derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
218 lines
8.2 KiB
LLVM
218 lines
8.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -enable-subreg-liveness -mattr=+sve -force-streaming-compatible < %s | FileCheck %s
|
|
; RUN: llc -enable-subreg-liveness -mattr=+sme -force-streaming < %s | FileCheck %s
|
|
; RUN: llc -enable-subreg-liveness -force-streaming-compatible < %s | FileCheck %s --check-prefix=NONEON-NOSVE
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
declare void @def(ptr)
|
|
|
|
define void @alloc_v4i8(ptr %st_ptr) nounwind {
|
|
; CHECK-LABEL: alloc_v4i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov x19, x0
|
|
; CHECK-NEXT: add x0, sp, #12
|
|
; CHECK-NEXT: add x20, sp, #12
|
|
; CHECK-NEXT: bl def
|
|
; CHECK-NEXT: ptrue p0.b, vl2
|
|
; CHECK-NEXT: ld2b { z0.b, z1.b }, p0/z, [x20]
|
|
; CHECK-NEXT: ptrue p0.s, vl2
|
|
; CHECK-NEXT: mov z1.b, z0.b[1]
|
|
; CHECK-NEXT: zip1 z0.s, z0.s, z1.s
|
|
; CHECK-NEXT: st1b { z0.s }, p0, [x19]
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; NONEON-NOSVE-LABEL: alloc_v4i8:
|
|
; NONEON-NOSVE: // %bb.0:
|
|
; NONEON-NOSVE-NEXT: sub sp, sp, #32
|
|
; NONEON-NOSVE-NEXT: stp x30, x19, [sp, #16] // 16-byte Folded Spill
|
|
; NONEON-NOSVE-NEXT: mov x19, x0
|
|
; NONEON-NOSVE-NEXT: add x0, sp, #12
|
|
; NONEON-NOSVE-NEXT: bl def
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #14]
|
|
; NONEON-NOSVE-NEXT: ldrb w9, [sp, #12]
|
|
; NONEON-NOSVE-NEXT: strb w8, [x19, #1]
|
|
; NONEON-NOSVE-NEXT: strb w9, [x19]
|
|
; NONEON-NOSVE-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
|
|
; NONEON-NOSVE-NEXT: add sp, sp, #32
|
|
; NONEON-NOSVE-NEXT: ret
|
|
%alloc = alloca [4 x i8]
|
|
call void @def(ptr %alloc)
|
|
%load = load <4 x i8>, ptr %alloc
|
|
%strided.vec = shufflevector <4 x i8> %load, <4 x i8> poison, <2 x i32> <i32 0, i32 2>
|
|
store <2 x i8> %strided.vec, ptr %st_ptr
|
|
ret void
|
|
}
|
|
|
|
define void @alloc_v6i8(ptr %st_ptr) nounwind {
|
|
; CHECK-LABEL: alloc_v6i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #32
|
|
; CHECK-NEXT: stp x30, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov x19, x0
|
|
; CHECK-NEXT: add x0, sp, #8
|
|
; CHECK-NEXT: bl def
|
|
; CHECK-NEXT: ldr d0, [sp, #8]
|
|
; CHECK-NEXT: ptrue p0.h, vl4
|
|
; CHECK-NEXT: add x8, sp, #4
|
|
; CHECK-NEXT: ptrue p1.s, vl2
|
|
; CHECK-NEXT: mov z1.b, z0.b[3]
|
|
; CHECK-NEXT: mov z2.b, z0.b[1]
|
|
; CHECK-NEXT: mov z0.b, z0.b[5]
|
|
; CHECK-NEXT: zip1 z1.h, z2.h, z1.h
|
|
; CHECK-NEXT: zip1 z1.s, z1.s, z0.s
|
|
; CHECK-NEXT: st1b { z1.h }, p0, [x8]
|
|
; CHECK-NEXT: ld1h { z1.s }, p1/z, [x8]
|
|
; CHECK-NEXT: fmov w8, s0
|
|
; CHECK-NEXT: strb w8, [x19, #2]
|
|
; CHECK-NEXT: str h1, [x19]
|
|
; CHECK-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: add sp, sp, #32
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; NONEON-NOSVE-LABEL: alloc_v6i8:
|
|
; NONEON-NOSVE: // %bb.0:
|
|
; NONEON-NOSVE-NEXT: sub sp, sp, #48
|
|
