shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/RISCV/rvv/vfmadd-sdnode.ll
Luke Lau edac1b2d63
[RISCV] Promote bf16 ops to f32 with zvfbfmin (#108937) 
For f16 with zvfhmin, we promote most ops and VP ops to f32. This does
the same for bf16 with zvfbfmin, so the two fp types should now be in
sync.

There are a few places in the custom lowering where we need to check for
a LMUL 8 f16/bf16 vector that can't be promoted and must be split, this
extracts that out into isPromotedOpNeedingSplit.

In a follow up NFC we can deduplicate the code that sets up the
promotions.
2024-09-18 17:39:40 +08:00

1256 lines
55 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+zvfh,+zfbfmin,+zvfbfmin,+v -target-abi=ilp32d \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+zvfh,+zfbfmin,+zvfbfmin,+v -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple=riscv32 -mattr=+m,+d,+zfhmin,+zvfhmin,+zfbfmin,+zvfbfmin,+v -target-abi=ilp32d \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
; RUN: llc -mtriple=riscv64 -mattr=+m,+d,+zfhmin,+zvfhmin,+zfbfmin,+zvfbfmin,+v -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
; This tests a mix of vfmacc and vfmadd by using different operand orders to
; trigger commuting in TwoAddressInstructionPass.
define <vscale x 1 x bfloat> @vfmadd_vv_nxv1bf16(<vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, <vscale x 1 x bfloat> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv1bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfwcvtbf16.f.f.v v11, v10
; CHECK-NEXT: vfwcvtbf16.f.f.v v10, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v12, v9
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmadd.vv v12, v10, v11
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v12
; CHECK-NEXT: ret
%vd = call <vscale x 1 x bfloat> @llvm.fma.v1bf16(<vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, <vscale x 1 x bfloat> %vc)
ret <vscale x 1 x bfloat> %vd
}
define <vscale x 1 x bfloat> @vfmadd_vv_nxv1bf16_commuted(<vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, <vscale x 1 x bfloat> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv1bf16_commuted:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfwcvtbf16.f.f.v v11, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v8, v9
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v10
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmadd.vv v9, v8, v11
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v9
; CHECK-NEXT: ret
%vd = call <vscale x 1 x bfloat> @llvm.fma.v1bf16(<vscale x 1 x bfloat> %vb, <vscale x 1 x bfloat> %vc, <vscale x 1 x bfloat> %va)
ret <vscale x 1 x bfloat> %vd
}
define <vscale x 1 x bfloat> @vfmadd_vf_nxv1bf16(<vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, bfloat %c) {
; CHECK-LABEL: vfmadd_vf_nxv1bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fmv.x.h a0, fa0
; CHECK-NEXT: vsetvli a1, zero, e16, mf4, ta, ma
; CHECK-NEXT: vmv.v.x v10, a0
; CHECK-NEXT: vfwcvtbf16.f.f.v v11, v9
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v12, v10
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmadd.vv v12, v9, v11
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v12
; CHECK-NEXT: ret
%head = insertelement <vscale x 1 x bfloat> poison, bfloat %c, i32 0
%splat = shufflevector <vscale x 1 x bfloat> %head, <vscale x 1 x bfloat> poison, <vscale x 1 x i32> zeroinitializer
%vd = call <vscale x 1 x bfloat> @llvm.fma.v1bf16(<vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %splat, <vscale x 1 x bfloat> %vb)
ret <vscale x 1 x bfloat> %vd
}
declare <vscale x 2 x bfloat> @llvm.fma.v2bf16(<vscale x 2 x bfloat>, <vscale x 2 x bfloat>, <vscale x 2 x bfloat>)
define <vscale x 2 x bfloat> @vfmadd_vv_nxv2bf16(<vscale x 2 x bfloat> %va, <vscale x 2 x bfloat> %vb, <vscale x 2 x bfloat> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv2bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
; CHECK-NEXT: vfwcvtbf16.f.f.v v11, v9
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v12, v10
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT: vfmadd.vv v12, v9, v11
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v12
; CHECK-NEXT: ret
%vd = call <vscale x 2 x bfloat> @llvm.fma.v2bf16(<vscale x 2 x bfloat> %va, <vscale x 2 x bfloat> %vc, <vscale x 2 x bfloat> %vb)
ret <vscale x 2 x bfloat> %vd
}
define <vscale x 2 x bfloat> @vfmadd_vf_nxv2bf16(<vscale x 2 x bfloat> %va, <vscale x 2 x bfloat> %vb, bfloat %c) {
; CHECK-LABEL: vfmadd_vf_nxv2bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fmv.x.h a0, fa0
; CHECK-NEXT: vsetvli a1, zero, e16, mf2, ta, ma
; CHECK-NEXT: vmv.v.x v10, a0
; CHECK-NEXT: vfwcvtbf16.f.f.v v11, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v8, v9
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v10
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT: vfmadd.vv v9, v8, v11
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v9
; CHECK-NEXT: ret
