llvm-project/llvm/test/CodeGen/AMDGPU/clamp-omod-special-case.mir

425 lines
15 KiB
YAML

# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-fold-operands %s -o - | FileCheck -check-prefix=GCN %s
--- |
define amdgpu_ps void @v_max_self_clamp_not_set_f32() #0 {
ret void
}
define amdgpu_ps void @v_clamp_omod_already_set_f32() #0 {
ret void
}
define amdgpu_ps void @v_omod_mul_omod_already_set_f32() #0 {
ret void
}
define amdgpu_ps void @v_omod_mul_clamp_already_set_f32() #0 {
ret void
}
define amdgpu_ps void @v_omod_add_omod_already_set_f32() #0 {
ret void
}
define amdgpu_ps void @v_omod_add_clamp_already_set_f32() #0 {
ret void
}
attributes #0 = { nounwind "no-signed-zeros-fp-math"="false" }
...
---
# GCN-LABEL: name: v_max_self_clamp_not_set_f32
# GCN: %20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
# GCN-NEXT: %21 = V_MAX_F32_e64 0, killed %20, 0, killed %20, 0, 0, implicit %exec
name: v_max_self_clamp_not_set_f32
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_64_xexec }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_64 }
- { id: 10, class: sreg_32_xm0 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sgpr_64 }
- { id: 13, class: sgpr_128 }
- { id: 14, class: sreg_32_xm0 }
- { id: 15, class: sreg_64 }
- { id: 16, class: sgpr_128 }
- { id: 17, class: vgpr_32 }
- { id: 18, class: vreg_64 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vgpr_32 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vreg_64 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: vreg_64 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%24 = V_ASHRREV_I32_e32 31, %3, implicit %exec
%25 = REG_SEQUENCE %3, 1, %24, 2
%10 = S_MOV_B32 61440
%11 = S_MOV_B32 0
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
%13 = REG_SEQUENCE killed %5, 17, %12, 18
%14 = S_MOV_B32 2
%26 = V_LSHL_B64 killed %25, 2, implicit %exec
%16 = REG_SEQUENCE killed %4, 17, %12, 18
%18 = COPY %26
%17 = BUFFER_LOAD_DWORD_ADDR64 %26, killed %13, 0, 0, 0, 0, 0, implicit %exec
%20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
%21 = V_MAX_F32_e64 0, killed %20, 0, killed %20, 0, 0, implicit %exec
BUFFER_STORE_DWORD_ADDR64 killed %21, %26, killed %16, 0, 0, 0, 0, 0, implicit %exec
S_ENDPGM
...
---
# GCN-LABEL: name: v_clamp_omod_already_set_f32
# GCN: %20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
# GCN: %21 = V_MAX_F32_e64 0, killed %20, 0, killed %20, 1, 3, implicit %exec
name: v_clamp_omod_already_set_f32
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_64_xexec }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_64 }
- { id: 10, class: sreg_32_xm0 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sgpr_64 }
- { id: 13, class: sgpr_128 }
- { id: 14, class: sreg_32_xm0 }
- { id: 15, class: sreg_64 }
- { id: 16, class: sgpr_128 }
- { id: 17, class: vgpr_32 }
- { id: 18, class: vreg_64 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vgpr_32 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vreg_64 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: vreg_64 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%24 = V_ASHRREV_I32_e32 31, %3, implicit %exec
%25 = REG_SEQUENCE %3, 1, %24, 2
%10 = S_MOV_B32 61440
%11 = S_MOV_B32 0
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
%13 = REG_SEQUENCE killed %5, 17, %12, 18
%14 = S_MOV_B32 2
%26 = V_LSHL_B64 killed %25, 2, implicit %exec
%16 = REG_SEQUENCE killed %4, 17, %12, 18
%18 = COPY %26
%17 = BUFFER_LOAD_DWORD_ADDR64 %26, killed %13, 0, 0, 0, 0, 0, implicit %exec
%20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
%21 = V_MAX_F32_e64 0, killed %20, 0, killed %20, 1, 3, implicit %exec
BUFFER_STORE_DWORD_ADDR64 killed %21, %26, killed %16, 0, 0, 0, 0, 0, implicit %exec
S_ENDPGM
...
---
# Don't fold a mul that looks like an omod if itself has omod set
# GCN-LABEL: name: v_omod_mul_omod_already_set_f32
# GCN: %20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
# GCN-NEXT: %21 = V_MUL_F32_e64 0, killed %20, 0, 1056964608, 0, 3, implicit %exec
name: v_omod_mul_omod_already_set_f32
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_64_xexec }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_64 }
- { id: 10, class: sreg_32_xm0 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sgpr_64 }
- { id: 13, class: sgpr_128 }
- { id: 14, class: sreg_32_xm0 }
- { id: 15, class: sreg_64 }
- { id: 16, class: sgpr_128 }
- { id: 17, class: vgpr_32 }
- { id: 18, class: vreg_64 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vgpr_32 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vreg_64 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: vreg_64 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%24 = V_ASHRREV_I32_e32 31, %3, implicit %exec
%25 = REG_SEQUENCE %3, 1, %24, 2
%10 = S_MOV_B32 61440
%11 = S_MOV_B32 0
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
%13 = REG_SEQUENCE killed %5, 17, %12, 18
%14 = S_MOV_B32 2
%26 = V_LSHL_B64 killed %25, 2, implicit %exec
%16 = REG_SEQUENCE killed %4, 17, %12, 18
%18 = COPY %26
%17 = BUFFER_LOAD_DWORD_ADDR64 %26, killed %13, 0, 0, 0, 0, 0, implicit %exec
%20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
%21 = V_MUL_F32_e64 0, killed %20, 0, 1056964608, 0, 3, implicit %exec
BUFFER_STORE_DWORD_ADDR64 killed %21, %26, killed %16, 0, 0, 0, 0, 0, implicit %exec
S_ENDPGM
...