; NONEON-NOSVE-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
|
|
; NONEON-NOSVE-NEXT: mov x19, x0
|
|
; NONEON-NOSVE-NEXT: add x0, sp, #24
|
|
; NONEON-NOSVE-NEXT: bl def
|
|
; NONEON-NOSVE-NEXT: ldr d0, [sp, #24]
|
|
; NONEON-NOSVE-NEXT: str d0, [sp, #8]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #11]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #21]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #9]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #20]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #13]
|
|
; NONEON-NOSVE-NEXT: ldrh w9, [sp, #20]
|
|
; NONEON-NOSVE-NEXT: strb w8, [x19, #2]
|
|
; NONEON-NOSVE-NEXT: strh w9, [x19]
|
|
; NONEON-NOSVE-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
|
|
; NONEON-NOSVE-NEXT: add sp, sp, #48
|
|
; NONEON-NOSVE-NEXT: ret
|
|
%alloc = alloca [6 x i8]
|
|
call void @def(ptr %alloc)
|
|
%load = load <6 x i8>, ptr %alloc
|
|
%strided.vec = shufflevector <6 x i8> %load, <6 x i8> poison, <3 x i32> <i32 1, i32 3, i32 5>
|
|
store <3 x i8> %strided.vec, ptr %st_ptr
|
|
ret void
|
|
}
|
|
|
|
define void @alloc_v32i8(ptr %st_ptr) nounwind {
|
|
; CHECK-LABEL: alloc_v32i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #48
|
|
; CHECK-NEXT: stp x30, x19, [sp, #32] // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov x19, x0
|
|
; CHECK-NEXT: mov x0, sp
|
|
; CHECK-NEXT: bl def
|
|
; CHECK-NEXT: adrp x8, .LCPI2_0
|
|
; CHECK-NEXT: ldr q0, [sp]
|
|
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI2_0]
|
|
; CHECK-NEXT: ldrb w8, [sp, #16]
|
|
; CHECK-NEXT: tbl z0.b, { z0.b }, z1.b
|
|
; CHECK-NEXT: strb w8, [x19, #8]
|
|
; CHECK-NEXT: str d0, [x19]
|
|
; CHECK-NEXT: ldp x30, x19, [sp, #32] // 16-byte Folded Reload
|
|
; CHECK-NEXT: add sp, sp, #48
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; NONEON-NOSVE-LABEL: alloc_v32i8:
|
|
; NONEON-NOSVE: // %bb.0:
|
|
; NONEON-NOSVE-NEXT: sub sp, sp, #112
|
|
; NONEON-NOSVE-NEXT: stp x30, x19, [sp, #96] // 16-byte Folded Spill
|
|
; NONEON-NOSVE-NEXT: mov x19, x0
|
|
; NONEON-NOSVE-NEXT: add x0, sp, #64
|
|
; NONEON-NOSVE-NEXT: bl def
|
|
; NONEON-NOSVE-NEXT: ldp q0, q1, [sp, #64]
|
|
; NONEON-NOSVE-NEXT: str q0, [sp]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #14]
|
|
; NONEON-NOSVE-NEXT: str q1, [sp, #32]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #23]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #12]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #22]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #10]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #21]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #8]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #20]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #6]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #19]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #4]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #18]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #2]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #17]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp]