%head = insertelement <vscale x 2 x bfloat> poison, bfloat %c, i32 0
%splat = shufflevector <vscale x 2 x bfloat> %head, <vscale x 2 x bfloat> poison, <vscale x 2 x i32> zeroinitializer
%vd = call <vscale x 2 x bfloat> @llvm.fma.v2bf16(<vscale x 2 x bfloat> %vb, <vscale x 2 x bfloat> %splat, <vscale x 2 x bfloat> %va)
ret <vscale x 2 x bfloat> %vd
}
declare <vscale x 4 x bfloat> @llvm.fma.v4bf16(<vscale x 4 x bfloat>, <vscale x 4 x bfloat>, <vscale x 4 x bfloat>)
define <vscale x 4 x bfloat> @vfmadd_vv_nxv4bf16(<vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %vb, <vscale x 4 x bfloat> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma
; CHECK-NEXT: vfwcvtbf16.f.f.v v12, v10
; CHECK-NEXT: vfwcvtbf16.f.f.v v10, v9
; CHECK-NEXT: vfwcvtbf16.f.f.v v14, v8
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: vfmadd.vv v14, v10, v12
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v14
; CHECK-NEXT: ret
%vd = call <vscale x 4 x bfloat> @llvm.fma.v4bf16(<vscale x 4 x bfloat> %vb, <vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %vc)
ret <vscale x 4 x bfloat> %vd
}
define <vscale x 4 x bfloat> @vfmadd_vf_nxv4bf16(<vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %vb, bfloat %c) {
; CHECK-LABEL: vfmadd_vf_nxv4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fmv.x.h a0, fa0
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, ma
; CHECK-NEXT: vmv.v.x v10, a0
; CHECK-NEXT: vfwcvtbf16.f.f.v v12, v9
; CHECK-NEXT: vfwcvtbf16.f.f.v v14, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v16, v10
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: vfmadd.vv v16, v14, v12
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v16
; CHECK-NEXT: ret
%head = insertelement <vscale x 4 x bfloat> poison, bfloat %c, i32 0
%splat = shufflevector <vscale x 4 x bfloat> %head, <vscale x 4 x bfloat> poison, <vscale x 4 x i32> zeroinitializer
%vd = call <vscale x 4 x bfloat> @llvm.fma.v4bf16(<vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %splat, <vscale x 4 x bfloat> %vb)
ret <vscale x 4 x bfloat> %vd
}
declare <vscale x 8 x bfloat> @llvm.fma.v8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
define <vscale x 8 x bfloat> @vfmadd_vv_nxv8bf16(<vscale x 8 x bfloat> %va, <vscale x 8 x bfloat> %vb, <vscale x 8 x bfloat> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma
; CHECK-NEXT: vfwcvtbf16.f.f.v v16, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v20, v10
; CHECK-NEXT: vfwcvtbf16.f.f.v v24, v12
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; CHECK-NEXT: vfmadd.vv v24, v20, v16
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v24
; CHECK-NEXT: ret
%vd = call <vscale x 8 x bfloat> @llvm.fma.v8bf16(<vscale x 8 x bfloat> %vb, <vscale x 8 x bfloat> %vc, <vscale x 8 x bfloat> %va)
ret <vscale x 8 x bfloat> %vd
}
define <vscale x 8 x bfloat> @vfmadd_vf_nxv8bf16(<vscale x 8 x bfloat> %va, <vscale x 8 x bfloat> %vb, bfloat %c) {
; CHECK-LABEL: vfmadd_vf_nxv8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fmv.x.h a0, fa0
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.v.x v12, a0
; CHECK-NEXT: vfwcvtbf16.f.f.v v16, v8
; CHECK-NEXT: vfwcvtbf16.f.f.v v20, v10
; CHECK-NEXT: vfwcvtbf16.f.f.v v24, v12
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; CHECK-NEXT: vfmadd.vv v24, v20, v16
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v24
; CHECK-NEXT: ret
%head = insertelement <vscale x 8 x bfloat> poison, bfloat %c, i32 0
%splat = shufflevector <vscale x 8 x bfloat> %head, <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
%vd = call <vscale x 8 x bfloat> @llvm.fma.v8bf16(<vscale x 8 x bfloat> %vb, <vscale x 8 x bfloat> %splat, <vscale x 8 x bfloat> %va)
ret <vscale x 8 x bfloat> %vd
}
declare <vscale x 16 x bfloat> @llvm.fma.v16bf16(<vscale x 16 x bfloat>, <vscale x 16 x bfloat>, <vscale x 16 x bfloat>)
define <vscale x 16 x bfloat> @vfmadd_vv_nxv16bf16(<vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %vb, <vscale x 16 x bfloat> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv16bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; CHECK-NEXT: vfwcvtbf16.f.f.v v24, v12
; CHECK-NEXT: vfwcvtbf16.f.f.v v0, v16
; CHECK-NEXT: vfwcvtbf16.f.f.v v16, v8
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; CHECK-NEXT: vfmadd.vv v16, v0, v24
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v16
; CHECK-NEXT: ret
%vd = call <vscale x 16 x bfloat> @llvm.fma.v16bf16(<vscale x 16 x bfloat> %vc, <vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %vb)
ret <vscale x 16 x bfloat> %vd
}
define <vscale x 16 x bfloat> @vfmadd_vf_nxv16bf16(<vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %vb, bfloat %c) {
; CHECK-LABEL: vfmadd_vf_nxv16bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: sub sp, sp, a0
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x04, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 4 * vlenb
; CHECK-NEXT: fmv.x.h a0, fa0
; CHECK-NEXT: vsetvli a1, zero, e16, m4, ta, ma
