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
173 lines
4.6 KiB
LLVM
173 lines
4.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -global-isel -mattr=+m -verify-machineinstrs < %s \
|
|
; RUN: | FileCheck %s -check-prefixes=CHECK,RV32I
|
|
; RUN: llc -mtriple=riscv32 -global-isel -mattr=+m,+zba -verify-machineinstrs < %s \
|
|
; RUN: | FileCheck %s -check-prefixes=CHECK,RV32ZBA
|
|
|
|
define signext i16 @sh1add(i64 %0, ptr %1) {
|
|
; RV32I-LABEL: sh1add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: slli a0, a0, 1
|
|
; RV32I-NEXT: add a0, a2, a0
|
|
; RV32I-NEXT: lh a0, 0(a0)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: sh1add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: sh1add a0, a0, a2
|
|
; RV32ZBA-NEXT: lh a0, 0(a0)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = getelementptr inbounds i16, ptr %1, i64 %0
|
|
%4 = load i16, ptr %3
|
|
ret i16 %4
|
|
}
|
|
|
|
define i32 @sh2add(i64 %0, ptr %1) {
|
|
; RV32I-LABEL: sh2add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: slli a0, a0, 2
|
|
; RV32I-NEXT: add a0, a2, a0
|
|
; RV32I-NEXT: lw a0, 0(a0)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: sh2add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: sh2add a0, a0, a2
|
|
; RV32ZBA-NEXT: lw a0, 0(a0)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = getelementptr inbounds i32, ptr %1, i64 %0
|
|
%4 = load i32, ptr %3
|
|
ret i32 %4
|
|
}
|
|
|
|
define i64 @sh3add(i64 %0, ptr %1) {
|
|
; RV32I-LABEL: sh3add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: slli a0, a0, 3
|
|
; RV32I-NEXT: add a2, a2, a0
|
|
; RV32I-NEXT: lw a0, 0(a2)
|
|
; RV32I-NEXT: lw a1, 4(a2)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: sh3add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: sh3add a1, a0, a2
|
|
; RV32ZBA-NEXT: lw a0, 0(a1)
|
|
; RV32ZBA-NEXT: lw a1, 4(a1)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = getelementptr inbounds i64, ptr %1, i64 %0
|
|
%4 = load i64, ptr %3
|
|
ret i64 %4
|
|
}
|
|
|
|
define i32 @srli_1_sh2add(ptr %0, i32 %1) {
|
|
; RV32I-LABEL: srli_1_sh2add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: srli a1, a1, 1
|
|
; RV32I-NEXT: slli a1, a1, 2
|
|
; RV32I-NEXT: add a0, a0, a1
|
|
; RV32I-NEXT: lw a0, 0(a0)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: srli_1_sh2add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: srli a1, a1, 1
|
|
; RV32ZBA-NEXT: sh2add a0, a1, a0
|
|
; RV32ZBA-NEXT: lw a0, 0(a0)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = lshr i32 %1, 1
|
|
%4 = getelementptr inbounds i32, ptr %0, i32 %3
|
|
%5 = load i32, ptr %4, align 4
|
|
ret i32 %5
|
|
}
|
|
|
|
define i64 @srli_2_sh3add(ptr %0, i32 %1) {
|
|
; RV32I-LABEL: srli_2_sh3add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: srli a1, a1, 2
|
|
; RV32I-NEXT: slli a1, a1, 3
|
|
; RV32I-NEXT: add a1, a0, a1
|
|
; RV32I-NEXT: lw a0, 0(a1)
|
|
; RV32I-NEXT: lw a1, 4(a1)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: srli_2_sh3add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: srli a1, a1, 2
|
|
; RV32ZBA-NEXT: sh3add a1, a1, a0
|
|
; RV32ZBA-NEXT: lw a0, 0(a1)
|
|
; RV32ZBA-NEXT: lw a1, 4(a1)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = lshr i32 %1, 2
|
|
%4 = getelementptr inbounds i64, ptr %0, i32 %3
|
|
%5 = load i64, ptr %4, align 8
|
|
ret i64 %5
|
|
}
|
|
|
|
define signext i16 @srli_2_sh1add(ptr %0, i32 %1) {
|
|
; RV32I-LABEL: srli_2_sh1add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: srli a1, a1, 2
|
|
; RV32I-NEXT: slli a1, a1, 1
|
|
; RV32I-NEXT: add a0, a0, a1
|
|
; RV32I-NEXT: lh a0, 0(a0)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: srli_2_sh1add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: srli a1, a1, 2
|
|
; RV32ZBA-NEXT: sh1add a0, a1, a0
|
|
; RV32ZBA-NEXT: lh a0, 0(a0)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = lshr i32 %1, 2
|
|
%4 = getelementptr inbounds i16, ptr %0, i32 %3
|
|
%5 = load i16, ptr %4, align 2
|
|
ret i16 %5
|
|
}
|
|
|
|
define i32 @srli_3_sh2add(ptr %0, i32 %1) {
|
|
; RV32I-LABEL: srli_3_sh2add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: srli a1, a1, 3
|
|
; RV32I-NEXT: slli a1, a1, 2
|
|
; RV32I-NEXT: add a0, a0, a1
|
|
; RV32I-NEXT: lw a0, 0(a0)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: srli_3_sh2add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: srli a1, a1, 3
|
|
; RV32ZBA-NEXT: sh2add a0, a1, a0
|
|
; RV32ZBA-NEXT: lw a0, 0(a0)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = lshr i32 %1, 3
|
|
%4 = getelementptr inbounds i32, ptr %0, i32 %3
|
|
%5 = load i32, ptr %4, align 4
|
|
ret i32 %5
|
|
}
|
|
|
|
define i64 @srli_4_sh3add(ptr %0, i32 %1) {
|
|
; RV32I-LABEL: srli_4_sh3add:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: srli a1, a1, 4
|
|
; RV32I-NEXT: slli a1, a1, 3
|
|
; RV32I-NEXT: add a1, a0, a1
|
|
; RV32I-NEXT: lw a0, 0(a1)
|
|
; RV32I-NEXT: lw a1, 4(a1)
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV32ZBA-LABEL: srli_4_sh3add:
|
|
; RV32ZBA: # %bb.0:
|
|
; RV32ZBA-NEXT: srli a1, a1, 4
|
|
; RV32ZBA-NEXT: sh3add a1, a1, a0
|
|
; RV32ZBA-NEXT: lw a0, 0(a1)
|
|
; RV32ZBA-NEXT: lw a1, 4(a1)
|
|
; RV32ZBA-NEXT: ret
|
|
%3 = lshr i32 %1, 4
|
|
%4 = getelementptr inbounds i64, ptr %0, i32 %3
|
|
%5 = load i64, ptr %4, align 8
|
|
ret i64 %5
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; CHECK: {{.*}}
|