llvm.org GIT mirror llvm / release_70 test / CodeGen / AMDGPU / GlobalISel / legalize-merge-values.mir
release_70

Tree @release_70 (Download .tar.gz)

legalize-merge-values.mir @release_70raw · history · blame

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-- -O0 -run-pass=legalizer -o - %s | FileCheck %s

---
name: test_merge_s32_s32_s64
body: |
  bb.0:
    ; CHECK-LABEL: name: test_merge_s32_s32_s64
    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
    ; CHECK: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[C]](s32), [[C1]](s32)
    ; CHECK: $vgpr0_vgpr1 = COPY [[MV]](s64)
    %0:_(s32) = G_CONSTANT i32 0
    %1:_(s32) = G_CONSTANT i32 1
    %2:_(s64) = G_MERGE_VALUES %0:_(s32), %1:_(s32)
    $vgpr0_vgpr1 = COPY %2(s64)
...

---
name: test_merge_s32_s32_v2s32
body: |
  bb.0:
    ; CHECK-LABEL: name: test_merge_s32_s32_v2s32
    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
    ; CHECK: [[MV:%[0-9]+]]:_(<2 x s32>) = G_MERGE_VALUES [[C]](s32), [[C1]](s32)
    ; CHECK: $vgpr0_vgpr1 = COPY [[MV]](<2 x s32>)
    %0:_(s32) = G_CONSTANT i32 0
    %1:_(s32) = G_CONSTANT i32 1
    %2:_(<2 x s32>) = G_MERGE_VALUES %0:_(s32), %1:_(s32)
    $vgpr0_vgpr1 = COPY %2(<2 x s32>)
...

---
name: test_merge_s32_s32_s32_v3s32
body: |
  bb.0:
    ; CHECK-LABEL: name: test_merge_s32_s32_s32_v3s32
    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
    ; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
    ; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 2
    ; CHECK: [[MV:%[0-9]+]]:_(<3 x s32>) = G_MERGE_VALUES [[C]](s32), [[C1]](s32), [[C2]](s32)
    ; CHECK: $vgpr0_vgpr1_vgpr2 = COPY [[MV]](<3 x s32>)
    %0:_(s32) = G_CONSTANT i32 0
    %1:_(s32) = G_CONSTANT i32 1
    %2:_(s32) = G_CONSTANT i32 2
    %3:_(<3 x s32>) = G_MERGE_VALUES %0:_(s32), %1:_(s32), %2:_(s32)
    $vgpr0_vgpr1_vgpr2 = COPY %3(<3 x s32>)
...

---
name: test_merge_s64_s64_s128
body: |
  bb.0:
    ; CHECK-LABEL: name: test_merge_s64_s64_s128
    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK: [[MV:%[0-9]+]]:_(<2 x s64>) = G_MERGE_VALUES [[C]](s64), [[C1]](s64)
    ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[MV]](<2 x s64>)
    %0:_(s64) = G_CONSTANT i64 0
    %1:_(s64) = G_CONSTANT i64 1
    %2:_(<2 x s64>) = G_MERGE_VALUES %0(s64), %1(s64)
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2(<2 x s64>)
...

---
name: test_merge_s64_s64_s64_s64_v4s64
body: |
  bb.0:
    ; CHECK-LABEL: name: test_merge_s64_s64_s64_s64_v4s64
    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
    ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
    ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 2
    ; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 3
    ; CHECK: [[MV:%[0-9]+]]:_(<4 x s64>) = G_MERGE_VALUES [[C]](s64), [[C1]](s64), [[C2]](s64), [[C3]](s64)
    ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[MV]](<4 x s64>)
    %0:_(s64) = G_CONSTANT i64 0
    %1:_(s64) = G_CONSTANT i64 1
    %2:_(s64) = G_CONSTANT i64 2
    %3:_(s64) = G_CONSTANT i64 3
    %4:_(<4 x s64>) = G_MERGE_VALUES %0(s64), %1(s64), %2(s64), %3(s64)
    $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %4(<4 x s64>)
...

# FIXME: Should be split up
# ---
# name: test_merge_17_x_i32
# body: |
#   bb.0:
#     %0:_(s32) = G_CONSTANT i32 0
#     %1:_(s32) = G_CONSTANT i32 1
#     %2:_(s32) = G_CONSTANT i32 2
#     %3:_(s32) = G_CONSTANT i32 3

#     %4:_(s32) = G_CONSTANT i32 4
#     %5:_(s32) = G_CONSTANT i32 5
#     %6:_(s32) = G_CONSTANT i32 6
#     %7:_(s32) = G_CONSTANT i32 7

#     %8:_(s32) = G_CONSTANT i32 8
#     %9:_(s32) = G_CONSTANT i32 9
#     %10:_(s32) = G_CONSTANT i32 10
#     %11:_(s32) = G_CONSTANT i32 11

#     %12:_(s32) = G_CONSTANT i32 12
#     %13:_(s32) = G_CONSTANT i32 13
#     %14:_(s32) = G_CONSTANT i32 14
#     %15:_(s32) = G_CONSTANT i32 15

#     %16:_(s32) = G_CONSTANT i32 16

#     %17:_(<17 x s32>) = G_MERGE_VALUES %0:_(s32), %1:_(s32), %2:_(s32), %3:_(s32), %4:_(s32), %5:_(s32), %6:_(s32), %7:_(s32), %8:_(s32), %9:_(s32), %10:_(s32), %11:_(s32), %12:_(s32), %13:_(s32), %14:_(s32), %15:_(s32), %16:_(s32)
#     S_ENDPGM implicit %17(<17 x s32>)
# ...