caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ec056f54589d937ae3f74d795b94de886cbb7ec7
clang-p2996/llvm/test/CodeGen/RISCV/rvv/vpscatter-sdnode.ll
Philip Reames 859c871184 [RISCV] Default to MicroOpBufferSize = 1 for scheduling purposes (#126608) 
This change introduces a default schedule model for the RISCV target
which leaves everything unchanged except the MicroOpBufferSize. The
default value of this flag in NoSched is 0. Both configurations
represent in order cores (i.e. no reorder window), the difference
between them comes down to whether heuristics other than latency are
allowed to apply. (Implementation details below)

I left the processor models which explicitly set MicroOpBufferSize=0
unchanged in this patch, but strongly suspect we should change those
too. Honestly, I think the LLVM wide default for this flag should be
changed, but don't have the energy to manage the updates for all
targets.

Implementation wise, the effect of this change is that schedule units
which are ready to run *except that* one of their predecessors may not
have completed yet are added to the Available list, not the Pending one.
The result of this is that it becomes possible to chose to schedule a
node before it's ready cycle if the heuristics prefer. This is
essentially chosing to insert a resource stall instead of e.g.
increasing register pressure.

Note that I was initially concerned there might be a correctness aspect
(as in some kind of exposed pipeline design), but the generic scheduler
doesn't seem to know how to insert noop instructions. Without that, a
program wouldn't be guaranteed to schedule on an exposed pipeline
depending on the program and schedule model in question.

The effect of this is that we sometimes prefer register pressure in
codegen results. This is mostly churn (or small wins) on scalar because
we have many more registers, but is of major importance on vector -
particularly high LMUL - because we effectively have many fewer
registers and the relative cost of spilling is much higher. This is a
significant improvement on high LMUL code quality for default rva23u
configurations - or any non -mcpu vector configuration for that matter.

Fixes #107532
2025-02-12 12:31:39 -08:00

2544 lines
106 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfh,+zvfbfmin,+v,+m \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV32
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfh,+zvfbfmin,+v,+m \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV64
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfhmin,+zvfbfmin,+v,+m \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV32
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfhmin,+zvfbfmin,+v,+m \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV64
declare void @llvm.vp.scatter.nxv1i8.nxv1p0(<vscale x 1 x i8>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1i8(<vscale x 1 x i8> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1i8.nxv1p0(<vscale x 1 x i8> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2i8(<vscale x 2 x i8> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_nxv2i16_truncstore_nxv2i8(<vscale x 2 x i16> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i16_truncstore_nxv2i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf4, ta, ma
; RV32-NEXT: vnsrl.wi v8, v8, 0
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i16_truncstore_nxv2i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf4, ta, ma
; RV64-NEXT: vnsrl.wi v8, v8, 0
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
%tval = trunc <vscale x 2 x i16> %val to <vscale x 2 x i8>
call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> %tval, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_nxv2i32_truncstore_nxv2i8(<vscale x 2 x i32> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i32_truncstore_nxv2i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV32-NEXT: vnsrl.wi v8, v8, 0
; RV32-NEXT: vsetvli zero, zero, e8, mf4, ta, ma
; RV32-NEXT: vnsrl.wi v8, v8, 0
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i32_truncstore_nxv2i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV64-NEXT: vnsrl.wi v8, v8, 0
; RV64-NEXT: vsetvli zero, zero, e8, mf4, ta, ma
; RV64-NEXT: vnsrl.wi v8, v8, 0
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
%tval = trunc <vscale x 2 x i32> %val to <vscale x 2 x i8>
call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> %tval, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_nxv2i64_truncstore_nxv2i8(<vscale x 2 x i64> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i64_truncstore_nxv2i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV32-NEXT: vnsrl.wi v11, v8, 0
; RV32-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; RV32-NEXT: vnsrl.wi v8, v11, 0
; RV32-NEXT: vsetvli zero, zero, e8, mf4, ta, ma
; RV32-NEXT: vnsrl.wi v8, v8, 0
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i64_truncstore_nxv2i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV64-NEXT: vnsrl.wi v12, v8, 0
; RV64-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; RV64-NEXT: vnsrl.wi v8, v12, 0
; RV64-NEXT: vsetvli zero, zero, e8, mf4, ta, ma
; RV64-NEXT: vnsrl.wi v8, v8, 0
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
%tval = trunc <vscale x 2 x i64> %val to <vscale x 2 x i8>
call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> %tval, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4i8.nxv4p0(<vscale x 4 x i8>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4i8(<vscale x 4 x i8> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i8.nxv4p0(<vscale x 4 x i8> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4i8(<vscale x 4 x i8> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i8.nxv4p0(<vscale x 4 x i8> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8i8(<vscale x 8 x i8> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8(<vscale x 8 x i8> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v9
