forked from OSchip/llvm-project
[SelectionDAG][RISCV] Add tests showing missed scalable-splat optimizations
These tests show missed opportunities in the SelectionDAG layer when dealing with scalable-vector splats. All of these are handled for the equivalent `ISD::BUILD_VECTOR` code, and the tests have largely been translated from the equivalent X86 tests. Reviewed By: craig.topper Differential Revision: https://reviews.llvm.org/D106574
This commit is contained in:
Fraser Cormack
parent
c698be47ff
commit
99ed6ce2bd
|
|
@ -0,0 +1,116 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc -mtriple=riscv32 -mattr=+m,+experimental-v < %s | FileCheck %s
|
||||
; RUN: llc -mtriple=riscv64 -mattr=+m,+experimental-v < %s | FileCheck %s
|
||||
|
||||
; fold (and (or x, C), D) -> D if (C & D) == D
|
||||
|
||||
define <vscale x 4 x i32> @and_or_nxv4i32(<vscale x 4 x i32> %A) {
|
||||
; CHECK-LABEL: and_or_nxv4i32:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: addi a0, zero, 255
|
||||
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, mu
|
||||
; CHECK-NEXT: vor.vx v26, v8, a0
|
||||
; CHECK-NEXT: vand.vi v8, v26, 8
|
||||
; CHECK-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 4 x i32> poison, i32 255, i32 0
|
||||
%splat1 = shufflevector <vscale x 4 x i32> %ins1, <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
|
||||
%ins2 = insertelement <vscale x 4 x i32> poison, i32 8, i32 0
|
||||
%splat2 = shufflevector <vscale x 4 x i32> %ins2, <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
|
||||
%v1 = or <vscale x 4 x i32> %A, %splat1
|
||||
%v2 = and <vscale x 4 x i32> %v1, %splat2
|
||||
ret <vscale x 4 x i32> %v2
|
||||
}
|
||||
|
||||
; (or (and X, c1), c2) -> (and (or X, c2), c1|c2) iff (c1 & c2) != 0
|
||||
|
||||
define <vscale x 2 x i64> @or_and_nxv2i64(<vscale x 2 x i64> %a0) {
|
||||
; CHECK-LABEL: or_and_nxv2i64:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, mu
|
||||
; CHECK-NEXT: vand.vi v26, v8, 7
|
||||
; CHECK-NEXT: vor.vi v8, v26, 3
|
||||
; CHECK-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 2 x i64> poison, i64 7, i32 0
|
||||
%splat1 = shufflevector <vscale x 2 x i64> %ins1, <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
|
||||
%ins2 = insertelement <vscale x 2 x i64> poison, i64 3, i32 0
|
||||
%splat2 = shufflevector <vscale x 2 x i64> %ins2, <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
|
||||
%v1 = and <vscale x 2 x i64> %a0, %splat1
|
||||
%v2 = or <vscale x 2 x i64> %v1, %splat2
|
||||
ret <vscale x 2 x i64> %v2
|
||||
}
|
||||
|
||||
; If all masked bits are going to be set, that's a constant fold.
