Files
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

334 lines
10 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=riscv32 < %s | FileCheck -check-prefixes=RV32,NO-ZBA %s
; RUN: llc -mtriple=riscv32 -mattr=+zba < %s | FileCheck -check-prefixes=RV32,ZBA %s
; RUN: llc -mtriple=riscv32 -mattr=+xandesperf < %s | FileCheck -check-prefixes=RV32,XANDESPERF %s
define i32 @add_shl_oneUse(i32 %x, i32 %y) nounwind {
; NO-ZBA-LABEL: add_shl_oneUse:
; NO-ZBA: # %bb.0:
; NO-ZBA-NEXT: slli a0, a0, 3
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: addi a0, a0, 984
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_oneUse:
; ZBA: # %bb.0:
; ZBA-NEXT: addi a0, a0, 123
; ZBA-NEXT: sh3add a0, a0, a1
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_oneUse:
; XANDESPERF: # %bb.0:
; XANDESPERF-NEXT: addi a0, a0, 123
; XANDESPERF-NEXT: nds.lea.d a0, a1, a0
; XANDESPERF-NEXT: ret
%add.0 = add i32 %x, 123
%shl = shl i32 %add.0, 3
%add.1 = add i32 %shl, %y
ret i32 %add.1
}
define void @add_shl_moreOneUse_inStore(ptr %array1, i32 %a, i32 %b) {
; NO-ZBA-LABEL: add_shl_moreOneUse_inStore:
; NO-ZBA: # %bb.0: # %entry
; NO-ZBA-NEXT: addi a3, a1, 5
; NO-ZBA-NEXT: slli a1, a1, 2
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: sw a2, 20(a0)
; NO-ZBA-NEXT: sw a2, 24(a0)
; NO-ZBA-NEXT: sw a3, 140(a0)
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_inStore:
; ZBA: # %bb.0: # %entry
; ZBA-NEXT: addi a3, a1, 5
; ZBA-NEXT: sh2add a0, a1, a0
; ZBA-NEXT: sw a2, 20(a0)
; ZBA-NEXT: sw a2, 24(a0)
; ZBA-NEXT: sw a3, 140(a0)
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_inStore:
; XANDESPERF: # %bb.0: # %entry
; XANDESPERF-NEXT: addi a3, a1, 5
; XANDESPERF-NEXT: nds.lea.w a0, a0, a1
; XANDESPERF-NEXT: sw a2, 20(a0)
; XANDESPERF-NEXT: sw a2, 24(a0)
; XANDESPERF-NEXT: sw a3, 140(a0)
; XANDESPERF-NEXT: ret
entry:
%add = add nsw i32 %a, 5
%arrayidx = getelementptr inbounds i32, ptr %array1, i32 %add
store i32 %b, ptr %arrayidx
%0 = getelementptr i32, ptr %array1, i32 %a
%arrayidx3 = getelementptr i8, ptr %0, i32 24
store i32 %b, ptr %arrayidx3
%arrayidx5 = getelementptr i8, ptr %0, i32 140
store i32 %add, ptr %arrayidx5
ret void
}
define void @add_shl_moreOneUse_inStore_addexceedsign12(ptr %array1, i32 %a, i32 %b) {
; NO-ZBA-LABEL: add_shl_moreOneUse_inStore_addexceedsign12:
; NO-ZBA: # %bb.0: # %entry
; NO-ZBA-NEXT: addi a3, a1, 2047
; NO-ZBA-NEXT: lui a4, 2
; NO-ZBA-NEXT: slli a1, a1, 2
; NO-ZBA-NEXT: addi a3, a3, 1
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: add a0, a0, a4
; NO-ZBA-NEXT: sw a2, 0(a0)
; NO-ZBA-NEXT: sw a3, 4(a0)
; NO-ZBA-NEXT: sw a2, 120(a0)
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_inStore_addexceedsign12:
; ZBA: # %bb.0: # %entry
; ZBA-NEXT: addi a3, a1, 2047
; ZBA-NEXT: lui a4, 2
; ZBA-NEXT: sh2add a0, a1, a0
; ZBA-NEXT: addi a3, a3, 1
; ZBA-NEXT: add a0, a0, a4
; ZBA-NEXT: sw a2, 0(a0)
; ZBA-NEXT: sw a3, 4(a0)
; ZBA-NEXT: sw a2, 120(a0)
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_inStore_addexceedsign12:
; XANDESPERF: # %bb.0: # %entry
; XANDESPERF-NEXT: addi a3, a1, 2047
; XANDESPERF-NEXT: lui a4, 2
; XANDESPERF-NEXT: nds.lea.w a0, a0, a1
; XANDESPERF-NEXT: addi a3, a3, 1