; RV32-NEXT: vsetvli zero, zero, e8, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v9
; RV64-NEXT: vsetvli zero, zero, e8, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i8, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1i16.nxv1p0(<vscale x 1 x i16>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1i16(<vscale x 1 x i16> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1i16.nxv1p0(<vscale x 1 x i16> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2i16.nxv2p0(<vscale x 2 x i16>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2i16(<vscale x 2 x i16> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2i16.nxv2p0(<vscale x 2 x i16> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_nxv2i32_truncstore_nxv2i16(<vscale x 2 x i32> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i32_truncstore_nxv2i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV32-NEXT: vnsrl.wi v8, v8, 0
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i32_truncstore_nxv2i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV64-NEXT: vnsrl.wi v8, v8, 0
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
%tval = trunc <vscale x 2 x i32> %val to <vscale x 2 x i16>
call void @llvm.vp.scatter.nxv2i16.nxv2p0(<vscale x 2 x i16> %tval, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_nxv2i64_truncstore_nxv2i16(<vscale x 2 x i64> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i64_truncstore_nxv2i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV32-NEXT: vnsrl.wi v11, v8, 0
; RV32-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; RV32-NEXT: vnsrl.wi v8, v11, 0
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i64_truncstore_nxv2i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV64-NEXT: vnsrl.wi v12, v8, 0
; RV64-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; RV64-NEXT: vnsrl.wi v8, v12, 0
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
%tval = trunc <vscale x 2 x i64> %val to <vscale x 2 x i16>
call void @llvm.vp.scatter.nxv2i16.nxv2p0(<vscale x 2 x i16> %tval, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4i16.nxv4p0(<vscale x 4 x i16>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4i16(<vscale x 4 x i16> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i16.nxv4p0(<vscale x 4 x i16> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4i16(<vscale x 4 x i16> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i16.nxv4p0(<vscale x 4 x i16> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8i16(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v10
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v10
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i16>
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i16> %eidxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwaddu.vv v12, v10, v10
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwaddu.vv v12, v10, v10
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i16>
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i16> %eidxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwadd.vv v12, v10, v10
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare <vscale x 8 x i32> @llvm.vp.sext.nxv8i16.nxv8i32(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
define void @vpscatter_baseidx_vpsext_nxv8i16_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_vpsext_nxv8i16_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwadd.vv v12, v10, v10, v0.t
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_vpsext_nxv8i16_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vsext.vf2 v12, v10, v0.t
; RV64-NEXT: vwadd.vv v16, v12, v12
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i16.nxv8i32(<vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 %evl)
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare <vscale x 8 x i32> @llvm.vp.zext.nxv8i16.nxv8i32(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
define void @vpscatter_baseidx_vpzext_nxv8i16_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_vpzext_nxv8i16_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwaddu.vv v12, v10, v10, v0.t
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_vpzext_nxv8i16_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vzext.vf2 v12, v10, v0.t
; RV64-NEXT: vwadd.vv v16, v12, v12
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = call <vscale x 8 x i32> @llvm.vp.zext.nxv8i16.nxv8i32(<vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 %evl)
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare <vscale x 8 x i64> @llvm.vp.sext.nxv8i32.nxv8i64(<vscale x 8 x i32>, <vscale x 8 x i1>, i32)
define void @vpscatter_baseidx_vpsext_nxv8i32_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_vpsext_nxv8i32_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV32-NEXT: vsext.vf2 v16, v12, v0.t
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vnsrl.wi v12, v16, 0
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_vpsext_nxv8i32_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwadd.vv v16, v12, v12, v0.t
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = call <vscale x 8 x i64> @llvm.vp.sext.nxv8i32.nxv8i64(<vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 %evl)
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare <vscale x 8 x i64> @llvm.vp.zext.nxv8i32.nxv8i64(<vscale x 8 x i32>, <vscale x 8 x i1>, i32)
define void @vpscatter_baseidx_vpzext_nxv8i32_nxv8i16(<vscale x 8 x i16> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_vpzext_nxv8i32_nxv8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV32-NEXT: vzext.vf2 v16, v12, v0.t