; CHECK-NEXT: vmv.v.x v16, a0
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs4r.v v16, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: vfwcvtbf16.f.f.v v24, v12
; CHECK-NEXT: vfwcvtbf16.f.f.v v0, v8
; CHECK-NEXT: vl4r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vfwcvtbf16.f.f.v v16, v8
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; CHECK-NEXT: vfmadd.vv v16, v0, v24
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v16
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%head = insertelement <vscale x 16 x bfloat> poison, bfloat %c, i32 0
%splat = shufflevector <vscale x 16 x bfloat> %head, <vscale x 16 x bfloat> poison, <vscale x 16 x i32> zeroinitializer
%vd = call <vscale x 16 x bfloat> @llvm.fma.v16bf16(<vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %splat, <vscale x 16 x bfloat> %vb)
ret <vscale x 16 x bfloat> %vd
}
declare <vscale x 32 x bfloat> @llvm.fma.v32bf16(<vscale x 32 x bfloat>, <vscale x 32 x bfloat>, <vscale x 32 x bfloat>)
define <vscale x 32 x bfloat> @vfmadd_vv_nxv32bf16(<vscale x 32 x bfloat> %va, <vscale x 32 x bfloat> %vb, <vscale x 32 x bfloat> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv32bf16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: addi sp, sp, -16
; ZVFH-NEXT: .cfi_def_cfa_offset 16
; ZVFH-NEXT: csrr a1, vlenb
; ZVFH-NEXT: slli a1, a1, 5
; ZVFH-NEXT: sub sp, sp, a1
; ZVFH-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 32 * vlenb
; ZVFH-NEXT: vl8re16.v v0, (a0)
; ZVFH-NEXT: vmv8r.v v24, v16
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 4
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vmv8r.v v16, v8
; ZVFH-NEXT: addi a0, sp, 16
; ZVFH-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfwcvtbf16.f.f.v v8, v16
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: mv a1, a0
; ZVFH-NEXT: slli a0, a0, 1
; ZVFH-NEXT: add a0, a0, a1
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vfwcvtbf16.f.f.v v8, v24
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vmv8r.v v8, v0
; ZVFH-NEXT: vfwcvtbf16.f.f.v v0, v8
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: mv a1, a0
; ZVFH-NEXT: slli a0, a0, 1
; ZVFH-NEXT: add a0, a0, a1
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFH-NEXT: vfmadd.vv v0, v16, v24
; ZVFH-NEXT: addi a0, sp, 16
; ZVFH-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfwcvtbf16.f.f.v v24, v20
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 4
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vfwcvtbf16.f.f.v v24, v20
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: mv a1, a0
; ZVFH-NEXT: slli a0, a0, 1
; ZVFH-NEXT: add a0, a0, a1
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vfwcvtbf16.f.f.v v16, v12
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: mv a1, a0
; ZVFH-NEXT: slli a0, a0, 1
; ZVFH-NEXT: add a0, a0, a1
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFH-NEXT: vfmadd.vv v16, v8, v24
; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfncvtbf16.f.f.w v8, v0
; ZVFH-NEXT: vfncvtbf16.f.f.w v12, v16
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 5
; ZVFH-NEXT: add sp, sp, a0
; ZVFH-NEXT: addi sp, sp, 16
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv32bf16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: addi sp, sp, -16
; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16
; ZVFHMIN-NEXT: csrr a1, vlenb
; ZVFHMIN-NEXT: slli a1, a1, 5
; ZVFHMIN-NEXT: sub sp, sp, a1
; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 32 * vlenb
; ZVFHMIN-NEXT: vl8re16.v v0, (a0)
; ZVFHMIN-NEXT: vmv8r.v v24, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vmv8r.v v16, v8
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v8, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v8, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vmv8r.v v8, v0
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v0, v8
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v0, v16, v24
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v24, v20
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v24, v20
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v16, v12
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v16, v8, v24
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvtbf16.f.f.w v8, v0
; ZVFHMIN-NEXT: vfncvtbf16.f.f.w v12, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 5
; ZVFHMIN-NEXT: add sp, sp, a0
; ZVFHMIN-NEXT: addi sp, sp, 16
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 32 x bfloat> @llvm.fma.v32bf16(<vscale x 32 x bfloat> %vc, <vscale x 32 x bfloat> %vb, <vscale x 32 x bfloat> %va)
ret <vscale x 32 x bfloat> %vd
}
define <vscale x 32 x bfloat> @vfmadd_vf_nxv32bf16(<vscale x 32 x bfloat> %va, <vscale x 32 x bfloat> %vb, bfloat %c) {
; ZVFH-LABEL: vfmadd_vf_nxv32bf16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: addi sp, sp, -16
; ZVFH-NEXT: .cfi_def_cfa_offset 16
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: mv a1, a0