|
|
; NONEON-NOSVE-NEXT: strb w8, [sp, #16]
|
|
; NONEON-NOSVE-NEXT: ldrb w8, [sp, #32]
|
|
; NONEON-NOSVE-NEXT: ldr q0, [sp, #16]
|
|
; NONEON-NOSVE-NEXT: strb w8, [x19, #8]
|
|
; NONEON-NOSVE-NEXT: str q0, [sp, #48]
|
|
; NONEON-NOSVE-NEXT: ldr x8, [sp, #48]
|
|
; NONEON-NOSVE-NEXT: str x8, [x19]
|
|
; NONEON-NOSVE-NEXT: ldp x30, x19, [sp, #96] // 16-byte Folded Reload
|
|
; NONEON-NOSVE-NEXT: add sp, sp, #112
|
|
; NONEON-NOSVE-NEXT: ret
|
|
%alloc = alloca [32 x i8]
|
|
call void @def(ptr %alloc)
|
|
%load = load <32 x i8>, ptr %alloc
|
|
%strided.vec = shufflevector <32 x i8> %load, <32 x i8> poison, <9 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16>
|
|
store <9 x i8> %strided.vec, ptr %st_ptr
|
|
ret void
|
|
}
|
|
|
|
|
|
define void @alloc_v8f64(ptr %st_ptr) nounwind {
|
|
; CHECK-LABEL: alloc_v8f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #96
|
|
; CHECK-NEXT: stp x20, x19, [sp, #80] // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov x19, x0
|
|
; CHECK-NEXT: mov x0, sp
|
|
; CHECK-NEXT: str x30, [sp, #64] // 8-byte Spill
|
|
; CHECK-NEXT: mov x20, sp
|
|
; CHECK-NEXT: bl def
|
|
; CHECK-NEXT: ptrue p0.d, vl2
|
|
; CHECK-NEXT: mov x8, #4 // =0x4
|
|
; CHECK-NEXT: ld2d { z0.d, z1.d }, p0/z, [x20]
|
|
; CHECK-NEXT: ld2d { z1.d, z2.d }, p0/z, [x20, x8, lsl #3]
|
|
; CHECK-NEXT: ldr x30, [sp, #64] // 8-byte Reload
|
|
; CHECK-NEXT: stp q0, q1, [x19]
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #80] // 16-byte Folded Reload
|
|
; CHECK-NEXT: add sp, sp, #96
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; NONEON-NOSVE-LABEL: alloc_v8f64:
|
|
; NONEON-NOSVE: // %bb.0:
|
|
; NONEON-NOSVE-NEXT: sub sp, sp, #176
|
|
; NONEON-NOSVE-NEXT: stp x30, x19, [sp, #160] // 16-byte Folded Spill
|
|
; NONEON-NOSVE-NEXT: mov x19, x0
|
|
; NONEON-NOSVE-NEXT: add x0, sp, #96
|
|
; NONEON-NOSVE-NEXT: bl def
|
|
; NONEON-NOSVE-NEXT: ldp q1, q0, [sp, #96]
|
|
; NONEON-NOSVE-NEXT: ldp q2, q3, [sp, #128]
|
|
; NONEON-NOSVE-NEXT: stp q1, q0, [sp, #48]
|
|
; NONEON-NOSVE-NEXT: ldr d1, [sp, #64]
|
|
; NONEON-NOSVE-NEXT: ldr d0, [sp, #48]
|
|
; NONEON-NOSVE-NEXT: stp q2, q3, [sp]
|
|
; NONEON-NOSVE-NEXT: stp d0, d1, [sp, #80]
|
|
; NONEON-NOSVE-NEXT: ldr d1, [sp, #16]
|
|
; NONEON-NOSVE-NEXT: ldr d0, [sp]
|
|
; NONEON-NOSVE-NEXT: stp d0, d1, [sp, #32]
|
|
; NONEON-NOSVE-NEXT: ldr q1, [sp, #80]
|
|
; NONEON-NOSVE-NEXT: ldr q0, [sp, #32]
|
|
; NONEON-NOSVE-NEXT: stp q1, q0, [x19]
|
|
; NONEON-NOSVE-NEXT: ldp x30, x19, [sp, #160] // 16-byte Folded Reload
|
|
; NONEON-NOSVE-NEXT: add sp, sp, #176
|
|
; NONEON-NOSVE-NEXT: ret
|
|
%alloc = alloca [8 x double]
|
|
call void @def(ptr %alloc)
|
|
%load = load <8 x double>, ptr %alloc
|
|
%strided.vec = shufflevector <8 x double> %load, <8 x double> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
store <4 x double> %strided.vec, ptr %st_ptr
|
|
ret void
|
|
}
|