147 lines
7.5 KiB
LLVM
147 lines
7.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16 -o - | FileCheck %s
|
|
|
|
target triple = "aarch64-arm-none-eabi"
|
|
|
|
; Expected to not transform
|
|
define <2 x half> @complex_mul_v2f16(<2 x half> %a, <2 x half> %b) {
|
|
; CHECK-LABEL: complex_mul_v2f16:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: mov h3, v0.h[1]
|
|
; CHECK-NEXT: mov h2, v1.h[1]
|
|
; CHECK-NEXT: fmul h4, h2, v0.h[0]
|
|
; CHECK-NEXT: fnmul h2, h3, h2
|
|
; CHECK-NEXT: fmla h4, h3, v1.h[0]
|
|
; CHECK-NEXT: fmla h2, h0, v1.h[0]
|
|
; CHECK-NEXT: mov v2.h[1], v4.h[0]
|
|
; CHECK-NEXT: fmov d0, d2
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.real = shufflevector <2 x half> %a, <2 x half> poison, <1 x i32> <i32 0>
|
|
%a.imag = shufflevector <2 x half> %a, <2 x half> poison, <1 x i32> <i32 1>
|
|
%b.real = shufflevector <2 x half> %b, <2 x half> poison, <1 x i32> <i32 0>
|
|
%b.imag = shufflevector <2 x half> %b, <2 x half> poison, <1 x i32> <i32 1>
|
|
%0 = fmul fast <1 x half> %b.imag, %a.real
|
|
%1 = fmul fast <1 x half> %b.real, %a.imag
|
|
%2 = fadd fast <1 x half> %1, %0
|
|
%3 = fmul fast <1 x half> %b.real, %a.real
|
|
%4 = fmul fast <1 x half> %a.imag, %b.imag
|
|
%5 = fsub fast <1 x half> %3, %4
|
|
%interleaved.vec = shufflevector <1 x half> %5, <1 x half> %2, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x half> %interleaved.vec
|
|
}
|
|
|
|
; Expected to transform
|
|
define <4 x half> @complex_mul_v4f16(<4 x half> %a, <4 x half> %b) {
|
|
; CHECK-LABEL: complex_mul_v4f16:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: movi d2, #0000000000000000
|
|
; CHECK-NEXT: fcmla v2.4h, v0.4h, v1.4h, #0
|
|
; CHECK-NEXT: fcmla v2.4h, v0.4h, v1.4h, #90
|
|
; CHECK-NEXT: fmov d0, d2
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.real = shufflevector <4 x half> %a, <4 x half> poison, <2 x i32> <i32 0, i32 2>
|
|
%a.imag = shufflevector <4 x half> %a, <4 x half> poison, <2 x i32> <i32 1, i32 3>
|
|
%b.real = shufflevector <4 x half> %b, <4 x half> poison, <2 x i32> <i32 0, i32 2>
|
|
%b.imag = shufflevector <4 x half> %b, <4 x half> poison, <2 x i32> <i32 1, i32 3>
|
|
%0 = fmul fast <2 x half> %b.imag, %a.real
|
|
%1 = fmul fast <2 x half> %b.real, %a.imag
|
|
%2 = fadd fast <2 x half> %1, %0
|
|
%3 = fmul fast <2 x half> %b.real, %a.real
|
|
%4 = fmul fast <2 x half> %a.imag, %b.imag
|
|
%5 = fsub fast <2 x half> %3, %4
|
|
%interleaved.vec = shufflevector <2 x half> %5, <2 x half> %2, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
|
|
ret <4 x half> %interleaved.vec
|
|
}
|
|
|
|
; Expected to transform
|
|
define <8 x half> @complex_mul_v8f16(<8 x half> %a, <8 x half> %b) {
|
|
; CHECK-LABEL: complex_mul_v8f16:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: movi v2.2d, #0000000000000000
|
|
; CHECK-NEXT: fcmla v2.8h, v0.8h, v1.8h, #0
|
|
; CHECK-NEXT: fcmla v2.8h, v0.8h, v1.8h, #90
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.real = shufflevector <8 x half> %a, <8 x half> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
%a.imag = shufflevector <8 x half> %a, <8 x half> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
%b.real = shufflevector <8 x half> %b, <8 x half> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
%b.imag = shufflevector <8 x half> %b, <8 x half> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
%0 = fmul fast <4 x half> %b.imag, %a.real
|
|
%1 = fmul fast <4 x half> %b.real, %a.imag
|
|
%2 = fadd fast <4 x half> %1, %0
|
|
%3 = fmul fast <4 x half> %b.real, %a.real
|
|
