Files
TheRock/rocm-libraries/shared/stinkytofu/tests/filecheck/redundant_mov_elimination.stir
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

97 lines
3.0 KiB
Plaintext

# RUN: %stinkytofu-opt --arch gfx1250 %s --RedundantMovEliminationPass --print-output
#
# Redundant MOV Elimination: remove duplicate v_mov_b32 instructions
# that write the same value to the same destination.
# Converted from RedundantMovEliminationPassTest.
#--- Simple duplicate: two identical movs, second is eliminated
# CHECK-LABEL: @eliminate_simple_duplicate
# CHECK: v_mov_b32
# CHECK-SAME: v0
# CHECK-SAME: v1
# CHECK: v_add_f32
# CHECK: v_sub_f32
# CHECK-NOT: v_mov_b32
st.func @eliminate_simple_duplicate() {
^entry:
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v3 = "st.v_add_f32"(v4, v5) { issueCycles = 1, latencyCycles = 5 }
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v7 = "st.v_sub_f32"(v0, v3) { issueCycles = 1, latencyCycles = 5 }
}
#--- Multiple duplicates: three identical movs, only first kept
# CHECK-LABEL: @multiple_duplicates
# CHECK: v_mov_b32
# CHECK-SAME: v0
# CHECK-SAME: v1
# CHECK: v_add_f32
# CHECK: v_sub_f32
# CHECK: v_fma_f32
# CHECK-NOT: v_mov_b32
st.func @multiple_duplicates() {
^entry:
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v3 = "st.v_add_f32"(v4, v5) { issueCycles = 1, latencyCycles = 5 }
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v6 = "st.v_sub_f32"(v7, v8) { issueCycles = 1, latencyCycles = 5 }
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v9 = "st.v_fma_f32"(v0, v3, v6) { issueCycles = 1, latencyCycles = 5 }
}
#--- Don't eliminate when source is modified between movs
# CHECK-LABEL: @dont_eliminate_modified_operand
# CHECK: v_mov_b32
# CHECK-SAME: v0
# CHECK-SAME: v1
# CHECK: v_add_f32
# CHECK: v_sub_f32
# CHECK-SAME: v1
# CHECK: v_mov_b32
# CHECK-SAME: v8
# CHECK-SAME: v1
st.func @dont_eliminate_modified_operand() {
^entry:
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v3 = "st.v_add_f32"(v4, v5) { issueCycles = 1, latencyCycles = 5 }
v1 = "st.v_sub_f32"(v6, v7) { issueCycles = 1, latencyCycles = 5 }
v8 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
}
#--- Different operands: all movs have different src/dst, none eliminated
# CHECK-LABEL: @different_operands
# CHECK: v_mov_b32
# CHECK-SAME: v0
# CHECK-SAME: v1
# CHECK: v_mov_b32
# CHECK-SAME: v3
# CHECK-SAME: v4
# CHECK: v_mov_b32
# CHECK-SAME: v6
# CHECK-SAME: v5
st.func @different_operands() {
^entry:
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v3 = "st.v_mov_b32"(v4) { issueCycles = 1, latencyCycles = 1 }
v6 = "st.v_mov_b32"(v5) { issueCycles = 1, latencyCycles = 1 }
}
#--- No duplicates: all movs to different destinations with different sources
# CHECK-LABEL: @no_duplicates
# CHECK: v_mov_b32
# CHECK: v_mov_b32
# CHECK: v_mov_b32
# CHECK: v_mov_b32
st.func @no_duplicates() {
^entry:
v0 = "st.v_mov_b32"(v1) { issueCycles = 1, latencyCycles = 1 }
v3 = "st.v_mov_b32"(v4) { issueCycles = 1, latencyCycles = 1 }
v6 = "st.v_mov_b32"(v7) { issueCycles = 1, latencyCycles = 1 }
v9 = "st.v_mov_b32"(v10) { issueCycles = 1, latencyCycles = 1 }
}