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vnsrl.wi v12, v16, 0
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_vpzext_nxv8i32_nxv8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwaddu.vv v16, v12, v12, v0.t
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = call <vscale x 8 x i64> @llvm.vp.zext.nxv8i32.nxv8i64(<vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 %evl)
%ptrs = getelementptr inbounds i16, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1i32.nxv1p0(<vscale x 1 x i32>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1i32(<vscale x 1 x i32> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1i32.nxv1p0(<vscale x 1 x i32> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2i32(<vscale x 2 x i32> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_nxv2i64_truncstore_nxv2i32(<vscale x 2 x i64> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i64_truncstore_nxv2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV32-NEXT: vnsrl.wi v11, v8, 0
; RV32-NEXT: vsoxei32.v v11, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i64_truncstore_nxv2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV64-NEXT: vnsrl.wi v12, v8, 0
; RV64-NEXT: vsoxei64.v v12, (zero), v10, v0.t
; RV64-NEXT: ret
%tval = trunc <vscale x 2 x i64> %val to <vscale x 2 x i32>
call void @llvm.vp.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> %tval, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4i32(<vscale x 4 x i32> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4i32(<vscale x 4 x i32> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8i32(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v16, v12
; RV32-NEXT: vsll.vi v12, v16, 2
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v16, v12
; RV32-NEXT: vsll.vi v12, v16, 2
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwmulu.vx v14, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v14, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 4
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwmulu.vx v14, v12, a2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v14, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i16_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i16_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v16, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i16_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i16_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v16, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i16> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i16_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulu.vx v16, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 4
; RV64-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV64-NEXT: vwmulu.vx v16, v12, a2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i16> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i32(<vscale x 8 x i32> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v12, v12, 2
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i32:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 4
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v16, v12, a2
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i32, ptr %base, <vscale x 8 x i32> %idxs
call void @llvm.vp.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1i64(<vscale x 1 x i64> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2i64(<vscale x 2 x i64> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4i64.nxv4p0(<vscale x 4 x i64>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4i64(<vscale x 4 x i64> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i64.nxv4p0(<vscale x 4 x i64> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4i64(<vscale x 4 x i64> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4i64.nxv4p0(<vscale x 4 x i64> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8i64(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v20, v16
; RV32-NEXT: vsll.vi v16, v20, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v20, v16
; RV32-NEXT: vsll.vi v16, v20, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwmulu.vx v18, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v18, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwmulu.vx v18, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v18, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i16_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i16_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i16_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i16_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i16> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i16_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV64-NEXT: vwmulu.vx v20, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i16> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i32_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i32_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i32_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i32> %idxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i32_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i32_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i32_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i32> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i32_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i32_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i32_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i32> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i64(<vscale x 8 x i64> %val, ptr %base, <vscale x 8 x i64> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vnsrl.wi v24, v16, 0
