; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
; RUN: llc -global-isel=1 -mtriple=amdgcn--amdpal -mcpu=gfx1100 -mattr=+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=GISEL-GFX11 %s
; RUN: llc -global-isel=1 -mtriple=amdgcn--amdpal -mcpu=gfx1030 -mattr=+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=GISEL-GFX10 %s
; RUN: llc -global-isel=0 -mtriple=amdgcn--amdpal -mcpu=gfx1100 -mattr=+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX11 %s
; RUN: llc -global-isel=0 -mtriple=amdgcn--amdpal -mcpu=gfx1030 -mattr=+wavefrontsize64 -stop-after=finalize-isel -verify-machineinstrs < %s | FileCheck -check-prefix=DAGISEL-GFX10 %s
declare amdgpu_cs_chain void @callee(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
declare amdgpu_cs_chain_preserve void @callee_preserve(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
declare void @llvm.amdgcn.cs.chain(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) noreturn
define amdgpu_cs_chain void @chain_to_chain(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: chain_to_chain
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; GISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[COPY7]], @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: chain_to_chain
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; GISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[COPY8]], @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: chain_to_chain
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: chain_to_chain
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs void @cs_to_chain(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: cs_to_chain
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; GISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[COPY7]], @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: cs_to_chain
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; GISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[COPY8]], @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: cs_to_chain
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: cs_to_chain
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs_chain void @chain_to_chain_preserve(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: chain_to_chain_preserve
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; GISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[COPY7]], @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: chain_to_chain_preserve
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; GISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[COPY8]], @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: chain_to_chain_preserve
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee_preserve, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: chain_to_chain_preserve
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee_preserve, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs void @cs_to_chain_preserve(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: cs_to_chain_preserve
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; GISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[COPY7]], @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: cs_to_chain_preserve
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY1]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY2]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; GISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[COPY8]], @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: cs_to_chain_preserve
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee_preserve, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: cs_to_chain_preserve
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee_preserve
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee_preserve
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], @callee_preserve, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs_chain void @indirect(ptr inreg %callee, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: indirect
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY2]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY3]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY7]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY8]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[REG_SEQUENCE]], 0, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: indirect
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY2]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY3]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY8]]
; GISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[REG_SEQUENCE]], 0, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: indirect
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], 0, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: indirect
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; DAGISEL-GFX10-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE]], 0, 0, killed [[S_MOV_B64_]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr %callee, i64 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs_chain void @non_imm_exec(i64 inreg %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: non_imm_exec
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY2]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY3]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY7]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY8]]
; GISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; GISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; GISEL-GFX11-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY9:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE1]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[COPY9]], @callee, 0, [[REG_SEQUENCE]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: non_imm_exec
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY2]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY3]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY8]]
; GISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
; GISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; GISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; GISEL-GFX10-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY10:%[0-9]+]]:ccr_sgpr_64 = COPY [[REG_SEQUENCE1]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[COPY10]], @callee, 0, [[REG_SEQUENCE]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: non_imm_exec
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; DAGISEL-GFX11-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE1]], @callee, 0, killed [[REG_SEQUENCE]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: non_imm_exec
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr4
