forked from OSchip/llvm-project
AMDGPU/GlobalISel: Add selection tests for G_ATOMICRMW_ADD
This commit is contained in:
Matt Arsenault
parent
a107f86417
commit
4fdae24733
|
|
@ -0,0 +1,707 @@
|
|||
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
||||
# RUN: llc -march=amdgcn -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX7 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX7 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX9 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX10 %s
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s32) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
$vgpr0 = COPY %2
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s32) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset2047
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset2047
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2047, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset2047
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2047, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset2047
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2047, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2047
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset2047_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2047, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2047, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2047, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2047
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset2048
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset2048
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset2048
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2048, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset2048
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2048
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset2048_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2048, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2048
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset4095
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset4095
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset4095
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset4095
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset4095_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset4097
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset4097
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset4097
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX9: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX9: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX9: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX9: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX9: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX9: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset4097
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4097
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s32_offset4097_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX9: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX9: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX9: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX9: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX9: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX9: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4097
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 0)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s64
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s64
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX7: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s64
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s64
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX10: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 8, addrspace 0)
|
||||
$vgpr0_vgpr1 = COPY %2
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s64_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s64_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s64_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s64_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 8, addrspace 0)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s64_offset4095
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s64_offset4095
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX7: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s64_offset4095
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s64_offset4095
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX10: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s64) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 8, addrspace 0)
|
||||
$vgpr0_vgpr1 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: flat_atomicrmw_add_s64_offset4095_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX7-LABEL: name: flat_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX9-LABEL: name: flat_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
; GFX10-LABEL: name: flat_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8)
|
||||
%0:vgpr(p0) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p0) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s64) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 8, addrspace 0)
|
||||
|
||||
...
|
||||
|
|
@ -0,0 +1,785 @@
|
|||
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
||||
# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX6 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX7 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX7 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX9 %s
|
||||
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck -check-prefix=GFX10 %s
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_ADD [[COPY]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX6: $vgpr0 = COPY [[ATOMICRMW_ADD]](s32)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s32) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
$vgpr0 = COPY %2
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s32) = G_ATOMICRMW_ADD [[COPY]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s32) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset2047
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset2047
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 2047
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX6: $vgpr0 = COPY [[ATOMICRMW_ADD]](s32)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset2047
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2047, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset2047
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2047, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset2047
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2047, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2047
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset2047_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 2047
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2047, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2047, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset2047_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2047, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2047
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset2048
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset2048
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 2048
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX6: $vgpr0 = COPY [[ATOMICRMW_ADD]](s32)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset2048
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset2048
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2048, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset2048
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2048
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset2048_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 2048
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 2048, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset2048_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2048, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 2048
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset4095
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset4095
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 4095
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX6: $vgpr0 = COPY [[ATOMICRMW_ADD]](s32)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset4095
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset4095
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset4095
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset4095_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 4095
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset4095_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset4097
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset4097
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 4097
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX6: $vgpr0 = COPY [[ATOMICRMW_ADD]](s32)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset4097
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset4097
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX9: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX9: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX9: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX9: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX9: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX9: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset4097
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4097
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
$vgpr0 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s32_offset4097_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 4097
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s32) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX9: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX9: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX9: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX9: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX9: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX9: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX9: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX9: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s32_offset4097_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr2
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4097, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 4, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s32) = COPY $vgpr2
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4097
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s32) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 4, addrspace 1)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s64
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s64
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vreg_64(s64) = G_ATOMICRMW_ADD [[COPY]](p1), [[COPY1]] :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX6: $vgpr0_vgpr1 = COPY [[ATOMICRMW_ADD]](s64)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s64
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX7: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s64
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s64
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX10: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 8, addrspace 1)
|
||||
$vgpr0_vgpr1 = COPY %2
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s64_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s64_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s64) = G_ATOMICRMW_ADD [[COPY]](p1), [[COPY1]] :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s64_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s64_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s64_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_ATOMICRMW_ADD %0, %1 :: (load store seq_cst 8, addrspace 1)
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s64_offset4095
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s64_offset4095
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 4095
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vreg_64(s64) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX6: $vgpr0_vgpr1 = COPY [[ATOMICRMW_ADD]](s64)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s64_offset4095
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX7: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s64_offset4095
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s64_offset4095
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX10: $vgpr0_vgpr1 = COPY [[FLAT_ATOMIC_ADD_X2_RTN]]
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s64) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 8, addrspace 1)
|
||||
$vgpr0_vgpr1 = COPY %4
|
||||
|
||||
...
|
||||
|
||||
---
|
||||
name: global_atomicrmw_add_s64_offset4095_nortn
|
||||
legalized: true
|
||||
regBankSelected: true
|
||||
tracksRegLiveness: true
|
||||
body: |
|
||||
bb.0:
|
||||
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
|
||||
; GFX6-LABEL: name: global_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX6: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX6: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
; GFX6: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 4095
|
||||
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p1) = G_PTR_ADD [[COPY]], [[C]](s64)
|
||||
; GFX6: [[ATOMICRMW_ADD:%[0-9]+]]:vgpr(s64) = G_ATOMICRMW_ADD [[PTR_ADD]](p1), [[COPY1]] :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX7-LABEL: name: global_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX7: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX7: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX7: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX7: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX7: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX7: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX7: %10:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX7: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX7: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX9-LABEL: name: global_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[COPY]], [[COPY1]], 4095, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
; GFX10-LABEL: name: global_atomicrmw_add_s64_offset4095_nortn
|
||||
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
||||
; GFX10: $vcc_hi = IMPLICIT_DEF
|
||||
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
|
||||
; GFX10: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
|
||||
; GFX10: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4095, implicit $exec
|
||||
; GFX10: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_MOV_B32_e32_]], %subreg.sub0, [[V_MOV_B32_e32_1]], %subreg.sub1
|
||||
; GFX10: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
|
||||
; GFX10: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
|
||||
; GFX10: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
|
||||
; GFX10: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub1
|
||||
; GFX10: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_I32_e64 [[COPY2]], [[COPY3]], 0, implicit $exec
|
||||
; GFX10: %10:vgpr_32, dead %12:sreg_32_xm0_xexec = V_ADDC_U32_e64 [[COPY4]], [[COPY5]], killed [[V_ADD_I32_e64_1]], 0, implicit $exec
|
||||
; GFX10: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_ADD_I32_e64_]], %subreg.sub0, %10, %subreg.sub1
|
||||
; GFX10: [[FLAT_ATOMIC_ADD_X2_RTN:%[0-9]+]]:vreg_64 = FLAT_ATOMIC_ADD_X2_RTN [[REG_SEQUENCE1]], [[COPY1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store seq_cst 8, addrspace 1)
|
||||
%0:vgpr(p1) = COPY $vgpr0_vgpr1
|
||||
%1:vgpr(s64) = COPY $vgpr2_vgpr3
|
||||
%2:vgpr(s64) = G_CONSTANT i64 4095
|
||||
%3:vgpr(p1) = G_PTR_ADD %0, %2
|
||||
%4:vgpr(s64) = G_ATOMICRMW_ADD %3, %1 :: (load store seq_cst 8, addrspace 1)
|
||||
|
||||
...
|
||||
Loading…
Reference in New Issue