; RV32-NEXT: vsll.vi v16, v24, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, ptr %base, <vscale x 8 x i64> %idxs
call void @llvm.vp.scatter.nxv8i64.nxv8p0(<vscale x 8 x i64> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1bf16.nxv1p0(<vscale x 1 x bfloat>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1bf16(<vscale x 1 x bfloat> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1bf16.nxv1p0(<vscale x 1 x bfloat> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2bf16.nxv2p0(<vscale x 2 x bfloat>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2bf16(<vscale x 2 x bfloat> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2bf16.nxv2p0(<vscale x 2 x bfloat> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4bf16.nxv4p0(<vscale x 4 x bfloat>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4bf16(<vscale x 4 x bfloat> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4bf16.nxv4p0(<vscale x 4 x bfloat> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4bf16(<vscale x 4 x bfloat> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4bf16.nxv4p0(<vscale x 4 x bfloat> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8bf16.nxv8p0(<vscale x 8 x bfloat>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8bf16(<vscale x 8 x bfloat> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8bf16.nxv8p0(<vscale x 8 x bfloat> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8bf16(<vscale x 8 x bfloat> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v10
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds bfloat, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8bf16.nxv8p0(<vscale x 8 x bfloat> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8bf16(<vscale x 8 x bfloat> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v10
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i16>
%ptrs = getelementptr inbounds bfloat, ptr %base, <vscale x 8 x i16> %eidxs
call void @llvm.vp.scatter.nxv8bf16.nxv8p0(<vscale x 8 x bfloat> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8bf16(<vscale x 8 x bfloat> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwaddu.vv v12, v10, v10
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwaddu.vv v12, v10, v10
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i16>
%ptrs = getelementptr inbounds bfloat, ptr %base, <vscale x 8 x i16> %eidxs
call void @llvm.vp.scatter.nxv8bf16.nxv8p0(<vscale x 8 x bfloat> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8bf16(<vscale x 8 x bfloat> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8bf16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwadd.vv v12, v10, v10
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8bf16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds bfloat, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8bf16.nxv8p0(<vscale x 8 x bfloat> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1f16.nxv1p0(<vscale x 1 x half>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1f16(<vscale x 1 x half> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1f16.nxv1p0(<vscale x 1 x half> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2f16.nxv2p0(<vscale x 2 x half>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2f16(<vscale x 2 x half> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2f16.nxv2p0(<vscale x 2 x half> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4f16.nxv4p0(<vscale x 4 x half>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4f16(<vscale x 4 x half> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4f16.nxv4p0(<vscale x 4 x half> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4f16(<vscale x 4 x half> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4f16.nxv4p0(<vscale x 4 x half> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8f16.nxv8p0(<vscale x 8 x half>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8f16(<vscale x 8 x half> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8f16.nxv8p0(<vscale x 8 x half> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8f16(<vscale x 8 x half> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v10
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds half, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8f16.nxv8p0(<vscale x 8 x half> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8f16(<vscale x 8 x half> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v12, v10
; RV32-NEXT: vadd.vv v12, v12, v12
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i16>
%ptrs = getelementptr inbounds half, ptr %base, <vscale x 8 x i16> %eidxs
call void @llvm.vp.scatter.nxv8f16.nxv8p0(<vscale x 8 x half> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8f16(<vscale x 8 x half> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwaddu.vv v12, v10, v10
; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwaddu.vv v12, v10, v10
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i16>
%ptrs = getelementptr inbounds half, ptr %base, <vscale x 8 x i16> %eidxs
call void @llvm.vp.scatter.nxv8f16.nxv8p0(<vscale x 8 x half> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8f16(<vscale x 8 x half> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwadd.vv v12, v10, v10
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v10
; RV64-NEXT: vadd.vv v16, v16, v16