|
||||
|
||||
define <vscale x 2 x i64> @or_and_nxv2i64_fold(<vscale x 2 x i64> %a0) {
|
||||
; CHECK-LABEL: or_and_nxv2i64_fold:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, mu
|
||||
; CHECK-NEXT: vand.vi v26, v8, 1
|
||||
; CHECK-NEXT: vor.vi v8, v26, 3
|
||||
; CHECK-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 2 x i64> poison, i64 1, i32 0
|
||||
%splat1 = shufflevector <vscale x 2 x i64> %ins1, <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
|
||||
%ins2 = insertelement <vscale x 2 x i64> poison, i64 3, i32 0
|
||||
%splat2 = shufflevector <vscale x 2 x i64> %ins2, <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
|
||||
%v1 = and <vscale x 2 x i64> %a0, %splat1
|
||||
%v2 = or <vscale x 2 x i64> %v1, %splat2
|
||||
ret <vscale x 2 x i64> %v2
|
||||
}
|
||||
|
||||
; fold (shl (shl x, c1), c2) -> (shl x, (add c1, c2))
|
||||
|
||||
define <vscale x 4 x i32> @combine_vec_shl_shl(<vscale x 4 x i32> %x) {
|
||||
; CHECK-LABEL: combine_vec_shl_shl:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: addi a0, zero, 2
|
||||
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, mu
|
||||
; CHECK-NEXT: vmv.s.x v26, a0
|
||||
; CHECK-NEXT: addi a0, zero, 4
|
||||
; CHECK-NEXT: vmv.s.x v28, a0
|
||||
; CHECK-NEXT: vsll.vv v26, v8, v26
|
||||
; CHECK-NEXT: vsll.vv v8, v26, v28
|
||||
; CHECK-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 4 x i32> poison, i32 2, i32 0
|
||||
%splat1 = shufflevector <vscale x 4 x i32> %ins1, <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
|
||||
%ins2 = insertelement <vscale x 4 x i32> poison, i32 4, i32 0
|
||||
%splat2 = shufflevector <vscale x 4 x i32> %ins2, <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
|
||||
%v1 = shl <vscale x 4 x i32> %x, %ins1
|
||||
%v2 = shl <vscale x 4 x i32> %v1, %ins2
|
||||
ret <vscale x 4 x i32> %v2
|
||||
}
|
||||
|
||||
; fold (sra (sra x, c1), c2) -> (sra x, (add c1, c2))
|
||||
|
||||
define <vscale x 2 x i32> @combine_vec_ashr_ashr(<vscale x 2 x i32> %x) {
|
||||
; CHECK-LABEL: combine_vec_ashr_ashr:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, mu
|
||||
; CHECK-NEXT: vsra.vi v25, v8, 2
|
||||
; CHECK-NEXT: vsra.vi v8, v25, 4
|
||||
; CHECK-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 2 x i32> poison, i32 2, i32 0
|
||||
%splat1 = shufflevector <vscale x 2 x i32> %ins1, <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
|
||||
%ins2 = insertelement <vscale x 2 x i32> poison, i32 4, i32 0
|
||||
%splat2 = shufflevector <vscale x 2 x i32> %ins2, <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
|
||||
%v1 = ashr <vscale x 2 x i32> %x, %splat1
|
||||
%v2 = ashr <vscale x 2 x i32> %v1, %splat2
|
||||
ret <vscale x 2 x i32> %v2
|
||||
}
|
||||
|
||||
; fold (srl (srl x, c1), c2) -> (srl x, (add c1, c2))
|
||||
|
||||
define <vscale x 8 x i16> @combine_vec_lshr_lshr(<vscale x 8 x i16> %x) {
|
||||
; CHECK-LABEL: combine_vec_lshr_lshr:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, mu
|
||||
; CHECK-NEXT: vsrl.vi v26, v8, 4
|
||||
; CHECK-NEXT: vsrl.vi v8, v26, 4
|
||||
; CHECK-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 8 x i16> poison, i16 2, i32 0
|
||||
%splat1 = shufflevector <vscale x 8 x i16> %ins1, <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
|
||||
%ins2 = insertelement <vscale x 8 x i16> poison, i16 4, i32 0
|
||||
%splat2 = shufflevector <vscale x 8 x i16> %ins2, <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
|
||||
%v1 = lshr <vscale x 8 x i16> %x, %splat2
|
||||
%v2 = lshr <vscale x 8 x i16> %v1, %splat2
|
||||
ret <vscale x 8 x i16> %v2
|
||||
}
|
||||
|
|
@ -0,0 +1,155 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc -mtriple=riscv32 -mattr=+m,+experimental-v < %s | FileCheck %s --check-prefix=RV32