---
# Don't fold a mul that looks like an omod if itself has clamp set
# This might be OK, but would require folding the clamp at the same time.
# GCN-LABEL: name: v_omod_mul_clamp_already_set_f32
# GCN: %20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
# GCN-NEXT: %21 = V_MUL_F32_e64 0, killed %20, 0, 1056964608, 1, 0, implicit %exec
name: v_omod_mul_clamp_already_set_f32
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_64_xexec }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_64 }
- { id: 10, class: sreg_32_xm0 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sgpr_64 }
- { id: 13, class: sgpr_128 }
- { id: 14, class: sreg_32_xm0 }
- { id: 15, class: sreg_64 }
- { id: 16, class: sgpr_128 }
- { id: 17, class: vgpr_32 }
- { id: 18, class: vreg_64 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vgpr_32 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vreg_64 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: vreg_64 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%24 = V_ASHRREV_I32_e32 31, %3, implicit %exec
%25 = REG_SEQUENCE %3, 1, %24, 2
%10 = S_MOV_B32 61440
%11 = S_MOV_B32 0
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
%13 = REG_SEQUENCE killed %5, 17, %12, 18
%14 = S_MOV_B32 2
%26 = V_LSHL_B64 killed %25, 2, implicit %exec
%16 = REG_SEQUENCE killed %4, 17, %12, 18
%18 = COPY %26
%17 = BUFFER_LOAD_DWORD_ADDR64 %26, killed %13, 0, 0, 0, 0, 0, implicit %exec
%20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
%21 = V_MUL_F32_e64 0, killed %20, 0, 1056964608, 1, 0, implicit %exec
BUFFER_STORE_DWORD_ADDR64 killed %21, %26, killed %16, 0, 0, 0, 0, 0, implicit %exec
S_ENDPGM
...
---
# Don't fold a mul that looks like an omod if itself has omod set
# GCN-LABEL: name: v_omod_add_omod_already_set_f32
# GCN: %20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
# GCN-NEXT: %21 = V_ADD_F32_e64 0, killed %20, 0, killed %20, 0, 3, implicit %exec
name: v_omod_add_omod_already_set_f32
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_64_xexec }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_64 }
- { id: 10, class: sreg_32_xm0 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sgpr_64 }
- { id: 13, class: sgpr_128 }
- { id: 14, class: sreg_32_xm0 }
- { id: 15, class: sreg_64 }
- { id: 16, class: sgpr_128 }
- { id: 17, class: vgpr_32 }
- { id: 18, class: vreg_64 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vgpr_32 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vreg_64 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: vreg_64 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%24 = V_ASHRREV_I32_e32 31, %3, implicit %exec
%25 = REG_SEQUENCE %3, 1, %24, 2
%10 = S_MOV_B32 61440
%11 = S_MOV_B32 0
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
%13 = REG_SEQUENCE killed %5, 17, %12, 18
%14 = S_MOV_B32 2
%26 = V_LSHL_B64 killed %25, 2, implicit %exec
%16 = REG_SEQUENCE killed %4, 17, %12, 18
%18 = COPY %26
%17 = BUFFER_LOAD_DWORD_ADDR64 %26, killed %13, 0, 0, 0, 0, 0, implicit %exec
%20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
%21 = V_ADD_F32_e64 0, killed %20, 0, killed %20, 0, 3, implicit %exec
BUFFER_STORE_DWORD_ADDR64 killed %21, %26, killed %16, 0, 0, 0, 0, 0, implicit %exec
S_ENDPGM
...
---
# Don't fold a mul that looks like an omod if itself has clamp set
# This might be OK, but would require folding the clamp at the same time.
# GCN-LABEL: name: v_omod_add_clamp_already_set_f32
# GCN: %20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
# GCN-NEXT: %21 = V_ADD_F32_e64 0, killed %20, 0, killed %20, 1, 0, implicit %exec
name: v_omod_add_clamp_already_set_f32
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_64_xexec }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_64 }
- { id: 10, class: sreg_32_xm0 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sgpr_64 }
- { id: 13, class: sgpr_128 }
- { id: 14, class: sreg_32_xm0 }
- { id: 15, class: sreg_64 }
- { id: 16, class: sgpr_128 }
- { id: 17, class: vgpr_32 }
- { id: 18, class: vreg_64 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vgpr_32 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vreg_64 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: vreg_64 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%24 = V_ASHRREV_I32_e32 31, %3, implicit %exec
%25 = REG_SEQUENCE %3, 1, %24, 2
%10 = S_MOV_B32 61440
%11 = S_MOV_B32 0
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
%13 = REG_SEQUENCE killed %5, 17, %12, 18
%14 = S_MOV_B32 2
%26 = V_LSHL_B64 killed %25, 2, implicit %exec
%16 = REG_SEQUENCE killed %4, 17, %12, 18
%18 = COPY %26
%17 = BUFFER_LOAD_DWORD_ADDR64 %26, killed %13, 0, 0, 0, 0, 0, implicit %exec
%20 = V_ADD_F32_e64 0, killed %17, 0, 1065353216, 0, 0, implicit %exec
%21 = V_ADD_F32_e64 0, killed %20, 0, killed %20, 1, 0, implicit %exec
BUFFER_STORE_DWORD_ADDR64 killed %21, %26, killed %16, 0, 0, 0, 0, 0, implicit %exec
S_ENDPGM
...