db158c7c83
Refresh of the generic scheduling model to use A510 instead of A55. Main benefits are to the little core, and introducing SVE scheduling information. Changes tested on various OoO cores, no performance degradation is seen. Differential Revision: https://reviews.llvm.org/D156799
134 lines
5.2 KiB
LLVM
134 lines
5.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=aarch64-linux-gnu | FileCheck %s
|
|
|
|
define <4 x half> @interleave2_v4f16(<2 x half> %vec0, <2 x half> %vec1) {
|
|
; CHECK-LABEL: interleave2_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
%retval = call <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half> %vec0, <2 x half> %vec1)
|
|
ret <4 x half> %retval
|
|
}
|
|
|
|
define <8 x half> @interleave2_v8f16(<4 x half> %vec0, <4 x half> %vec1) {
|
|
; CHECK-LABEL: interleave2_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
|
|
; CHECK-NEXT: adrp x8, .LCPI1_0
|
|
; CHECK-NEXT: mov v0.d[1], v1.d[0]
|
|
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI1_0]
|
|
; CHECK-NEXT: tbl v0.16b, { v0.16b }, v1.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <8 x half> @llvm.experimental.vector.interleave2.v8f16(<4 x half> %vec0, <4 x half> %vec1)
|
|
ret <8 x half> %retval
|
|
}
|
|
|
|
define <16 x half> @interleave2_v16f16(<8 x half> %vec0, <8 x half> %vec1) {
|
|
; CHECK-LABEL: interleave2_v16f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: zip2 v1.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <16 x half> @llvm.experimental.vector.interleave2.v16f16(<8 x half> %vec0, <8 x half> %vec1)
|
|
ret <16 x half> %retval
|
|
}
|
|
|
|
define <4 x float> @interleave2_v4f32(<2 x float> %vec0, <2 x float> %vec1) {
|
|
; CHECK-LABEL: interleave2_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
|
|
; CHECK-NEXT: mov v0.d[1], v1.d[0]
|
|
; CHECK-NEXT: rev64 v1.4s, v0.4s
|
|
; CHECK-NEXT: uzp1 v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
%retval = call <4 x float> @llvm.experimental.vector.interleave2.v4f32(<2 x float> %vec0, <2 x float> %vec1)
|
|
ret <4 x float> %retval
|
|
}
|
|
|
|
define <8 x float> @interleave2_v8f32(<4 x float> %vec0, <4 x float> %vec1) {
|
|
; CHECK-LABEL: interleave2_v8f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: zip2 v1.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float> %vec0, <4 x float> %vec1)
|
|
ret <8 x float> %retval
|
|
}
|
|
|
|
define <4 x double> @interleave2_v4f64(<2 x double> %vec0, <2 x double> %vec1) {
|
|
; CHECK-LABEL: interleave2_v4f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: zip2 v1.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <4 x double>@llvm.experimental.vector.interleave2.v4f64(<2 x double> %vec0, <2 x double> %vec1)
|
|
ret <4 x double> %retval
|
|
}
|
|
|
|
; Integers
|
|
|
|
define <32 x i8> @interleave2_v32i8(<16 x i8> %vec0, <16 x i8> %vec1) {
|
|
; CHECK-LABEL: interleave2_v32i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.16b, v0.16b, v1.16b
|
|
; CHECK-NEXT: zip2 v1.16b, v0.16b, v1.16b
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <32 x i8> @llvm.experimental.vector.interleave2.v32i8(<16 x i8> %vec0, <16 x i8> %vec1)
|
|
ret <32 x i8> %retval
|
|
}
|
|
|
|
define <16 x i16> @interleave2_v16i16(<8 x i16> %vec0, <8 x i16> %vec1) {
|
|
; CHECK-LABEL: interleave2_v16i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: zip2 v1.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16> %vec0, <8 x i16> %vec1)
|
|
ret <16 x i16> %retval
|
|
}
|
|
|
|
define <8 x i32> @interleave2_v8i32(<4 x i32> %vec0, <4 x i32> %vec1) {
|
|
; CHECK-LABEL: interleave2_v8i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: zip2 v1.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32> %vec0, <4 x i32> %vec1)
|
|
ret <8 x i32> %retval
|
|
}
|
|
|
|
define <4 x i64> @interleave2_v4i64(<2 x i64> %vec0, <2 x i64> %vec1) {
|
|
; CHECK-LABEL: interleave2_v4i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: zip1 v2.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: zip2 v1.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: ret
|
|
%retval = call <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64> %vec0, <2 x i64> %vec1)
|
|
ret <4 x i64> %retval
|
|
}
|
|
|
|
|
|
; Float declarations
|
|
declare <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half>, <2 x half>)
|
|
declare <8 x half> @llvm.experimental.vector.interleave2.v8f16(<4 x half>, <4 x half>)
|
|
declare <16 x half> @llvm.experimental.vector.interleave2.v16f16(<8 x half>, <8 x half>)
|
|
declare <4 x float> @llvm.experimental.vector.interleave2.v4f32(<2 x float>, <2 x float>)
|
|
declare <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float>, <4 x float>)
|
|
declare <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double>, <2 x double>)
|
|
|
|
; Integer declarations
|
|
declare <32 x i8> @llvm.experimental.vector.interleave2.v32i8(<16 x i8>, <16 x i8>)
|
|
declare <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16>, <8 x i16>)
|
|
declare <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32>, <4 x i32>)
|
|
declare <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64>, <2 x i64>)
|
|
|