; ZVFH-NEXT: slli a0, a0, 1
; ZVFH-NEXT: add a0, a0, a1
; ZVFH-NEXT: sub sp, sp, a0
; ZVFH-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
; ZVFH-NEXT: vmv8r.v v24, v16
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: fmv.x.h a0, fa0
; ZVFH-NEXT: vsetvli a1, zero, e16, m8, ta, ma
; ZVFH-NEXT: vmv.v.x v16, a0
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 4
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfwcvtbf16.f.f.v v16, v8
; ZVFH-NEXT: addi a0, sp, 16
; ZVFH-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: vfwcvtbf16.f.f.v v16, v24
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 4
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vfwcvtbf16.f.f.v v0, v24
; ZVFH-NEXT: addi a0, sp, 16
; ZVFH-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFH-NEXT: vfmadd.vv v0, v16, v24
; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfwcvtbf16.f.f.v v16, v12
; ZVFH-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vfwcvtbf16.f.f.v v8, v20
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 4
; ZVFH-NEXT: add a0, sp, a0
; ZVFH-NEXT: addi a0, a0, 16
; ZVFH-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vfwcvtbf16.f.f.v v24, v20
; ZVFH-NEXT: addi a0, sp, 16
; ZVFH-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFH-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFH-NEXT: vfmadd.vv v24, v8, v16
; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfncvtbf16.f.f.w v8, v0
; ZVFH-NEXT: vfncvtbf16.f.f.w v12, v24
; ZVFH-NEXT: csrr a0, vlenb
; ZVFH-NEXT: slli a0, a0, 3
; ZVFH-NEXT: mv a1, a0
; ZVFH-NEXT: slli a0, a0, 1
; ZVFH-NEXT: add a0, a0, a1
; ZVFH-NEXT: add sp, sp, a0
; ZVFH-NEXT: addi sp, sp, 16
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv32bf16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: addi sp, sp, -16
; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: sub sp, sp, a0
; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
; ZVFHMIN-NEXT: vmv8r.v v24, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m8, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v16, a0
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v16, v8
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v16, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v0, v24
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v0, v16, v24
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v16, v12
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v8, v20
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvtbf16.f.f.v v24, v20
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v24, v8, v16
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvtbf16.f.f.w v8, v0
; ZVFHMIN-NEXT: vfncvtbf16.f.f.w v12, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add sp, sp, a0
; ZVFHMIN-NEXT: addi sp, sp, 16
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 32 x bfloat> poison, bfloat %c, i32 0
%splat = shufflevector <vscale x 32 x bfloat> %head, <vscale x 32 x bfloat> poison, <vscale x 32 x i32> zeroinitializer
%vd = call <vscale x 32 x bfloat> @llvm.fma.v32bf16(<vscale x 32 x bfloat> %vb, <vscale x 32 x bfloat> %splat, <vscale x 32 x bfloat> %va)
ret <vscale x 32 x bfloat> %vd
}
declare <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x half>)
define <vscale x 1 x half> @vfmadd_vv_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv1f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; ZVFH-NEXT: vfmadd.vv v8, v9, v10
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv1f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v11, v10
; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v9
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v12, v10, v11
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc)
ret <vscale x 1 x half> %vd
}
define <vscale x 1 x half> @vfmadd_vv_nxv1f16_commuted(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, <vscale x 1 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv1f16_commuted:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; ZVFH-NEXT: vfmacc.vv v8, v10, v9
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv1f16_commuted:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v11, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v9
; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v10
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v9, v8, v11
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %vb, <vscale x 1 x half> %vc, <vscale x 1 x half> %va)
ret <vscale x 1 x half> %vd
}
define <vscale x 1 x half> @vfmadd_vf_nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %vb, half %c) {
; ZVFH-LABEL: vfmadd_vf_nxv1f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
; ZVFH-NEXT: vfmadd.vf v8, fa0, v9
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv1f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v10, a0
; ZVFHMIN-NEXT: vfwcvt.f.f.v v11, v9
; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v12, v9, v11