; XANDESPERF-NEXT: add a0, a0, a4
; XANDESPERF-NEXT: sw a2, 0(a0)
; XANDESPERF-NEXT: sw a3, 4(a0)
; XANDESPERF-NEXT: sw a2, 120(a0)
; XANDESPERF-NEXT: ret
entry:
%add = add nsw i32 %a, 2048
%arrayidx = getelementptr inbounds i32, ptr %array1, i32 %add
store i32 %b, ptr %arrayidx
%0 = getelementptr i32, ptr %array1, i32 %a
%arrayidx2 = getelementptr i8, ptr %0, i32 8196
store i32 %add, ptr %arrayidx2
%arrayidx4 = getelementptr i8, ptr %0, i32 8312
store i32 %b, ptr %arrayidx4
ret void
}
define void @add_shl_moreOneUse_inSelect(ptr %array1, i32 %a, i32 %b, i32 %x) {
; NO-ZBA-LABEL: add_shl_moreOneUse_inSelect:
; NO-ZBA: # %bb.0: # %entry
; NO-ZBA-NEXT: addi a4, a1, 5
; NO-ZBA-NEXT: mv a5, a4
; NO-ZBA-NEXT: bgtz a3, .LBB3_2
; NO-ZBA-NEXT: # %bb.1: # %entry
; NO-ZBA-NEXT: mv a5, a2
; NO-ZBA-NEXT: .LBB3_2: # %entry
; NO-ZBA-NEXT: slli a1, a1, 2
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: sw a5, 20(a0)
; NO-ZBA-NEXT: sw a5, 24(a0)
; NO-ZBA-NEXT: sw a4, 140(a0)
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_inSelect:
; ZBA: # %bb.0: # %entry
; ZBA-NEXT: addi a4, a1, 5
; ZBA-NEXT: mv a5, a4
; ZBA-NEXT: bgtz a3, .LBB3_2
; ZBA-NEXT: # %bb.1: # %entry
; ZBA-NEXT: mv a5, a2
; ZBA-NEXT: .LBB3_2: # %entry
; ZBA-NEXT: sh2add a0, a1, a0
; ZBA-NEXT: sw a5, 20(a0)
; ZBA-NEXT: sw a5, 24(a0)
; ZBA-NEXT: sw a4, 140(a0)
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_inSelect:
; XANDESPERF: # %bb.0: # %entry
; XANDESPERF-NEXT: addi a4, a1, 5
; XANDESPERF-NEXT: mv a5, a4
; XANDESPERF-NEXT: bgtz a3, .LBB3_2
; XANDESPERF-NEXT: # %bb.1: # %entry
; XANDESPERF-NEXT: mv a5, a2
; XANDESPERF-NEXT: .LBB3_2: # %entry
; XANDESPERF-NEXT: nds.lea.w a0, a0, a1
; XANDESPERF-NEXT: sw a5, 20(a0)
; XANDESPERF-NEXT: sw a5, 24(a0)
; XANDESPERF-NEXT: sw a4, 140(a0)
; XANDESPERF-NEXT: ret
entry:
%add = add nsw i32 %a, 5
%cmp = icmp sgt i32 %x, 0
%cond = select i1 %cmp, i32 %add, i32 %b
%arrayidx = getelementptr inbounds i32, ptr %array1, i32 %add
store i32 %cond, ptr %arrayidx
%0 = getelementptr i32, ptr %array1, i32 %a
%arrayidx2 = getelementptr i32, ptr %0, i32 6
store i32 %cond, ptr %arrayidx2
%arrayidx4 = getelementptr i32, ptr %0, i32 35
store i32 %add, ptr %arrayidx4
ret void
}
define void @add_shl_moreOneUse_inSelect_addexceedsign12(ptr %array1, i32 %a, i32 %b, i32 %x) {
; NO-ZBA-LABEL: add_shl_moreOneUse_inSelect_addexceedsign12:
; NO-ZBA: # %bb.0: # %entry
; NO-ZBA-NEXT: addi a4, a1, 2047
; NO-ZBA-NEXT: addi a4, a4, 1
; NO-ZBA-NEXT: mv a5, a4
; NO-ZBA-NEXT: bgtz a3, .LBB4_2
; NO-ZBA-NEXT: # %bb.1: # %entry
; NO-ZBA-NEXT: mv a5, a2
; NO-ZBA-NEXT: .LBB4_2: # %entry
; NO-ZBA-NEXT: lui a2, 2
; NO-ZBA-NEXT: slli a1, a1, 2
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: add a0, a0, a2
; NO-ZBA-NEXT: sw a5, 0(a0)
; NO-ZBA-NEXT: sw a5, 4(a0)
; NO-ZBA-NEXT: sw a4, 120(a0)
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_inSelect_addexceedsign12:
; ZBA: # %bb.0: # %entry
; ZBA-NEXT: addi a4, a1, 2047
; ZBA-NEXT: addi a4, a4, 1
; ZBA-NEXT: mv a5, a4
; ZBA-NEXT: bgtz a3, .LBB4_2
; ZBA-NEXT: # %bb.1: # %entry
; ZBA-NEXT: mv a5, a2
; ZBA-NEXT: .LBB4_2: # %entry
; ZBA-NEXT: lui a2, 2
; ZBA-NEXT: sh2add a0, a1, a0
; ZBA-NEXT: add a0, a0, a2
; ZBA-NEXT: sw a5, 0(a0)