; RV64-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds half, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8f16.nxv8p0(<vscale x 8 x half> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1f32.nxv1p0(<vscale x 1 x float>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1f32(<vscale x 1 x float> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1f32.nxv1p0(<vscale x 1 x float> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2f32.nxv2p0(<vscale x 2 x float>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2f32(<vscale x 2 x float> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2f32.nxv2p0(<vscale x 2 x float> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4f32.nxv4p0(<vscale x 4 x float>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4f32(<vscale x 4 x float> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4f32(<vscale x 4 x float> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8f32(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v16, v12
; RV32-NEXT: vsll.vi v12, v16, 2
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v16, v12
; RV32-NEXT: vsll.vi v12, v16, 2
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwmulu.vx v14, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v14, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 4
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwmulu.vx v14, v12, a2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v14, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i16_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i16_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v16, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i16_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i16_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v16, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i16> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i16_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 4
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulu.vx v16, v12, a2
; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 4
; RV64-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV64-NEXT: vwmulu.vx v16, v12, a2
; RV64-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; RV64-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i16> %idxs to <vscale x 8 x i32>
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i32> %eidxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8f32(<vscale x 8 x float> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v12, v12, 2
; RV32-NEXT: vsoxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8f32:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 4
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v16, v12, a2
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds float, ptr %base, <vscale x 8 x i32> %idxs
call void @llvm.vp.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv1f64.nxv1p0(<vscale x 1 x double>, <vscale x 1 x ptr>, <vscale x 1 x i1>, i32)
define void @vpscatter_nxv1f64(<vscale x 1 x double> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv1f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v9, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv1f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v9, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv1f64.nxv1p0(<vscale x 1 x double> %val, <vscale x 1 x ptr> %ptrs, <vscale x 1 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv2f64.nxv2p0(<vscale x 2 x double>, <vscale x 2 x ptr>, <vscale x 2 x i1>, i32)
define void @vpscatter_nxv2f64(<vscale x 2 x double> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv2f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv2f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m2, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v10, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv2f64.nxv2p0(<vscale x 2 x double> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv4f64.nxv4p0(<vscale x 4 x double>, <vscale x 4 x ptr>, <vscale x 4 x i1>, i32)
define void @vpscatter_nxv4f64(<vscale x 4 x double> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv4f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv4f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4f64.nxv4p0(<vscale x 4 x double> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_truemask_nxv4f64(<vscale x 4 x double> %val, <vscale x 4 x ptr> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_truemask_nxv4f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v12
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_truemask_nxv4f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m4, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v12
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv4f64.nxv4p0(<vscale x 4 x double> %val, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> splat (i1 1), i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double>, <vscale x 6 x ptr>, <vscale x 6 x i1>, i32)
define void @vpscatter_nxv6f64(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv6i8_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i8> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv6i8_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v20, v16
; RV32-NEXT: vsll.vi v16, v20, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv6i8_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i8> %idxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv6i8_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i8> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv6i8_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v20, v16