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 1 x half> poison, half %c, i32 0
%splat = shufflevector <vscale x 1 x half> %head, <vscale x 1 x half> poison, <vscale x 1 x i32> zeroinitializer
%vd = call <vscale x 1 x half> @llvm.fma.v1f16(<vscale x 1 x half> %va, <vscale x 1 x half> %splat, <vscale x 1 x half> %vb)
ret <vscale x 1 x half> %vd
}
declare <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
define <vscale x 2 x half> @vfmadd_vv_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, <vscale x 2 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv2f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
; ZVFH-NEXT: vfmadd.vv v8, v10, v9
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv2f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v11, v9
; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v12, v9, v11
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vc, <vscale x 2 x half> %vb)
ret <vscale x 2 x half> %vd
}
define <vscale x 2 x half> @vfmadd_vf_nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x half> %vb, half %c) {
; ZVFH-LABEL: vfmadd_vf_nxv2f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
; ZVFH-NEXT: vfmacc.vf v8, fa0, v9
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv2f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v10, a0
; ZVFHMIN-NEXT: vfwcvt.f.f.v v11, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v9
; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v10
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v9, v8, v11
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 2 x half> poison, half %c, i32 0
%splat = shufflevector <vscale x 2 x half> %head, <vscale x 2 x half> poison, <vscale x 2 x i32> zeroinitializer
%vd = call <vscale x 2 x half> @llvm.fma.v2f16(<vscale x 2 x half> %vb, <vscale x 2 x half> %splat, <vscale x 2 x half> %va)
ret <vscale x 2 x half> %vd
}
declare <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
define <vscale x 4 x half> @vfmadd_vv_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, <vscale x 4 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv4f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m1, ta, ma
; ZVFH-NEXT: vfmadd.vv v8, v9, v10
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv4f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v10
; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v9
; ZVFHMIN-NEXT: vfwcvt.f.f.v v14, v8
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v14, v10, v12
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v14
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %vb, <vscale x 4 x half> %va, <vscale x 4 x half> %vc)
ret <vscale x 4 x half> %vd
}
define <vscale x 4 x half> @vfmadd_vf_nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %vb, half %c) {
; ZVFH-LABEL: vfmadd_vf_nxv4f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m1, ta, ma
; ZVFH-NEXT: vfmadd.vf v8, fa0, v9
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv4f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v10, a0
; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v9
; ZVFHMIN-NEXT: vfwcvt.f.f.v v14, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v10
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v16, v14, v12
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 4 x half> poison, half %c, i32 0
%splat = shufflevector <vscale x 4 x half> %head, <vscale x 4 x half> poison, <vscale x 4 x i32> zeroinitializer
%vd = call <vscale x 4 x half> @llvm.fma.v4f16(<vscale x 4 x half> %va, <vscale x 4 x half> %splat, <vscale x 4 x half> %vb)
ret <vscale x 4 x half> %vd
}
declare <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
define <vscale x 8 x half> @vfmadd_vv_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, <vscale x 8 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv8f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m2, ta, ma
; ZVFH-NEXT: vfmacc.vv v8, v12, v10
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv8f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v20, v10
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v12
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v24, v20, v16
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v24
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %vc, <vscale x 8 x half> %va)
ret <vscale x 8 x half> %vd
}
define <vscale x 8 x half> @vfmadd_vf_nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x half> %vb, half %c) {
; ZVFH-LABEL: vfmadd_vf_nxv8f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m2, ta, ma
; ZVFH-NEXT: vfmacc.vf v8, fa0, v10
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv8f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v12, a0
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT: vfwcvt.f.f.v v20, v10
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v12
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v24, v20, v16
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v24