%4 = fmul fast <4 x half> %a.imag, %b.imag
|
|
%5 = fsub fast <4 x half> %3, %4
|
|
%interleaved.vec = shufflevector <4 x half> %5, <4 x half> %2, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
|
|
ret <8 x half> %interleaved.vec
|
|
}
|
|
|
|
; Expected to transform
|
|
define <16 x half> @complex_mul_v16f16(<16 x half> %a, <16 x half> %b) {
|
|
; CHECK-LABEL: complex_mul_v16f16:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: movi v4.2d, #0000000000000000
|
|
; CHECK-NEXT: movi v5.2d, #0000000000000000
|
|
; CHECK-NEXT: fcmla v4.8h, v0.8h, v2.8h, #0
|
|
; CHECK-NEXT: fcmla v5.8h, v1.8h, v3.8h, #0
|
|
; CHECK-NEXT: fcmla v4.8h, v0.8h, v2.8h, #90
|
|
; CHECK-NEXT: fcmla v5.8h, v1.8h, v3.8h, #90
|
|
; CHECK-NEXT: mov v0.16b, v4.16b
|
|
; CHECK-NEXT: mov v1.16b, v5.16b
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.real = shufflevector <16 x half> %a, <16 x half> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
%a.imag = shufflevector <16 x half> %a, <16 x half> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
%b.real = shufflevector <16 x half> %b, <16 x half> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
%b.imag = shufflevector <16 x half> %b, <16 x half> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
%0 = fmul fast <8 x half> %b.imag, %a.real
|
|
%1 = fmul fast <8 x half> %b.real, %a.imag
|
|
%2 = fadd fast <8 x half> %1, %0
|
|
%3 = fmul fast <8 x half> %b.real, %a.real
|
|
%4 = fmul fast <8 x half> %a.imag, %b.imag
|
|
%5 = fsub fast <8 x half> %3, %4
|
|
%interleaved.vec = shufflevector <8 x half> %5, <8 x half> %2, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
|
|
ret <16 x half> %interleaved.vec
|
|
}
|
|
|
|
; Expected to transform
|
|
define <32 x half> @complex_mul_v32f16(<32 x half> %a, <32 x half> %b) {
|
|
; CHECK-LABEL: complex_mul_v32f16:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: movi v16.2d, #0000000000000000
|
|
; CHECK-NEXT: movi v17.2d, #0000000000000000
|
|
; CHECK-NEXT: movi v18.2d, #0000000000000000
|
|
; CHECK-NEXT: movi v19.2d, #0000000000000000
|
|
; CHECK-NEXT: fcmla v16.8h, v0.8h, v4.8h, #0
|
|
; CHECK-NEXT: fcmla v17.8h, v1.8h, v5.8h, #0
|
|
; CHECK-NEXT: fcmla v18.8h, v2.8h, v6.8h, #0
|
|
; CHECK-NEXT: fcmla v19.8h, v3.8h, v7.8h, #0
|
|
; CHECK-NEXT: fcmla v16.8h, v0.8h, v4.8h, #90
|
|
; CHECK-NEXT: fcmla v17.8h, v1.8h, v5.8h, #90
|
|
; CHECK-NEXT: fcmla v18.8h, v2.8h, v6.8h, #90
|
|
; CHECK-NEXT: fcmla v19.8h, v3.8h, v7.8h, #90
|
|
; CHECK-NEXT: mov v0.16b, v16.16b
|
|
; CHECK-NEXT: mov v1.16b, v17.16b
|
|
; CHECK-NEXT: mov v2.16b, v18.16b
|
|
; CHECK-NEXT: mov v3.16b, v19.16b
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.real = shufflevector <32 x half> %a, <32 x half> poison, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
|
|
%a.imag = shufflevector <32 x half> %a, <32 x half> poison, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
|
|
%b.real = shufflevector <32 x half> %b, <32 x half> poison, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
|
|
%b.imag = shufflevector <32 x half> %b, <32 x half> poison, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
|
|
%0 = fmul fast <16 x half> %b.imag, %a.real
|
|
%1 = fmul fast <16 x half> %b.real, %a.imag
|
|
%2 = fadd fast <16 x half> %1, %0
|
|
%3 = fmul fast <16 x half> %b.real, %a.real
|
|
%4 = fmul fast <16 x half> %a.imag, %b.imag
|
|
%5 = fsub fast <16 x half> %3, %4
|
|
%interleaved.vec = shufflevector <16 x half> %5, <16 x half> %2, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
|
|
ret <32 x half> %interleaved.vec
|
|
}
|