; RV32-NEXT: vsll.vi v16, v20, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv6i8_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 6 x i8> %idxs to <vscale x 6 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %eidxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv6i8_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i8> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv6i8_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwmulu.vx v18, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v18, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv6i8_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwmulu.vx v18, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v18, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 6 x i8> %idxs to <vscale x 6 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %eidxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv6i16_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i16> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv6i16_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv6i16_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i16> %idxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv6i16_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i16> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv6i16_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv6i16_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 6 x i16> %idxs to <vscale x 6 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %eidxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv6i16_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i16> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv6i16_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv6i16_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV64-NEXT: vwmulu.vx v20, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 6 x i16> %idxs to <vscale x 6 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %eidxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv6i32_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i32> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv6i32_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv6i32_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i32> %idxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv6i32_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i32> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv6i32_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv6i32_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 6 x i32> %idxs to <vscale x 6 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %eidxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv6i32_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i32> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv6i32_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv6i32_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 6 x i32> %idxs to <vscale x 6 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %eidxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv6f64(<vscale x 6 x double> %val, ptr %base, <vscale x 6 x i64> %idxs, <vscale x 6 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv6f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vnsrl.wi v24, v16, 0
; RV32-NEXT: vsll.vi v16, v24, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv6f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 6 x i64> %idxs
call void @llvm.vp.scatter.nxv6f64.nxv6p0(<vscale x 6 x double> %val, <vscale x 6 x ptr> %ptrs, <vscale x 6 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double>, <vscale x 8 x ptr>, <vscale x 8 x i1>, i32)
define void @vpscatter_nxv8f64(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i8_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i8_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v20, v16
; RV32-NEXT: vsll.vi v16, v20, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i8_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i8> %idxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i8_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsext.vf4 v20, v16
; RV32-NEXT: vsll.vi v16, v20, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i8_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf8 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i8> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i8_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i8> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV32-NEXT: vwmulu.vx v18, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei16.v v8, (a0), v18, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i8_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, ma
; RV64-NEXT: vwmulu.vx v18, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei16.v v8, (a0), v18, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i8> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i16_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i16_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i16_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i16> %idxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i16_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulsu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i16_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i16> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i16_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i16> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 8
; RV32-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV32-NEXT: vwmulu.vx v20, v16, a2
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i16_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; RV64-NEXT: vwmulu.vx v20, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei32.v v8, (a0), v20, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i16> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8i32_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8i32_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8i32_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i32> %idxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv8i32_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv8i32_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv8i32_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulsu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = sext <vscale x 8 x i32> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv8i32_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i32> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv8i32_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv8i32_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: li a2, 8