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 8 x half> poison, half %c, i32 0
%splat = shufflevector <vscale x 8 x half> %head, <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
%vd = call <vscale x 8 x half> @llvm.fma.v8f16(<vscale x 8 x half> %vb, <vscale x 8 x half> %splat, <vscale x 8 x half> %va)
ret <vscale x 8 x half> %vd
}
declare <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
define <vscale x 16 x half> @vfmadd_vv_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, <vscale x 16 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv16f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfmadd.vv v8, v16, v12
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv16f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v12
; ZVFHMIN-NEXT: vfwcvt.f.f.v v0, v16
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v16, v0, v24
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %vc, <vscale x 16 x half> %va, <vscale x 16 x half> %vb)
ret <vscale x 16 x half> %vd
}
define <vscale x 16 x half> @vfmadd_vf_nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %vb, half %c) {
; ZVFH-LABEL: vfmadd_vf_nxv16f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFH-NEXT: vfmadd.vf v8, fa0, v12
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv16f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: addi sp, sp, -16
; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 2
; ZVFHMIN-NEXT: sub sp, sp, a0
; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x04, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 4 * vlenb
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v16, a0
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vs4r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v12
; ZVFHMIN-NEXT: vfwcvt.f.f.v v0, v8
; ZVFHMIN-NEXT: vl4r.v v8, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v16, v0, v24
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 2
; ZVFHMIN-NEXT: add sp, sp, a0
; ZVFHMIN-NEXT: addi sp, sp, 16
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 16 x half> poison, half %c, i32 0
%splat = shufflevector <vscale x 16 x half> %head, <vscale x 16 x half> poison, <vscale x 16 x i32> zeroinitializer
%vd = call <vscale x 16 x half> @llvm.fma.v16f16(<vscale x 16 x half> %va, <vscale x 16 x half> %splat, <vscale x 16 x half> %vb)
ret <vscale x 16 x half> %vd
}
declare <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half>, <vscale x 32 x half>, <vscale x 32 x half>)
define <vscale x 32 x half> @vfmadd_vv_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, <vscale x 32 x half> %vc) {
; ZVFH-LABEL: vfmadd_vv_nxv32f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vl8re16.v v24, (a0)
; ZVFH-NEXT: vsetvli a0, zero, e16, m8, ta, ma
; ZVFH-NEXT: vfmacc.vv v8, v16, v24
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vv_nxv32f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: addi sp, sp, -16
; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16
; ZVFHMIN-NEXT: csrr a1, vlenb
; ZVFHMIN-NEXT: slli a1, a1, 5
; ZVFHMIN-NEXT: sub sp, sp, a1
; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 32 * vlenb
; ZVFHMIN-NEXT: vl8re16.v v0, (a0)
; ZVFHMIN-NEXT: vmv8r.v v24, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vmv8r.v v16, v8
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vmv8r.v v8, v0
; ZVFHMIN-NEXT: vfwcvt.f.f.v v0, v8
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v0, v16, v24
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v20
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v20
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v16, v8, v24
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v0
; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 5
; ZVFHMIN-NEXT: add sp, sp, a0
; ZVFHMIN-NEXT: addi sp, sp, 16
; ZVFHMIN-NEXT: ret
%vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %vc, <vscale x 32 x half> %vb, <vscale x 32 x half> %va)
ret <vscale x 32 x half> %vd
}
define <vscale x 32 x half> @vfmadd_vf_nxv32f16(<vscale x 32 x half> %va, <vscale x 32 x half> %vb, half %c) {
; ZVFH-LABEL: vfmadd_vf_nxv32f16:
; ZVFH: # %bb.0:
; ZVFH-NEXT: vsetvli a0, zero, e16, m8, ta, ma
; ZVFH-NEXT: vfmacc.vf v8, fa0, v16
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vfmadd_vf_nxv32f16:
; ZVFHMIN: # %bb.0:
; ZVFHMIN-NEXT: addi sp, sp, -16
; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: sub sp, sp, a0
; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
; ZVFHMIN-NEXT: vmv8r.v v24, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: fmv.x.h a0, fa0
; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m8, ta, ma
; ZVFHMIN-NEXT: vmv.v.x v16, a0
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvt.f.f.v v0, v24
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v0, v16, v24
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12
; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v20
