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
118 lines
4.6 KiB
LLVM
118 lines
4.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
|
|
; If we have some pattern that leaves only some low bits set, and then performs
|
|
; left-shift of those bits, we can combine those two shifts into a shift+mask.
|
|
|
|
; There are many variants to this pattern:
|
|
; e) ((x << maskNbits) l>> maskNbits) << shiftNbits
|
|
; simplify to:
|
|
; (x << shiftNbits) & (-1 >> ((-(maskNbits+shiftNbits))+32))
|
|
|
|
; Simple tests.
|
|
|
|
declare void @use32(i32)
|
|
|
|
define i32 @t0_basic(i32 %x, i32 %nbits) {
|
|
; CHECK-LABEL: @t0_basic(
|
|
; CHECK-NEXT: [[T0:%.*]] = shl i32 [[X:%.*]], [[NBITS:%.*]]
|
|
; CHECK-NEXT: [[T2:%.*]] = add i32 [[NBITS]], -1
|
|
; CHECK-NEXT: call void @use32(i32 [[T0]])
|
|
; CHECK-NEXT: call void @use32(i32 [[T2]])
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shl i32 [[X]], [[T2]]
|
|
; CHECK-NEXT: [[T3:%.*]] = and i32 [[TMP1]], 2147483647
|
|
; CHECK-NEXT: ret i32 [[T3]]
|
|
;
|
|
%t0 = shl i32 %x, %nbits
|
|
%t1 = lshr i32 %t0, %nbits
|
|
%t2 = add i32 %nbits, -1
|
|
call void @use32(i32 %t0)
|
|
call void @use32(i32 %t2)
|
|
%t3 = shl i32 %t1, %t2 ; shift is smaller than mask
|
|
ret i32 %t3
|
|
}
|
|
|
|
; Vectors
|
|
|
|
declare void @use8xi32(<8 x i32>)
|
|
|
|
define <8 x i32> @t1_vec_splat(<8 x i32> %x, <8 x i32> %nbits) {
|
|
; CHECK-LABEL: @t1_vec_splat(
|
|
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> [[X:%.*]], [[NBITS:%.*]]
|
|
; CHECK-NEXT: [[T2:%.*]] = add <8 x i32> [[NBITS]], splat (i32 -1)
|
|
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
|
|
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X]], [[T2]]
|
|
; CHECK-NEXT: [[T3:%.*]] = and <8 x i32> [[TMP1]], splat (i32 2147483647)
|
|
; CHECK-NEXT: ret <8 x i32> [[T3]]
|
|
;
|
|
%t0 = shl <8 x i32> %x, %nbits
|
|
%t1 = lshr <8 x i32> %t0, %nbits
|
|
%t2 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
|
|
call void @use8xi32(<8 x i32> %t0)
|
|
call void @use8xi32(<8 x i32> %t2)
|
|
%t3 = shl <8 x i32> %t1, %t2 ; shift is smaller than mask
|
|
ret <8 x i32> %t3
|
|
}
|
|
|
|
define <8 x i32> @t1_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
|
|
; CHECK-LABEL: @t1_vec_splat_undef(
|
|
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> [[X:%.*]], [[NBITS:%.*]]
|
|
; CHECK-NEXT: [[T2:%.*]] = add <8 x i32> [[NBITS]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
|
|
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
|
|
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X]], [[T2]]
|
|
; CHECK-NEXT: [[T3:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 poison, i32 2147483647>
|
|
; CHECK-NEXT: ret <8 x i32> [[T3]]
|
|
;
|
|
%t0 = shl <8 x i32> %x, %nbits
|
|
%t1 = lshr <8 x i32> %t0, %nbits
|
|
%t2 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
|
|
call void @use8xi32(<8 x i32> %t0)
|
|
call void @use8xi32(<8 x i32> %t2)
|
|
%t3 = shl <8 x i32> %t1, %t2 ; shift is smaller than mask
|
|
ret <8 x i32> %t3
|
|
}
|
|
|
|
define <8 x i32> @t1_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
|
|
; CHECK-LABEL: @t1_vec_nonsplat(
|
|
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> [[X:%.*]], [[NBITS:%.*]]
|
|
; CHECK-NEXT: [[T2:%.*]] = add <8 x i32> [[NBITS]], <i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32, i32 33>
|
|
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
|
|
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X]], [[T2]]
|
|
; CHECK-NEXT: [[T3:%.*]] = and <8 x i32> [[TMP1]], <i32 poison, i32 1, i32 2147483647, i32 -1, i32 -1, i32 -1, i32 -1, i32 poison>
|
|
; CHECK-NEXT: ret <8 x i32> [[T3]]
|
|
;
|
|
%t0 = shl <8 x i32> %x, %nbits
|
|
%t1 = lshr <8 x i32> %t0, %nbits
|
|
%t2 = add <8 x i32> %nbits, <i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32, i32 33>
|
|
call void @use8xi32(<8 x i32> %t0)
|
|
call void @use8xi32(<8 x i32> %t2)
|
|
%t3 = shl <8 x i32> %t1, %t2 ; shift is smaller than mask
|
|
ret <8 x i32> %t3
|
|
}
|
|
|
|
; Extra uses.
|
|
|
|
define i32 @n3_extrause(i32 %x, i32 %nbits) {
|
|
; CHECK-LABEL: @n3_extrause(
|
|
; CHECK-NEXT: [[T0:%.*]] = shl i32 [[X:%.*]], [[NBITS:%.*]]
|
|
; CHECK-NEXT: [[T1:%.*]] = lshr exact i32 [[T0]], [[NBITS]]
|
|
; CHECK-NEXT: [[T2:%.*]] = add i32 [[NBITS]], -1
|
|
; CHECK-NEXT: call void @use32(i32 [[T0]])
|
|
; CHECK-NEXT: call void @use32(i32 [[T1]])
|
|
; CHECK-NEXT: call void @use32(i32 [[T2]])
|
|
; CHECK-NEXT: [[T3:%.*]] = shl i32 [[T1]], [[T2]]
|
|
; CHECK-NEXT: ret i32 [[T3]]
|
|
;
|
|
%t0 = shl i32 %x, %nbits
|
|
%t1 = lshr i32 %t0, %nbits
|
|
%t2 = add i32 %nbits, -1
|
|
call void @use32(i32 %t0)
|
|
call void @use32(i32 %t1) ; BAD
|
|
call void @use32(i32 %t2)
|
|
%t3 = shl i32 %t1, %t2 ; shift is smaller than mask
|
|
ret i32 %t3
|
|
}
|