; RV64-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV64-NEXT: vwmulu.vx v24, v16, a2
; RV64-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 8 x i32> %idxs to <vscale x 8 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %eidxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv8f64(<vscale x 8 x double> %val, ptr %base, <vscale x 8 x i64> %idxs, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; RV32-NEXT: vnsrl.wi v24, v16, 0
; RV32-NEXT: vsll.vi v16, v24, 3
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 8 x i64> %idxs
call void @llvm.vp.scatter.nxv8f64.nxv8p0(<vscale x 8 x double> %val, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %m, i32 %evl)
ret void
}
declare void @llvm.vp.scatter.nxv16f64.nxv16p0(<vscale x 16 x double>, <vscale x 16 x ptr>, <vscale x 16 x i1>, i32)
define void @vpscatter_nxv16f64(<vscale x 16 x double> %val, <vscale x 16 x ptr> %ptrs, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_nxv16f64:
; RV32: # %bb.0:
; RV32-NEXT: vl8re32.v v24, (a0)
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: mv a2, a1
; RV32-NEXT: bltu a1, a0, .LBB108_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a0
; RV32-NEXT: .LBB108_2:
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (zero), v24, v0.t
; RV32-NEXT: sub a2, a1, a0
; RV32-NEXT: srli a0, a0, 3
; RV32-NEXT: sltu a1, a1, a2
; RV32-NEXT: addi a1, a1, -1
; RV32-NEXT: and a1, a1, a2
; RV32-NEXT: vsetvli a2, zero, e8, mf4, ta, ma
; RV32-NEXT: vslidedown.vx v0, v0, a0
; RV32-NEXT: vsetvli zero, a1, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v16, (zero), v28, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_nxv16f64:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -16
; RV64-NEXT: .cfi_def_cfa_offset 16
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: slli a1, a1, 3
; RV64-NEXT: sub sp, sp, a1
; RV64-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; RV64-NEXT: addi a1, sp, 16
; RV64-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: slli a3, a1, 3
; RV64-NEXT: add a3, a0, a3
; RV64-NEXT: vl8re64.v v16, (a3)
; RV64-NEXT: mv a3, a2
; RV64-NEXT: vl8re64.v v24, (a0)
; RV64-NEXT: bltu a2, a1, .LBB108_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a3, a1
; RV64-NEXT: .LBB108_2:
; RV64-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v24, v0.t
; RV64-NEXT: sub a0, a2, a1
; RV64-NEXT: srli a1, a1, 3
; RV64-NEXT: sltu a2, a2, a0
; RV64-NEXT: addi a2, a2, -1
; RV64-NEXT: and a0, a2, a0
; RV64-NEXT: vsetvli a2, zero, e8, mf4, ta, ma
; RV64-NEXT: vslidedown.vx v0, v0, a1
; RV64-NEXT: addi a1, sp, 16
; RV64-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
; RV64-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: slli a0, a0, 3
; RV64-NEXT: add sp, sp, a0
; RV64-NEXT: .cfi_def_cfa sp, 16
; RV64-NEXT: addi sp, sp, 16
; RV64-NEXT: .cfi_def_cfa_offset 0
; RV64-NEXT: ret
call void @llvm.vp.scatter.nxv16f64.nxv16p0(<vscale x 16 x double> %val, <vscale x 16 x ptr> %ptrs, <vscale x 16 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_nxv16i16_nxv16f64(<vscale x 16 x double> %val, ptr %base, <vscale x 16 x i16> %idxs, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_nxv16i16_nxv16f64:
; RV32: # %bb.0:
; RV32-NEXT: vl4re16.v v4, (a1)
; RV32-NEXT: li a1, 8
; RV32-NEXT: vsetvli a3, zero, e16, m4, ta, ma
; RV32-NEXT: vwmulsu.vx v24, v4, a1
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: mv a3, a2
; RV32-NEXT: bltu a2, a1, .LBB109_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a3, a1
; RV32-NEXT: .LBB109_2:
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v24, v0.t
; RV32-NEXT: sub a3, a2, a1
; RV32-NEXT: srli a1, a1, 3
; RV32-NEXT: sltu a2, a2, a3
; RV32-NEXT: addi a2, a2, -1
; RV32-NEXT: and a2, a2, a3
; RV32-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV32-NEXT: vslidedown.vx v0, v0, a1
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v16, (a0), v28, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_nxv16i16_nxv16f64:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -16
; RV64-NEXT: .cfi_def_cfa_offset 16
; RV64-NEXT: csrr a3, vlenb
; RV64-NEXT: slli a3, a3, 4
; RV64-NEXT: sub sp, sp, a3
; RV64-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
; RV64-NEXT: csrr a3, vlenb
; RV64-NEXT: slli a3, a3, 3
; RV64-NEXT: add a3, sp, a3
; RV64-NEXT: addi a3, a3, 16
; RV64-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; RV64-NEXT: vl4re16.v v24, (a1)
; RV64-NEXT: vsetvli a1, zero, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v26
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: addi a1, sp, 16
; RV64-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; RV64-NEXT: vsext.vf4 v16, v24
; RV64-NEXT: vsll.vi v24, v16, 3
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: mv a3, a2
; RV64-NEXT: bltu a2, a1, .LBB109_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a3, a1
; RV64-NEXT: .LBB109_2:
; RV64-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: sub a3, a2, a1
; RV64-NEXT: srli a1, a1, 3
; RV64-NEXT: sltu a2, a2, a3
; RV64-NEXT: addi a2, a2, -1
; RV64-NEXT: and a2, a2, a3
; RV64-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV64-NEXT: vslidedown.vx v0, v0, a1
