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
186 lines
9.5 KiB
LLVM
186 lines
9.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple aarch64-none-linux-gnu -mattr=+sve2p1 -stop-after=finalize-isel | FileCheck %s --check-prefix=CHECK
|
|
|
|
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64-none-linux-gnu"
|
|
|
|
define <vscale x 16 x i8> @test_svadd_i8(<vscale x 16 x i8> %Zn, <vscale x 16 x i8> %Zm) {
|
|
; CHECK-LABEL: name: test_svadd_i8
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $z0, $z1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z1
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:zpr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:zpr_3b = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"add $0.b, $1.b, $2.b", attdialect, regdef:ZPR, def %2, reguse:ZPR, [[COPY2]], reguse:ZPR_3b, [[COPY3]]
|
|
; CHECK-NEXT: $z0 = COPY %2
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 16 x i8> asm "add $0.b, $1.b, $2.b", "=w,w,y"(<vscale x 16 x i8> %Zn, <vscale x 16 x i8> %Zm)
|
|
ret <vscale x 16 x i8> %1
|
|
}
|
|
|
|
define <vscale x 2 x i64> @test_svsub_i64(<vscale x 2 x i64> %Zn, <vscale x 2 x i64> %Zm) {
|
|
; CHECK-LABEL: name: test_svsub_i64
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $z0, $z1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z1
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:zpr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:zpr_4b = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"sub $0.d, $1.d, $2.d", attdialect, regdef:ZPR, def %2, reguse:ZPR, [[COPY2]], reguse:ZPR_4b, [[COPY3]]
|
|
; CHECK-NEXT: $z0 = COPY %2
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 2 x i64> asm "sub $0.d, $1.d, $2.d", "=w,w,x"(<vscale x 2 x i64> %Zn, <vscale x 2 x i64> %Zm)
|
|
ret <vscale x 2 x i64> %1
|
|
}
|
|
|
|
define <vscale x 8 x half> @test_svfmul_f16(<vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm) {
|
|
; CHECK-LABEL: name: test_svfmul_f16
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $z0, $z1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z1
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:zpr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:zpr_3b = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"fmul $0.h, $1.h, $2.h", attdialect, regdef:ZPR, def %2, reguse:ZPR, [[COPY2]], reguse:ZPR_3b, [[COPY3]]
|
|
; CHECK-NEXT: $z0 = COPY %2
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 8 x half> asm "fmul $0.h, $1.h, $2.h", "=w,w,y"(<vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm)
|
|
ret <vscale x 8 x half> %1
|
|
}
|
|
|
|
define <vscale x 4 x float> @test_svfmul_f(<vscale x 4 x float> %Zn, <vscale x 4 x float> %Zm) {
|
|
; CHECK-LABEL: name: test_svfmul_f
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $z0, $z1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z1
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:zpr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:zpr_4b = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"fmul $0.s, $1.s, $2.s", attdialect, regdef:ZPR, def %2, reguse:ZPR, [[COPY2]], reguse:ZPR_4b, [[COPY3]]
|
|
; CHECK-NEXT: $z0 = COPY %2
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 4 x float> asm "fmul $0.s, $1.s, $2.s", "=w,w,x"(<vscale x 4 x float> %Zn, <vscale x 4 x float> %Zm)
|
|
ret <vscale x 4 x float> %1
|
|
}
|
|
|
|
define <vscale x 8 x half> @test_svfadd_f16(<vscale x 16 x i1> %Pg, <vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm) {
|
|
; CHECK-LABEL: name: test_svfadd_f16
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $p0, $z0, $z1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z1
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:ppr = COPY $p0
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:ppr_3b = COPY [[COPY2]]
|
|
; CHECK-NEXT: [[COPY4:%[0-9]+]]:zpr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY5:%[0-9]+]]:zpr = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"fadd $0.h, $1/m, $2.h, $3.h", attdialect, regdef:ZPR, def %3, reguse:PPR_3b, [[COPY3]], reguse:ZPR, [[COPY4]], reguse:ZPR, [[COPY5]]
|
|
; CHECK-NEXT: $z0 = COPY %3
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 8 x half> asm "fadd $0.h, $1/m, $2.h, $3.h", "=w,@3Upl,w,w"(<vscale x 16 x i1> %Pg, <vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm)
|
|
ret <vscale x 8 x half> %1
|
|
}
|
|
|
|
define <vscale x 4 x i32> @test_incp(<vscale x 16 x i1> %Pg, <vscale x 4 x i32> %Zn) {
|
|
; CHECK-LABEL: name: test_incp
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $p0, $z0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:ppr = COPY $p0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:ppr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:zpr = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"incp $0.s, $1", attdialect, regdef:ZPR, def %2, reguse:PPR, [[COPY2]], reguse tiedto:$0, [[COPY3]](tied-def 3)