; ZBA-NEXT: sw a5, 4(a0)
; ZBA-NEXT: sw a4, 120(a0)
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_inSelect_addexceedsign12:
; XANDESPERF: # %bb.0: # %entry
; XANDESPERF-NEXT: addi a4, a1, 2047
; XANDESPERF-NEXT: addi a4, a4, 1
; XANDESPERF-NEXT: mv a5, a4
; XANDESPERF-NEXT: bgtz a3, .LBB4_2
; XANDESPERF-NEXT: # %bb.1: # %entry
; XANDESPERF-NEXT: mv a5, a2
; XANDESPERF-NEXT: .LBB4_2: # %entry
; XANDESPERF-NEXT: lui a2, 2
; XANDESPERF-NEXT: nds.lea.w a0, a0, a1
; XANDESPERF-NEXT: add a0, a0, a2
; XANDESPERF-NEXT: sw a5, 0(a0)
; XANDESPERF-NEXT: sw a5, 4(a0)
; XANDESPERF-NEXT: sw a4, 120(a0)
; XANDESPERF-NEXT: ret
entry:
%add = add nsw i32 %a, 2048
%cmp = icmp sgt i32 %x, 0
%spec.select = select i1 %cmp, i32 %add, i32 %b
%0 = getelementptr inbounds i32, ptr %array1, i32 %add
store i32 %spec.select, ptr %0, align 4
%1 = getelementptr i32, ptr %array1, i32 %a
%arrayidx4 = getelementptr i8, ptr %1, i32 8196
store i32 %spec.select, ptr %arrayidx4
%arrayidx6 = getelementptr i8, ptr %1, i32 8312
store i32 %add, ptr %arrayidx6
ret void
}
define i32 @add_shl_moreOneUse_sh1add(i32 %x) {
; NO-ZBA-LABEL: add_shl_moreOneUse_sh1add:
; NO-ZBA: # %bb.0:
; NO-ZBA-NEXT: ori a1, a0, 1
; NO-ZBA-NEXT: slli a0, a0, 1
; NO-ZBA-NEXT: ori a0, a0, 2
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_sh1add:
; ZBA: # %bb.0:
; ZBA-NEXT: ori a0, a0, 1
; ZBA-NEXT: sh1add a0, a0, a0
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_sh1add:
; XANDESPERF: # %bb.0:
; XANDESPERF-NEXT: ori a0, a0, 1
; XANDESPERF-NEXT: nds.lea.h a0, a0, a0
; XANDESPERF-NEXT: ret
%or = or i32 %x, 1
%mul = shl i32 %or, 1
%add = add i32 %mul, %or
ret i32 %add
}
define i32 @add_shl_moreOneUse_sh2add(i32 %x) {
; NO-ZBA-LABEL: add_shl_moreOneUse_sh2add:
; NO-ZBA: # %bb.0:
; NO-ZBA-NEXT: ori a1, a0, 1
; NO-ZBA-NEXT: slli a0, a0, 2
; NO-ZBA-NEXT: ori a0, a0, 4
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_sh2add:
; ZBA: # %bb.0:
; ZBA-NEXT: ori a0, a0, 1
; ZBA-NEXT: sh2add a0, a0, a0
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_sh2add:
; XANDESPERF: # %bb.0:
; XANDESPERF-NEXT: ori a0, a0, 1
; XANDESPERF-NEXT: nds.lea.w a0, a0, a0
; XANDESPERF-NEXT: ret
%or = or i32 %x, 1
%mul = shl i32 %or, 2
%add = add i32 %mul, %or
ret i32 %add
}
define i32 @add_shl_moreOneUse_sh3add(i32 %x) {
; NO-ZBA-LABEL: add_shl_moreOneUse_sh3add:
; NO-ZBA: # %bb.0:
; NO-ZBA-NEXT: ori a1, a0, 1
; NO-ZBA-NEXT: slli a0, a0, 3
; NO-ZBA-NEXT: ori a0, a0, 8
; NO-ZBA-NEXT: add a0, a0, a1
; NO-ZBA-NEXT: ret
;
; ZBA-LABEL: add_shl_moreOneUse_sh3add:
; ZBA: # %bb.0:
; ZBA-NEXT: ori a0, a0, 1
; ZBA-NEXT: sh3add a0, a0, a0
; ZBA-NEXT: ret
;
; XANDESPERF-LABEL: add_shl_moreOneUse_sh3add:
; XANDESPERF: # %bb.0:
; XANDESPERF-NEXT: ori a0, a0, 1
; XANDESPERF-NEXT: nds.lea.d a0, a0, a0
; XANDESPERF-NEXT: ret
%or = or i32 %x, 1
%mul = shl i32 %or, 3
%add = add i32 %mul, %or
ret i32 %add
}
define i32 @add_shl_moreOneUse_sh4add(i32 %x) {
; RV32-LABEL: add_shl_moreOneUse_sh4add:
; RV32: # %bb.0:
; RV32-NEXT: ori a1, a0, 1
; RV32-NEXT: slli a0, a0, 4
; RV32-NEXT: ori a0, a0, 16
; RV32-NEXT: add a0, a0, a1
; RV32-NEXT: ret
%or = or i32 %x, 1
%mul = shl i32 %or, 4
%add = add i32 %mul, %or
ret i32 %add
}