Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AArch64/fold-csel-cttz-and.ll
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

161 lines
3.9 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 < %s | FileCheck %s
;; Check the transformation
;; CSEL 0, cttz, cc -> AND cttz numbits-1
;; for cttz in the case of i32 and i64 respectively
;; Cases for which the optimzation takes place
define i32 @cttzi32(i32 %x) {
; CHECK-LABEL: cttzi32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit w8, w0
; CHECK-NEXT: clz w8, w8
; CHECK-NEXT: and w0, w8, #0x1f
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
%1 = icmp eq i32 %x, 0
%2 = select i1 %1, i32 0, i32 %0
ret i32 %2
}
define i64 @cttzi64(i64 %x) {
; CHECK-LABEL: cttzi64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit x8, x0
; CHECK-NEXT: clz x8, x8
; CHECK-NEXT: and x0, x8, #0x3f
; CHECK-NEXT: ret
entry:
%0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
%1 = icmp eq i64 %x, 0
%2 = select i1 %1, i64 0, i64 %0
ret i64 %2
}
define i32 @cttzi32ne(i32 %x) {
; CHECK-LABEL: cttzi32ne:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit w8, w0
; CHECK-NEXT: clz w8, w8
; CHECK-NEXT: and w0, w8, #0x1f
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
%1 = icmp ne i32 %x, 0
%2 = select i1 %1, i32 %0, i32 0
ret i32 %2
}
define i64 @cttzi64ne(i64 %x) {
; CHECK-LABEL: cttzi64ne:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit x8, x0
; CHECK-NEXT: clz x8, x8
; CHECK-NEXT: and x0, x8, #0x3f
; CHECK-NEXT: ret
entry:
%0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
%1 = icmp ne i64 %x, 0
%2 = select i1 %1, i64 %0, i64 0
ret i64 %2
}
define i32 @cttztrunc(i64 %x) {
; CHECK-LABEL: cttztrunc:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit x8, x0
; CHECK-NEXT: clz x8, x8
; CHECK-NEXT: and w0, w8, #0x3f
; CHECK-NEXT: ret
entry:
%0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
%1 = icmp eq i64 %x, 0
%2 = select i1 %1, i64 0, i64 %0
%3 = trunc i64 %2 to i32
ret i32 %3
}
;; Cases for which the optimization does not take place
define i32 @cttzne(i32 %x) {
; CHECK-LABEL: cttzne:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit w8, w0
; CHECK-NEXT: cmp w0, #0
; CHECK-NEXT: clz w8, w8
; CHECK-NEXT: csel w0, wzr, w8, ne
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
%1 = icmp ne i32 %x, 0
%2 = select i1 %1, i32 0, i32 %0
ret i32 %2
}
define i32 @cttzxnot0(i32 %x) {
; CHECK-LABEL: cttzxnot0:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit w8, w0
; CHECK-NEXT: cmp w0, #10
; CHECK-NEXT: clz w8, w8
; CHECK-NEXT: csel w0, wzr, w8, eq
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
%1 = icmp eq i32 %x, 10
%2 = select i1 %1, i32 0, i32 %0
ret i32 %2
}
define i32 @cttzlhsnot0(i32 %x) {
; CHECK-LABEL: cttzlhsnot0:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit w9, w0
; CHECK-NEXT: mov w8, #10 // =0xa
; CHECK-NEXT: cmp w0, #0
; CHECK-NEXT: clz w9, w9
; CHECK-NEXT: csel w0, w8, w9, eq
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
%1 = icmp eq i32 %x, 0
%2 = select i1 %1, i32 10, i32 %0
ret i32 %2
}
define i32 @notcttz(i32 %x) {
; CHECK-LABEL: notcttz:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: clz w8, w0
; CHECK-NEXT: cmp w0, #0
; CHECK-NEXT: csel w0, wzr, w8, eq
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.ctlz.i32(i32 %x, i1 true)
%1 = icmp eq i32 %x, 0
%2 = select i1 %1, i32 0, i32 %0
ret i32 %2
}
define i32 @cttzlhsnotx(i32 %x, i32 %y) {
; CHECK-LABEL: cttzlhsnotx:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: rbit w8, w0
; CHECK-NEXT: cmp w1, #0
; CHECK-NEXT: clz w8, w8
; CHECK-NEXT: csel w0, wzr, w8, eq
; CHECK-NEXT: ret
entry:
%0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
%1 = icmp eq i32 %y, 0
%2 = select i1 %1, i32 0, i32 %0
ret i32 %2
}
declare i32 @llvm.cttz.i32(i32, i1)
declare i64 @llvm.cttz.i64(i64, i1)
declare i32 @llvm.ctlz.i32(i32, i1)