|
||||
; RUN: llc -mtriple=riscv64 -mattr=+m,+experimental-v < %s | FileCheck %s --check-prefix=RV64
|
||||
|
||||
define <vscale x 1 x i16> @test_urem_vec_even_divisor_eq0(<vscale x 1 x i16> %x) nounwind {
|
||||
; RV32-LABEL: test_urem_vec_even_divisor_eq0:
|
||||
; RV32: # %bb.0:
|
||||
; RV32-NEXT: lui a0, 1048571
|
||||
; RV32-NEXT: addi a0, a0, -1365
|
||||
; RV32-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV32-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV32-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV32-NEXT: addi a0, zero, 6
|
||||
; RV32-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV32-NEXT: vmv.v.i v26, 0
|
||||
; RV32-NEXT: vmsne.vi v0, v25, 0
|
||||
; RV32-NEXT: vmerge.vim v8, v26, -1, v0
|
||||
; RV32-NEXT: ret
|
||||
;
|
||||
; RV64-LABEL: test_urem_vec_even_divisor_eq0:
|
||||
; RV64: # %bb.0:
|
||||
; RV64-NEXT: lui a0, 1048571
|
||||
; RV64-NEXT: addiw a0, a0, -1365
|
||||
; RV64-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV64-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV64-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV64-NEXT: addi a0, zero, 6
|
||||
; RV64-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV64-NEXT: vmv.v.i v26, 0
|
||||
; RV64-NEXT: vmsne.vi v0, v25, 0
|
||||
; RV64-NEXT: vmerge.vim v8, v26, -1, v0
|
||||
; RV64-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 1 x i16> poison, i16 6, i32 0
|
||||
%splat1 = shufflevector <vscale x 1 x i16> %ins1, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%urem = urem <vscale x 1 x i16> %x, %splat1
|
||||
%ins2 = insertelement <vscale x 1 x i16> poison, i16 0, i32 0
|
||||
%splat2 = shufflevector <vscale x 1 x i16> %ins2, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%cmp = icmp ne <vscale x 1 x i16> %urem, %splat2
|
||||
%ext = sext <vscale x 1 x i1> %cmp to <vscale x 1 x i16>
|
||||
ret <vscale x 1 x i16> %ext
|
||||
}
|
||||
|
||||
define <vscale x 1 x i16> @test_urem_vec_odd_divisor_eq0(<vscale x 1 x i16> %x) nounwind {
|
||||
; RV32-LABEL: test_urem_vec_odd_divisor_eq0:
|
||||
; RV32: # %bb.0:
|
||||
; RV32-NEXT: lui a0, 1048573
|
||||
; RV32-NEXT: addi a0, a0, -819
|
||||
; RV32-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV32-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV32-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV32-NEXT: addi a0, zero, 5
|
||||
; RV32-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV32-NEXT: vmv.v.i v26, 0
|
||||
; RV32-NEXT: vmsne.vi v0, v25, 0
|
||||
; RV32-NEXT: vmerge.vim v8, v26, -1, v0
|
||||
; RV32-NEXT: ret
|
||||
;
|
||||
; RV64-LABEL: test_urem_vec_odd_divisor_eq0:
|
||||
; RV64: # %bb.0:
|
||||
; RV64-NEXT: lui a0, 1048573
|
||||
; RV64-NEXT: addiw a0, a0, -819
|
||||
; RV64-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV64-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV64-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV64-NEXT: addi a0, zero, 5
|
||||
; RV64-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV64-NEXT: vmv.v.i v26, 0
|
||||
; RV64-NEXT: vmsne.vi v0, v25, 0
|
||||
; RV64-NEXT: vmerge.vim v8, v26, -1, v0
|
||||
; RV64-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 1 x i16> poison, i16 5, i32 0
|
||||
%splat1 = shufflevector <vscale x 1 x i16> %ins1, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%urem = urem <vscale x 1 x i16> %x, %splat1
|
||||
%ins2 = insertelement <vscale x 1 x i16> poison, i16 0, i32 0
|
||||
%splat2 = shufflevector <vscale x 1 x i16> %ins2, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%cmp = icmp ne <vscale x 1 x i16> %urem, %splat2
|
||||
