 x double> @complex_mul_v8f64(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: complex_mul_v8f64: ; CHECK-LABEL: complex_mul_v8f64:
; CHECK: // %bb.0: // %entry ; CHECK: // %bb.0: // %entry
; CHECK-NEXT: zip2 v16.2d, v4.2d, v5.2d ; CHECK-NEXT: movi v16.2d, #0000000000000000
; CHECK-NEXT: zip1 v17.2d, v2.2d, v3.2d ; CHECK-NEXT: movi v17.2d, #0000000000000000
; CHECK-NEXT: zip1 v18.2d, v0.2d, v1.2d ; CHECK-NEXT: movi v18.2d, #0000000000000000
; CHECK-NEXT: zip2 v0.2d, v0.2d, v1.2d ; CHECK-NEXT: movi v19.2d, #0000000000000000
; CHECK-NEXT: zip2 v1.2d, v2.2d, v3.2d ; CHECK-NEXT: fcmla v16.2d, v0.2d, v4.2d, #0
; CHECK-NEXT: zip2 v2.2d, v6.2d, v7.2d ; CHECK-NEXT: fcmla v17.2d, v1.2d, v5.2d, #0
; CHECK-NEXT: zip1 v3.2d, v4.2d, v5.2d ; CHECK-NEXT: fcmla v18.2d, v2.2d, v6.2d, #0
; CHECK-NEXT: fmul v4.2d, v0.2d, v16.2d ; CHECK-NEXT: fcmla v19.2d, v3.2d, v7.2d, #0
; CHECK-NEXT: zip1 v5.2d, v6.2d, v7.2d ; CHECK-NEXT: fcmla v16.2d, v0.2d, v4.2d, #90
; CHECK-NEXT: fmul v6.2d, v1.2d, v2.2d ; CHECK-NEXT: fcmla v17.2d, v1.2d, v5.2d, #90
; CHECK-NEXT: fmul v7.2d, v16.2d, v18.2d ; CHECK-NEXT: fcmla v18.2d, v2.2d, v6.2d, #90
; CHECK-NEXT: fneg v4.2d, v4.2d ; CHECK-NEXT: fcmla v19.2d, v3.2d, v7.2d, #90
; CHECK-NEXT: fmul v16.2d, v2.2d, v17.2d ; CHECK-NEXT: mov v0.16b, v16.16b
; CHECK-NEXT: fneg v6.2d, v6.2d ; CHECK-NEXT: mov v1.16b, v17.16b
; CHECK-NEXT: fmla v7.2d, v0.2d, v3.2d ; CHECK-NEXT: mov v2.16b, v18.16b
; CHECK-NEXT: fmla v4.2d, v18.2d, v3.2d ; CHECK-NEXT: mov v3.16b, v19.16b
; CHECK-NEXT: fmla v16.2d, v1.2d, v5.2d
; CHECK-NEXT: fmla v6.2d, v17.2d, v5.2d
; CHECK-NEXT: zip1 v0.2d, v4.2d, v7.2d
; CHECK-NEXT: zip2 v1.2d, v4.2d, v7.2d
; CHECK-NEXT: zip1 v2.2d, v6.2d, v16.2d
; CHECK-NEXT: zip2 v3.2d, v6.2d, v16.2d
; CHECK-NEXT: ret ; CHECK-NEXT: ret
entry: entry:
%a.real = shufflevector <8 x double> %a, <8 x double> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6> %a.real = shufflevector <8 x double> %a, <8 x double> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
%a.imag = shufflevector <8 x double> %a, <8 x double> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7> %a.imag = shufflevector <8 x double> %a, <8 x double> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
%b.real = shufflevector <8 x double> %b, <8 x double> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6> %b.real = shufflevector <8 x double> %b, <8 x double> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
%b.imag = shufflevector <8 x double> %b, <8 x double> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7> %b.imag = shufflevector <8 x double> %b, <8 x double> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
%0 = fmul fast <4 x double> %b.imag, %a.real %0 = fmul fast <4 x double> %b.imag, %a.real
%1 = fmul fast <4 x double> %b.real, %a.imag %1 = fmul fast <4 x double> %b.real, %a.imag
%2 = fadd fast <4 x double> %1, %0 %2 = fadd fast <4 x double> %1, %0
%3 = fmul fast <4 x double> %b.real, %a.real %3 = fmul fast <4 x double> %b.real, %a.real
%4 = fmul fast <4 x double> %a.imag, %b.imag %4 = fmul fast <4 x double> %a.imag, %b.imag
%5 = fsub fast <4 x double> %3, %4 %5 = fsub fast <4 x double> %3, %4
%interleaved.vec = shufflevector <4 x double> %5, <4 x double> %2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7> %interleaved.vec = shufflevector <4 x double> %5, <4 x double> %2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x double> %interleaved.vec ret <8 x double> %interleaved.vec
} }