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
95 lines
3.3 KiB
LLVM
95 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
;
|
|
; Test folding of redundant early-exit guard around ctpop:
|
|
; select (icmp ule X, 1), X, ctpop(X) --> ctpop(X)
|
|
;
|
|
; This fold is valid because ctpop(0)==0 and ctpop(1)==1, so the guard
|
|
; is always redundant. The guard only existed to skip slow software emulation.
|
|
|
|
|
|
; RUN: opt < %s -S -passes=instcombine | FileCheck %s
|
|
|
|
|
|
;------------------------------------------------------------------------------
|
|
; Positive tests: select (icmp ule X, 1), X, ctpop(X) --> ctpop(X)
|
|
;------------------------------------------------------------------------------
|
|
|
|
define i64 @fold_ule1_i64(i64 %x) {
|
|
; CHECK-LABEL: @fold_ule1_i64(
|
|
; CHECK-NEXT: [[POP:%.*]] = call range(i64 0, 65) i64 @llvm.ctpop.i64(i64 [[X:%.*]])
|
|
; CHECK-NEXT: ret i64 [[POP]]
|
|
;
|
|
%cmp = icmp ule i64 %x, 1
|
|
%pop = call i64 @llvm.ctpop.i64(i64 %x)
|
|
%res = select i1 %cmp, i64 %x, i64 %pop
|
|
ret i64 %res
|
|
}
|
|
|
|
define i32 @fold_ule1_i32(i32 %x) {
|
|
; CHECK-LABEL: @fold_ule1_i32(
|
|
; CHECK-NEXT: [[POP:%.*]] = call range(i32 0, 33) i32 @llvm.ctpop.i32(i32 [[X:%.*]])
|
|
; CHECK-NEXT: ret i32 [[POP]]
|
|
;
|
|
%cmp = icmp ule i32 %x, 1
|
|
%pop = call i32 @llvm.ctpop.i32(i32 %x)
|
|
%res = select i1 %cmp, i32 %x, i32 %pop
|
|
ret i32 %res
|
|
}
|
|
|
|
define <4 x i32> @fold_vector_ule1(<4 x i32> %x) {
|
|
; CHECK-LABEL: @fold_vector_ule1(
|
|
; CHECK-NEXT: [[POP:%.*]] = call range(i32 0, 33) <4 x i32> @llvm.ctpop.v4i32(<4 x i32> [[X:%.*]])
|
|
; CHECK-NEXT: ret <4 x i32> [[POP]]
|
|
;
|
|
%cmp = icmp ule <4 x i32> %x, splat(i32 1)
|
|
%pop = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %x)
|
|
%res = select <4 x i1> %cmp, <4 x i32> %x, <4 x i32> %pop
|
|
ret <4 x i32> %res
|
|
}
|
|
|
|
;------------------------------------------------------------------------------
|
|
; Negative tests: should NOT fold.
|
|
;------------------------------------------------------------------------------
|
|
|
|
; Wrong predicate (ugt instead of ult/ule)
|
|
define i32 @no_fold_wrong_pred(i32 %x) {
|
|
; CHECK-LABEL: @no_fold_wrong_pred(
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp ugt i32 [[X:%.*]], 1
|
|
; CHECK-NEXT: [[POP:%.*]] = call range(i32 0, 33) i32 @llvm.ctpop.i32(i32 [[X]])
|
|
; CHECK-NEXT: [[RES:%.*]] = select i1 [[CMP]], i32 [[X]], i32 [[POP]]
|
|
; CHECK-NEXT: ret i32 [[RES]]
|
|
;
|
|
%cmp = icmp ugt i32 %x, 1
|
|
%pop = call i32 @llvm.ctpop.i32(i32 %x)
|
|
%res = select i1 %cmp, i32 %x, i32 %pop
|
|
ret i32 %res
|
|
}
|
|
|
|
; Wrong constant (ult 3 instead of ult 2)
|
|
define i32 @no_fold_wrong_const(i32 %x) {
|
|
; CHECK-LABEL: @no_fold_wrong_const(
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[X:%.*]], 3
|
|
; CHECK-NEXT: [[POP:%.*]] = call range(i32 0, 33) i32 @llvm.ctpop.i32(i32 [[X]])
|
|
; CHECK-NEXT: [[RES:%.*]] = select i1 [[CMP]], i32 [[X]], i32 [[POP]]
|
|
; CHECK-NEXT: ret i32 [[RES]]
|
|
;
|
|
%cmp = icmp ult i32 %x, 3
|
|
%pop = call i32 @llvm.ctpop.i32(i32 %x)
|
|
%res = select i1 %cmp, i32 %x, i32 %pop
|
|
ret i32 %res
|
|
}
|
|
|
|
; Mismatched variables (condition uses Y, ctpop uses X)
|
|
define i32 @no_fold_mismatch_var(i32 %x, i32 %y) {
|
|
; CHECK-LABEL: @no_fold_mismatch_var(
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[Y:%.*]], 2
|
|
; CHECK-NEXT: [[POP:%.*]] = call range(i32 0, 33) i32 @llvm.ctpop.i32(i32 [[X:%.*]])
|
|
; CHECK-NEXT: [[RES:%.*]] = select i1 [[CMP]], i32 [[Y]], i32 [[POP]]
|
|
; CHECK-NEXT: ret i32 [[RES]]
|
|
;
|
|
%cmp = icmp ult i32 %y, 2
|
|
%pop = call i32 @llvm.ctpop.i32(i32 %x)
|
|
%res = select i1 %cmp, i32 %y, i32 %pop
|
|
ret i32 %res
|
|
}
|