%ext = sext <vscale x 1 x i1> %cmp to <vscale x 1 x i16>
|
||||
ret <vscale x 1 x i16> %ext
|
||||
}
|
||||
|
||||
define <vscale x 1 x i16> @test_urem_vec_even_divisor_eq1(<vscale x 1 x i16> %x) nounwind {
|
||||
; RV32-LABEL: test_urem_vec_even_divisor_eq1:
|
||||
; RV32: # %bb.0:
|
||||
; RV32-NEXT: lui a0, 1048571
|
||||
; RV32-NEXT: addi a0, a0, -1365
|
||||
; RV32-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV32-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV32-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV32-NEXT: addi a0, zero, 6
|
||||
; RV32-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV32-NEXT: vmsne.vi v0, v25, 1
|
||||
; RV32-NEXT: vmv.v.i v25, 0
|
||||
; RV32-NEXT: vmerge.vim v8, v25, -1, v0
|
||||
; RV32-NEXT: ret
|
||||
;
|
||||
; RV64-LABEL: test_urem_vec_even_divisor_eq1:
|
||||
; RV64: # %bb.0:
|
||||
; RV64-NEXT: lui a0, 1048571
|
||||
; RV64-NEXT: addiw a0, a0, -1365
|
||||
; RV64-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV64-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV64-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV64-NEXT: addi a0, zero, 6
|
||||
; RV64-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV64-NEXT: vmsne.vi v0, v25, 1
|
||||
; RV64-NEXT: vmv.v.i v25, 0
|
||||
; RV64-NEXT: vmerge.vim v8, v25, -1, v0
|
||||
; RV64-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 1 x i16> poison, i16 6, i32 0
|
||||
%splat1 = shufflevector <vscale x 1 x i16> %ins1, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%urem = urem <vscale x 1 x i16> %x, %splat1
|
||||
%ins2 = insertelement <vscale x 1 x i16> poison, i16 1, i32 0
|
||||
%splat2 = shufflevector <vscale x 1 x i16> %ins2, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%cmp = icmp ne <vscale x 1 x i16> %urem, %splat2
|
||||
%ext = sext <vscale x 1 x i1> %cmp to <vscale x 1 x i16>
|
||||
ret <vscale x 1 x i16> %ext
|
||||
}
|
||||
|
||||
define <vscale x 1 x i16> @test_urem_vec_odd_divisor_eq1(<vscale x 1 x i16> %x) nounwind {
|
||||
; RV32-LABEL: test_urem_vec_odd_divisor_eq1:
|
||||
; RV32: # %bb.0:
|
||||
; RV32-NEXT: lui a0, 1048573
|
||||
; RV32-NEXT: addi a0, a0, -819
|
||||
; RV32-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV32-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV32-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV32-NEXT: addi a0, zero, 5
|
||||
; RV32-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV32-NEXT: vmsne.vi v0, v25, 1
|
||||
; RV32-NEXT: vmv.v.i v25, 0
|
||||
; RV32-NEXT: vmerge.vim v8, v25, -1, v0
|
||||
; RV32-NEXT: ret
|
||||
;
|
||||
; RV64-LABEL: test_urem_vec_odd_divisor_eq1:
|
||||
; RV64: # %bb.0:
|
||||
; RV64-NEXT: lui a0, 1048573
|
||||
; RV64-NEXT: addiw a0, a0, -819
|
||||
; RV64-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
|
||||
; RV64-NEXT: vmulhu.vx v25, v8, a0
|
||||
; RV64-NEXT: vsrl.vi v25, v25, 2
|
||||
; RV64-NEXT: addi a0, zero, 5
|
||||
; RV64-NEXT: vnmsub.vx v25, a0, v8
|
||||
; RV64-NEXT: vmsne.vi v0, v25, 1
|
||||
; RV64-NEXT: vmv.v.i v25, 0
|
||||
; RV64-NEXT: vmerge.vim v8, v25, -1, v0
|
||||
; RV64-NEXT: ret
|
||||
%ins1 = insertelement <vscale x 1 x i16> poison, i16 5, i32 0
|
||||
%splat1 = shufflevector <vscale x 1 x i16> %ins1, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%urem = urem <vscale x 1 x i16> %x, %splat1
|
||||
%ins2 = insertelement <vscale x 1 x i16> poison, i16 1, i32 0
|
||||
%splat2 = shufflevector <vscale x 1 x i16> %ins2, <vscale x 1 x i16> poison, <vscale x 1 x i32> zeroinitializer
|
||||
%cmp = icmp ne <vscale x 1 x i16> %urem, %splat2
|
||||
%ext = sext <vscale x 1 x i1> %cmp to <vscale x 1 x i16>
|
||||
ret <vscale x 1 x i16> %ext
|
||||
}
|
||||
Loading…
Reference in New Issue