140 lines
5.8 KiB
LLVM
140 lines
5.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
|
|
; llvm.experimental.vector.extract canonicalizes to shufflevector in the fixed case. In the
|
|
; scalable case, we lower to the EXTRACT_SUBVECTOR ISD node.
|
|
|
|
declare <10 x i32> @llvm.experimental.vector.extract.v10i32.v8i32(<8 x i32> %vec, i64 %idx)
|
|
declare <2 x i32> @llvm.experimental.vector.extract.v2i32.v4i32(<8 x i32> %vec, i64 %idx)
|
|
declare <3 x i32> @llvm.experimental.vector.extract.v3i32.v8i32(<8 x i32> %vec, i64 %idx)
|
|
declare <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> %vec, i64 %idx)
|
|
declare <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32> %vec, i64 %idx)
|
|
declare <8 x i32> @llvm.experimental.vector.extract.v8i32.v8i32(<8 x i32> %vec, i64 %idx)
|
|
|
|
; ============================================================================ ;
|
|
; Trivial cases
|
|
; ============================================================================ ;
|
|
|
|
; Extracting the entirety of a vector is a nop.
|
|
define <8 x i32> @trivial_nop(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @trivial_nop(
|
|
; CHECK-NEXT: ret <8 x i32> [[VEC:%.*]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.experimental.vector.extract.v8i32.v8i32(<8 x i32> %vec, i64 0)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
; ============================================================================ ;
|
|
; Valid canonicalizations
|
|
; ============================================================================ ;
|
|
|
|
define <2 x i32> @valid_extraction_a(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_a(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: ret <2 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <2 x i32> @llvm.experimental.vector.extract.v2i32.v4i32(<8 x i32> %vec, i64 0)
|
|
ret <2 x i32> %1
|
|
}
|
|
|
|
define <2 x i32> @valid_extraction_b(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_b(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>
|
|
; CHECK-NEXT: ret <2 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <2 x i32> @llvm.experimental.vector.extract.v2i32.v4i32(<8 x i32> %vec, i64 2)
|
|
ret <2 x i32> %1
|
|
}
|
|
|
|
define <2 x i32> @valid_extraction_c(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_c(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <2 x i32> <i32 4, i32 5>
|
|
; CHECK-NEXT: ret <2 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <2 x i32> @llvm.experimental.vector.extract.v2i32.v4i32(<8 x i32> %vec, i64 4)
|
|
ret <2 x i32> %1
|
|
}
|
|
|
|
define <2 x i32> @valid_extraction_d(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_d(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
|
|
; CHECK-NEXT: ret <2 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <2 x i32> @llvm.experimental.vector.extract.v2i32.v4i32(<8 x i32> %vec, i64 6)
|
|
ret <2 x i32> %1
|
|
}
|
|
|
|
define <4 x i32> @valid_extraction_e(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_e(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32> %vec, i64 0)
|
|
ret <4 x i32> %1
|
|
}
|
|
|
|
define <4 x i32> @valid_extraction_f(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_f(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32> %vec, i64 4)
|
|
ret <4 x i32> %1
|
|
}
|
|
|
|
define <3 x i32> @valid_extraction_g(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_g(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <3 x i32> <i32 0, i32 1, i32 2>
|
|
; CHECK-NEXT: ret <3 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <3 x i32> @llvm.experimental.vector.extract.v3i32.v8i32(<8 x i32> %vec, i64 0)
|
|
ret <3 x i32> %1
|
|
}
|
|
|
|
define <3 x i32> @valid_extraction_h(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @valid_extraction_h(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> undef, <3 x i32> <i32 3, i32 4, i32 5>
|
|
; CHECK-NEXT: ret <3 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <3 x i32> @llvm.experimental.vector.extract.v3i32.v8i32(<8 x i32> %vec, i64 3)
|
|
ret <3 x i32> %1
|
|
}
|
|
|
|
; ============================================================================ ;
|
|
; Invalid canonicalizations
|
|
; ============================================================================ ;
|
|
|
|
; Idx must be the be a constant multiple of the destination vector's length,
|
|
; otherwise the result is undefined.
|
|
define <4 x i32> @idx_not_constant_multiple(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @idx_not_constant_multiple(
|
|
; CHECK-NEXT: ret <4 x i32> undef
|
|
;
|
|
%1 = call <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32> %vec, i64 1)
|
|
ret <4 x i32> %1
|
|
}
|
|
|
|
; If the extraction overruns the vector, the result is undefined.
|
|
define <10 x i32> @extract_overrun(<8 x i32> %vec) {
|
|
; CHECK-LABEL: @extract_overrun(
|
|
; CHECK-NEXT: ret <10 x i32> undef
|
|
;
|
|
%1 = call <10 x i32> @llvm.experimental.vector.extract.v10i32.v8i32(<8 x i32> %vec, i64 0)
|
|
ret <10 x i32> %1
|
|
}
|
|
|
|
; ============================================================================ ;
|
|
; Scalable cases
|
|
; ============================================================================ ;
|
|
|
|
; Scalable extractions should not be canonicalized. This will be lowered to the
|
|
; EXTRACT_SUBVECTOR ISD node later.
|
|
define <4 x i32> @scalable_extract(<vscale x 4 x i32> %vec) {
|
|
; CHECK-LABEL: @scalable_extract(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> [[VEC:%.*]], i64 0)
|
|
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> %vec, i64 0)
|
|
ret <4 x i32> %1
|
|
}
|