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v20
; ZVFHMIN-NEXT: addi a0, sp, 16
; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; ZVFHMIN-NEXT: vfmadd.vv v24, v8, v16
; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v0
; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: li a1, 24
; ZVFHMIN-NEXT: mul a0, a0, a1
; ZVFHMIN-NEXT: add sp, sp, a0
; ZVFHMIN-NEXT: addi sp, sp, 16
; ZVFHMIN-NEXT: ret
%head = insertelement <vscale x 32 x half> poison, half %c, i32 0
%splat = shufflevector <vscale x 32 x half> %head, <vscale x 32 x half> poison, <vscale x 32 x i32> zeroinitializer
%vd = call <vscale x 32 x half> @llvm.fma.v32f16(<vscale x 32 x half> %vb, <vscale x 32 x half> %splat, <vscale x 32 x half> %va)
ret <vscale x 32 x half> %vd
}
declare <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x float>)
define <vscale x 1 x float> @vfmadd_vv_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v9, v10
; CHECK-NEXT: ret
%vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, <vscale x 1 x float> %vc)
ret <vscale x 1 x float> %vd
}
define <vscale x 1 x float> @vfmadd_vf_nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %vb, float %c) {
; CHECK-LABEL: vfmadd_vf_nxv1f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmadd.vf v8, fa0, v9
; CHECK-NEXT: ret
%head = insertelement <vscale x 1 x float> poison, float %c, i32 0
%splat = shufflevector <vscale x 1 x float> %head, <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
%vd = call <vscale x 1 x float> @llvm.fma.v1f32(<vscale x 1 x float> %va, <vscale x 1 x float> %splat, <vscale x 1 x float> %vb)
ret <vscale x 1 x float> %vd
}
declare <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
define <vscale x 2 x float> @vfmadd_vv_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, <vscale x 2 x float> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v10, v9
; CHECK-NEXT: ret
%vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vc, <vscale x 2 x float> %vb)
ret <vscale x 2 x float> %vd
}
define <vscale x 2 x float> @vfmadd_vf_nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x float> %vb, float %c) {
; CHECK-LABEL: vfmadd_vf_nxv2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vfmacc.vf v8, fa0, v9
; CHECK-NEXT: ret
%head = insertelement <vscale x 2 x float> poison, float %c, i32 0
%splat = shufflevector <vscale x 2 x float> %head, <vscale x 2 x float> poison, <vscale x 2 x i32> zeroinitializer
%vd = call <vscale x 2 x float> @llvm.fma.v2f32(<vscale x 2 x float> %vb, <vscale x 2 x float> %splat, <vscale x 2 x float> %va)
ret <vscale x 2 x float> %vd
}
declare <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
define <vscale x 4 x float> @vfmadd_vv_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, <vscale x 4 x float> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v10, v12
; CHECK-NEXT: ret
%vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %vb, <vscale x 4 x float> %va, <vscale x 4 x float> %vc)
ret <vscale x 4 x float> %vd
}
define <vscale x 4 x float> @vfmadd_vf_nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %vb, float %c) {
; CHECK-LABEL: vfmadd_vf_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
; CHECK-NEXT: vfmadd.vf v8, fa0, v10
; CHECK-NEXT: ret
%head = insertelement <vscale x 4 x float> poison, float %c, i32 0
%splat = shufflevector <vscale x 4 x float> %head, <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
%vd = call <vscale x 4 x float> @llvm.fma.v4f32(<vscale x 4 x float> %va, <vscale x 4 x float> %splat, <vscale x 4 x float> %vb)
ret <vscale x 4 x float> %vd
}
declare <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
define <vscale x 8 x float> @vfmadd_vv_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, <vscale x 8 x float> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv8f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma
; CHECK-NEXT: vfmacc.vv v8, v16, v12
; CHECK-NEXT: ret
%vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %vc, <vscale x 8 x float> %va)
ret <vscale x 8 x float> %vd
}
define <vscale x 8 x float> @vfmadd_vf_nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x float> %vb, float %c) {
; CHECK-LABEL: vfmadd_vf_nxv8f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma
; CHECK-NEXT: vfmacc.vf v8, fa0, v12
; CHECK-NEXT: ret
%head = insertelement <vscale x 8 x float> poison, float %c, i32 0
%splat = shufflevector <vscale x 8 x float> %head, <vscale x 8 x float> poison, <vscale x 8 x i32> zeroinitializer
%vd = call <vscale x 8 x float> @llvm.fma.v8f32(<vscale x 8 x float> %vb, <vscale x 8 x float> %splat, <vscale x 8 x float> %va)
ret <vscale x 8 x float> %vd
}
declare <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
define <vscale x 16 x float> @vfmadd_vv_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, <vscale x 16 x float> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv16f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vl8re32.v v24, (a0)
; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v24, v16
; CHECK-NEXT: ret
%vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %vc, <vscale x 16 x float> %va, <vscale x 16 x float> %vb)
ret <vscale x 16 x float> %vd
}
define <vscale x 16 x float> @vfmadd_vf_nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %vb, float %c) {
; CHECK-LABEL: vfmadd_vf_nxv16f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma
; CHECK-NEXT: vfmadd.vf v8, fa0, v16
; CHECK-NEXT: ret
%head = insertelement <vscale x 16 x float> poison, float %c, i32 0
%splat = shufflevector <vscale x 16 x float> %head, <vscale x 16 x float> poison, <vscale x 16 x i32> zeroinitializer
%vd = call <vscale x 16 x float> @llvm.fma.v16f32(<vscale x 16 x float> %va, <vscale x 16 x float> %splat, <vscale x 16 x float> %vb)
ret <vscale x 16 x float> %vd
}
declare <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x double>)
define <vscale x 1 x double> @vfmadd_vv_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v9, v10
; CHECK-NEXT: ret
%vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, <vscale x 1 x double> %vc)
ret <vscale x 1 x double> %vd
}
define <vscale x 1 x double> @vfmadd_vf_nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %vb, double %c) {
; CHECK-LABEL: vfmadd_vf_nxv1f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma
; CHECK-NEXT: vfmadd.vf v8, fa0, v9
; CHECK-NEXT: ret
%head = insertelement <vscale x 1 x double> poison, double %c, i32 0
%splat = shufflevector <vscale x 1 x double> %head, <vscale x 1 x double> poison, <vscale x 1 x i32> zeroinitializer
%vd = call <vscale x 1 x double> @llvm.fma.v1f64(<vscale x 1 x double> %va, <vscale x 1 x double> %splat, <vscale x 1 x double> %vb)
ret <vscale x 1 x double> %vd
}
declare <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
define <vscale x 2 x double> @vfmadd_vv_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, <vscale x 2 x double> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v12, v10
; CHECK-NEXT: ret
%vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vc, <vscale x 2 x double> %vb)
ret <vscale x 2 x double> %vd
}
define <vscale x 2 x double> @vfmadd_vf_nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x double> %vb, double %c) {
; CHECK-LABEL: vfmadd_vf_nxv2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma
; CHECK-NEXT: vfmacc.vf v8, fa0, v10
; CHECK-NEXT: ret
%head = insertelement <vscale x 2 x double> poison, double %c, i32 0
%splat = shufflevector <vscale x 2 x double> %head, <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
%vd = call <vscale x 2 x double> @llvm.fma.v2f64(<vscale x 2 x double> %vb, <vscale x 2 x double> %splat, <vscale x 2 x double> %va)
ret <vscale x 2 x double> %vd
}
declare <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
define <vscale x 4 x double> @vfmadd_vv_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, <vscale x 4 x double> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, ma
; CHECK-NEXT: vfmadd.vv v8, v12, v16
; CHECK-NEXT: ret
%vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %vb, <vscale x 4 x double> %va, <vscale x 4 x double> %vc)
ret <vscale x 4 x double> %vd
}
define <vscale x 4 x double> @vfmadd_vf_nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %vb, double %c) {
; CHECK-LABEL: vfmadd_vf_nxv4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, ma
; CHECK-NEXT: vfmadd.vf v8, fa0, v12
; CHECK-NEXT: ret
%head = insertelement <vscale x 4 x double> poison, double %c, i32 0
%splat = shufflevector <vscale x 4 x double> %head, <vscale x 4 x double> poison, <vscale x 4 x i32> zeroinitializer
%vd = call <vscale x 4 x double> @llvm.fma.v4f64(<vscale x 4 x double> %va, <vscale x 4 x double> %splat, <vscale x 4 x double> %vb)
ret <vscale x 4 x double> %vd
}
declare <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
define <vscale x 8 x double> @vfmadd_vv_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, <vscale x 8 x double> %vc) {
; CHECK-LABEL: vfmadd_vv_nxv8f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vl8re64.v v24, (a0)
; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, ma
; CHECK-NEXT: vfmacc.vv v8, v16, v24
; CHECK-NEXT: ret
%vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %vc, <vscale x 8 x double> %va)
ret <vscale x 8 x double> %vd
}
define <vscale x 8 x double> @vfmadd_vf_nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x double> %vb, double %c) {
; CHECK-LABEL: vfmadd_vf_nxv8f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, ma
; CHECK-NEXT: vfmacc.vf v8, fa0, v16
; CHECK-NEXT: ret
%head = insertelement <vscale x 8 x double> poison, double %c, i32 0
%splat = shufflevector <vscale x 8 x double> %head, <vscale x 8 x double> poison, <vscale x 8 x i32> zeroinitializer
%vd = call <vscale x 8 x double> @llvm.fma.v8f64(<vscale x 8 x double> %vb, <vscale x 8 x double> %splat, <vscale x 8 x double> %va)
ret <vscale x 8 x double> %vd
}
Reference in New Issue View Git Blame Copy Permalink