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr3
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-hi) @callee
; DAGISEL-GFX10-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 target-flags(amdgpu-abs32-lo) @callee
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE killed [[S_MOV_B32_1]], %subreg.sub0, killed [[S_MOV_B32_]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY9]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE1]], @callee, 0, killed [[REG_SEQUENCE]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i64 %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs_chain void @indirect_with_non_imm_exec(ptr inreg %callee, i64 inreg %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GISEL-GFX11-LABEL: name: indirect_with_non_imm_exec
; GISEL-GFX11: bb.1 (%ir-block.0):
; GISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX11-NEXT: {{ $}}
; GISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
; GISEL-GFX11-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1
; GISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
; GISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr5
; GISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; GISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX11-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX11-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY4]]
; GISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; GISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY6]]
; GISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY7]]
; GISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY8]]
; GISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY9]]
; GISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY10]]
; GISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 [[REG_SEQUENCE]], 0, 0, [[REG_SEQUENCE1]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GISEL-GFX10-LABEL: name: indirect_with_non_imm_exec
; GISEL-GFX10: bb.1 (%ir-block.0):
; GISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GISEL-GFX10-NEXT: {{ $}}
; GISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; GISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_32 = COPY $sgpr2
; GISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr3
; GISEL-GFX10-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1
; GISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr4
; GISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr5
; GISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; GISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; GISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; GISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; GISEL-GFX10-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; GISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY4]]
; GISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; GISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY6]]
; GISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY7]]
; GISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY8]]
; GISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY9]]
; GISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY10]]
; GISEL-GFX10-NEXT: [[COPY11:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY11]]
; GISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 [[REG_SEQUENCE]], 0, 0, [[REG_SEQUENCE1]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
;
; DAGISEL-GFX11-LABEL: name: indirect_with_non_imm_exec
; DAGISEL-GFX11: bb.0 (%ir-block.0):
; DAGISEL-GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX11-NEXT: {{ $}}
; DAGISEL-GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX11-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr6
; DAGISEL-GFX11-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr5
; DAGISEL-GFX11-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr4
; DAGISEL-GFX11-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr3
; DAGISEL-GFX11-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX11-NEXT: [[COPY9:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX11-NEXT: [[COPY10:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
; DAGISEL-GFX11-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY10]], %subreg.sub0, [[COPY9]], %subreg.sub1
; DAGISEL-GFX11-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX11-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX11-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX11-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX11-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX11-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX11-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX11-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE1]], 0, 0, killed [[REG_SEQUENCE]], amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; DAGISEL-GFX10-LABEL: name: indirect_with_non_imm_exec
; DAGISEL-GFX10: bb.0 (%ir-block.0):
; DAGISEL-GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; DAGISEL-GFX10-NEXT: {{ $}}
; DAGISEL-GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr11
; DAGISEL-GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr10
; DAGISEL-GFX10-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr9
; DAGISEL-GFX10-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; DAGISEL-GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr6
; DAGISEL-GFX10-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr5
; DAGISEL-GFX10-NEXT: [[COPY6:%[0-9]+]]:sgpr_32 = COPY $sgpr4
; DAGISEL-GFX10-NEXT: [[COPY7:%[0-9]+]]:sgpr_32 = COPY $sgpr3
; DAGISEL-GFX10-NEXT: [[COPY8:%[0-9]+]]:sgpr_32 = COPY $sgpr2
; DAGISEL-GFX10-NEXT: [[COPY9:%[0-9]+]]:sgpr_32 = COPY $sgpr1
; DAGISEL-GFX10-NEXT: [[COPY10:%[0-9]+]]:sgpr_32 = COPY $sgpr0
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY7]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:ccr_sgpr_64 = REG_SEQUENCE [[COPY10]], %subreg.sub0, [[COPY9]], %subreg.sub1
; DAGISEL-GFX10-NEXT: [[COPY11:%[0-9]+]]:sgpr_128 = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; DAGISEL-GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY11]]
; DAGISEL-GFX10-NEXT: $sgpr0 = COPY [[COPY6]]
; DAGISEL-GFX10-NEXT: $sgpr1 = COPY [[COPY5]]
; DAGISEL-GFX10-NEXT: $sgpr2 = COPY [[COPY4]]
; DAGISEL-GFX10-NEXT: $vgpr8 = COPY [[COPY3]]
; DAGISEL-GFX10-NEXT: $vgpr9 = COPY [[COPY2]]
; DAGISEL-GFX10-NEXT: $vgpr10 = COPY [[COPY1]]
; DAGISEL-GFX10-NEXT: $vgpr11 = COPY [[COPY]]
; DAGISEL-GFX10-NEXT: SI_CS_CHAIN_TC_W64 killed [[REG_SEQUENCE1]], 0, 0, killed [[REG_SEQUENCE]], amdgpu_allvgprs, implicit $sgpr48_sgpr49_sgpr50_sgpr51, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
call void(ptr, i64, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr %callee, i64 %exec, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
Codebase Browser
llvm