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: slli a1, a1, 3
; RV64-NEXT: add a1, sp, a1
; RV64-NEXT: addi a1, a1, 16
; RV64-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
; RV64-NEXT: addi a1, sp, 16
; RV64-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: slli a0, a0, 4
; RV64-NEXT: add sp, sp, a0
; RV64-NEXT: .cfi_def_cfa sp, 16
; RV64-NEXT: addi sp, sp, 16
; RV64-NEXT: .cfi_def_cfa_offset 0
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 16 x i16> %idxs
call void @llvm.vp.scatter.nxv16f64.nxv16p0(<vscale x 16 x double> %val, <vscale x 16 x ptr> %ptrs, <vscale x 16 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_sext_nxv16i16_nxv16f64(<vscale x 16 x double> %val, ptr %base, <vscale x 16 x i16> %idxs, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_sext_nxv16i16_nxv16f64:
; RV32: # %bb.0:
; RV32-NEXT: vl4re16.v v4, (a1)
; RV32-NEXT: li a1, 8
; RV32-NEXT: vsetvli a3, zero, e16, m4, ta, ma
; RV32-NEXT: vwmulsu.vx v24, v4, a1
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: mv a3, a2
; RV32-NEXT: bltu a2, a1, .LBB110_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a3, a1
; RV32-NEXT: .LBB110_2:
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v24, v0.t
; RV32-NEXT: sub a3, a2, a1
; RV32-NEXT: srli a1, a1, 3
; RV32-NEXT: sltu a2, a2, a3
; RV32-NEXT: addi a2, a2, -1
; RV32-NEXT: and a2, a2, a3
; RV32-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV32-NEXT: vslidedown.vx v0, v0, a1
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v16, (a0), v28, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_sext_nxv16i16_nxv16f64:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -16
; RV64-NEXT: .cfi_def_cfa_offset 16
; RV64-NEXT: csrr a3, vlenb
; RV64-NEXT: slli a3, a3, 4
; RV64-NEXT: sub sp, sp, a3
; RV64-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
; RV64-NEXT: csrr a3, vlenb
; RV64-NEXT: slli a3, a3, 3
; RV64-NEXT: add a3, sp, a3
; RV64-NEXT: addi a3, a3, 16
; RV64-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; RV64-NEXT: vl4re16.v v24, (a1)
; RV64-NEXT: vsetvli a1, zero, e64, m8, ta, ma
; RV64-NEXT: vsext.vf4 v16, v26
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: addi a1, sp, 16
; RV64-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; RV64-NEXT: vsext.vf4 v16, v24
; RV64-NEXT: vsll.vi v24, v16, 3
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: mv a3, a2
; RV64-NEXT: bltu a2, a1, .LBB110_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a3, a1
; RV64-NEXT: .LBB110_2:
; RV64-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: sub a3, a2, a1
; RV64-NEXT: srli a1, a1, 3
; RV64-NEXT: sltu a2, a2, a3
; RV64-NEXT: addi a2, a2, -1
; RV64-NEXT: and a2, a2, a3
; RV64-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV64-NEXT: vslidedown.vx v0, v0, a1
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: slli a1, a1, 3
; RV64-NEXT: add a1, sp, a1
; RV64-NEXT: addi a1, a1, 16
; RV64-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
; RV64-NEXT: addi a1, sp, 16
; RV64-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV64-NEXT: vsoxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: slli a0, a0, 4
; RV64-NEXT: add sp, sp, a0
; RV64-NEXT: .cfi_def_cfa sp, 16
; RV64-NEXT: addi sp, sp, 16
; RV64-NEXT: .cfi_def_cfa_offset 0
; RV64-NEXT: ret
%eidxs = sext <vscale x 16 x i16> %idxs to <vscale x 16 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 16 x i64> %eidxs
call void @llvm.vp.scatter.nxv16f64.nxv16p0(<vscale x 16 x double> %val, <vscale x 16 x ptr> %ptrs, <vscale x 16 x i1> %m, i32 %evl)
ret void
}
define void @vpscatter_baseidx_zext_nxv16i16_nxv16f64(<vscale x 16 x double> %val, ptr %base, <vscale x 16 x i16> %idxs, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpscatter_baseidx_zext_nxv16i16_nxv16f64:
; RV32: # %bb.0:
; RV32-NEXT: vl4re16.v v4, (a1)
; RV32-NEXT: li a1, 8
; RV32-NEXT: vsetvli a3, zero, e16, m4, ta, ma
; RV32-NEXT: vwmulu.vx v24, v4, a1
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: mv a3, a2
; RV32-NEXT: bltu a2, a1, .LBB111_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a3, a1
; RV32-NEXT: .LBB111_2:
; RV32-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v8, (a0), v24, v0.t
; RV32-NEXT: sub a3, a2, a1
; RV32-NEXT: srli a1, a1, 3
; RV32-NEXT: sltu a2, a2, a3
; RV32-NEXT: addi a2, a2, -1
; RV32-NEXT: and a2, a2, a3
; RV32-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV32-NEXT: vslidedown.vx v0, v0, a1
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT: vsoxei32.v v16, (a0), v28, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpscatter_baseidx_zext_nxv16i16_nxv16f64:
; RV64: # %bb.0:
; RV64-NEXT: vl4re16.v v4, (a1)
; RV64-NEXT: li a1, 8
; RV64-NEXT: vsetvli a3, zero, e16, m4, ta, ma
; RV64-NEXT: vwmulu.vx v24, v4, a1
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: mv a3, a2
; RV64-NEXT: bltu a2, a1, .LBB111_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a3, a1
; RV64-NEXT: .LBB111_2:
; RV64-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; RV64-NEXT: vsoxei32.v v8, (a0), v24, v0.t
; RV64-NEXT: sub a3, a2, a1
; RV64-NEXT: srli a1, a1, 3
; RV64-NEXT: sltu a2, a2, a3
; RV64-NEXT: addi a2, a2, -1
; RV64-NEXT: and a2, a2, a3
; RV64-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV64-NEXT: vslidedown.vx v0, v0, a1
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; RV64-NEXT: vsoxei32.v v16, (a0), v28, v0.t
; RV64-NEXT: ret
%eidxs = zext <vscale x 16 x i16> %idxs to <vscale x 16 x i64>
%ptrs = getelementptr inbounds double, ptr %base, <vscale x 16 x i64> %eidxs
call void @llvm.vp.scatter.nxv16f64.nxv16p0(<vscale x 16 x double> %val, <vscale x 16 x ptr> %ptrs, <vscale x 16 x i1> %m, i32 %evl)
ret void
}
Reference in New Issue View Git Blame Copy Permalink