|
|
; CHECK-NEXT: $z0 = COPY %2
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 4 x i32> asm "incp $0.s, $1", "=w,@3Upa,0"(<vscale x 16 x i1> %Pg, <vscale x 4 x i32> %Zn)
|
|
ret <vscale x 4 x i32> %1
|
|
}
|
|
|
|
define <vscale x 8 x half> @test_svfadd_f16_Uph_constraint(<vscale x 16 x i1> %Pg, <vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm) {
|
|
; CHECK-LABEL: name: test_svfadd_f16_Uph_constraint
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $p0, $z0, $z1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:zpr = COPY $z1
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:zpr = COPY $z0
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:ppr = COPY $p0
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:ppr_p8to15 = COPY [[COPY2]]
|
|
; CHECK-NEXT: [[COPY4:%[0-9]+]]:zpr = COPY [[COPY1]]
|
|
; CHECK-NEXT: [[COPY5:%[0-9]+]]:zpr = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"fadd $0.h, $1/m, $2.h, $3.h", attdialect, regdef:ZPR, def %3, reguse:PPR_p8to15, [[COPY3]], reguse:ZPR, [[COPY4]], reguse:ZPR, [[COPY5]]
|
|
; CHECK-NEXT: $z0 = COPY %3
|
|
; CHECK-NEXT: RET_ReallyLR implicit $z0
|
|
%1 = tail call <vscale x 8 x half> asm "fadd $0.h, $1/m, $2.h, $3.h", "=w,@3Uph,w,w"(<vscale x 16 x i1> %Pg, <vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm)
|
|
ret <vscale x 8 x half> %1
|
|
}
|
|
|
|
define void @explicit_p0(ptr %p) {
|
|
; CHECK-LABEL: name: explicit_p0
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $x0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
|
|
; CHECK-NEXT: [[PTRUE_B:%[0-9]+]]:ppr = PTRUE_B 31, implicit $vg
|
|
; CHECK-NEXT: $p0 = COPY [[PTRUE_B]]
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64common = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"ld4w { z0.s, z1.s, z2.s, z3.s }, $1/z, [$0]", sideeffect attdialect, regdef:GPR64common, def %1, reguse, $p0, reguse tiedto:$0, [[COPY1]](tied-def 3)
|
|
; CHECK-NEXT: RET_ReallyLR
|
|
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.b8(i32 31)
|
|
%2 = tail call i64 asm sideeffect "ld4w { z0.s, z1.s, z2.s, z3.s }, $1/z, [$0]", "=r,{p0},0"(<vscale x 16 x i1> %1, ptr %p)
|
|
ret void
|
|
}
|
|
|
|
define void @explicit_p8_invalid(ptr %p) {
|
|
; CHECK-LABEL: name: explicit_p8_invalid
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $x0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
|
|
; CHECK-NEXT: [[PTRUE_B:%[0-9]+]]:ppr = PTRUE_B 31, implicit $vg
|
|
; CHECK-NEXT: $p8 = COPY [[PTRUE_B]]
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64common = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"ld4w { z0.s, z1.s, z2.s, z3.s }, $1/z, [$0]", sideeffect attdialect, regdef:GPR64common, def %1, reguse, $p8, reguse tiedto:$0, [[COPY1]](tied-def 3)
|
|
; CHECK-NEXT: RET_ReallyLR
|
|
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.b8(i32 31)
|
|
%2 = tail call i64 asm sideeffect "ld4w { z0.s, z1.s, z2.s, z3.s }, $1/z, [$0]", "=r,{p8},0"(<vscale x 16 x i1> %1, ptr %p)
|
|
ret void
|
|
}
|
|
|
|
define void @explicit_pn8(ptr %p) {
|
|
; CHECK-LABEL: name: explicit_pn8
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $x0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
|
|
; CHECK-NEXT: [[PTRUE_C_B:%[0-9]+]]:pnr_p8to15 = PTRUE_C_B implicit $vg
|
|
; CHECK-NEXT: $pn8 = COPY [[PTRUE_C_B]]
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64common = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"ld1w { z0.s, z4.s, z8.s, z12.s }, $1/z, [$0]", sideeffect attdialect, regdef:GPR64common, def %1, reguse, $pn8, reguse tiedto:$0, [[COPY1]](tied-def 3)
|
|
; CHECK-NEXT: RET_ReallyLR
|
|
%1 = tail call target("aarch64.svcount") @llvm.aarch64.sve.ptrue.c8()
|
|
%2 = tail call i64 asm sideeffect "ld1w { z0.s, z4.s, z8.s, z12.s }, $1/z, [$0]", "=r,{pn8},0"(target("aarch64.svcount") %1, ptr %p)
|
|
ret void
|
|
}
|
|
|
|
define void @explicit_pn0_invalid(ptr %p) {
|
|
; CHECK-LABEL: name: explicit_pn0_invalid
|
|
; CHECK: bb.0 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $x0
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
|
|
; CHECK-NEXT: [[PTRUE_C_B:%[0-9]+]]:pnr_p8to15 = PTRUE_C_B implicit $vg
|
|
; CHECK-NEXT: $pn0 = COPY [[PTRUE_C_B]]
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64common = COPY [[COPY]]
|
|
; CHECK-NEXT: INLINEASM &"ld1w { z0.s, z4.s, z8.s, z12.s }, $1/z, [$0]", sideeffect attdialect, regdef:GPR64common, def %1, reguse, $pn0, reguse tiedto:$0, [[COPY1]](tied-def 3)
|
|
; CHECK-NEXT: RET_ReallyLR
|
|
%1 = tail call target("aarch64.svcount") @llvm.aarch64.sve.ptrue.c8()
|
|
%2 = tail call i64 asm sideeffect "ld1w { z0.s, z4.s, z8.s, z12.s }, $1/z, [$0]", "=r,{pn0},0"(target("aarch64.svcount") %1, ptr %p)
|
|
ret void
|
|
}
|