forked from OSchip/llvm-project
115 lines
5.6 KiB
LLVM
115 lines
5.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=avx512f | FileCheck %s
|
|
|
|
define void @eggs(<8 x double>* %arg, <8 x double>* %arg1, <8 x double>* %arg2, <8 x double>* %arg3, <8 x double>* %arg4, <8 x double>* %arg5, i64 %arg6, i64 %arg7, i64 %arg8, i64 %arg9, i64 %arg10, i64 %arg11, i64 %arg12, double* %arg13, double* %arg14) nounwind {
|
|
; CHECK-LABEL: eggs:
|
|
; CHECK: ## %bb.0: ## %bb
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %r10
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %r11
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %r14
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %rbx
|
|
; CHECK-NEXT: leaq (%rbx,%r14,8), %r14
|
|
; CHECK-NEXT: leaq (%rbx,%r15,8), %r15
|
|
; CHECK-NEXT: vxorpd %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: xorl %ebx, %ebx
|
|
; CHECK-NEXT: movq {{[0-9]+}}(%rsp), %r13
|
|
; CHECK-NEXT: addq %r12, %r13
|
|
; CHECK-NEXT: addq {{[0-9]+}}(%rsp), %r12
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
|
|
; CHECK-NEXT: vxorpd %xmm3, %xmm3, %xmm3
|
|
; CHECK-NEXT: vxorpd %xmm4, %xmm4, %xmm4
|
|
; CHECK-NEXT: vxorpd %xmm5, %xmm5, %xmm5
|
|
; CHECK-NEXT: .p2align 4, 0x90
|
|
; CHECK-NEXT: LBB0_1: ## %bb15
|
|
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: vmovupd (%rax,%r11,8), %zmm6
|
|
; CHECK-NEXT: vmovupd (%rax,%r13,8), %zmm7
|
|
; CHECK-NEXT: vmovupd (%rax,%r12,8), %zmm8
|
|
; CHECK-NEXT: vbroadcastsd (%r15,%rbx,8), %zmm9
|
|
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm0 = (zmm6 * zmm9) + zmm0
|
|
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm1 = (zmm7 * zmm9) + zmm1
|
|
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm2 = (zmm8 * zmm9) + zmm2
|
|
; CHECK-NEXT: vbroadcastsd (%r14,%rbx,8), %zmm9
|
|
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm3 = (zmm9 * zmm6) + zmm3
|
|
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm4 = (zmm9 * zmm7) + zmm4
|
|
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm5 = (zmm8 * zmm9) + zmm5
|
|
; CHECK-NEXT: incq %rbx
|
|
; CHECK-NEXT: cmpq %rbx, %r10
|
|
; CHECK-NEXT: jne LBB0_1
|
|
; CHECK-NEXT: ## %bb.2: ## %bb51
|
|
; CHECK-NEXT: vmovapd %zmm0, (%rdi)
|
|
; CHECK-NEXT: vmovapd %zmm1, (%rsi)
|
|
; CHECK-NEXT: vmovapd %zmm2, (%rdx)
|
|
; CHECK-NEXT: vmovapd %zmm3, (%rcx)
|
|
; CHECK-NEXT: vmovapd %zmm4, (%r8)
|
|
; CHECK-NEXT: vmovapd %zmm5, (%r9)
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
bb:
|
|
br label %bb15
|
|
|
|
bb15: ; preds = %bb15, %bb
|
|
%tmp = phi <8 x double> [ zeroinitializer, %bb ], [ %tmp38, %bb15 ]
|
|
%tmp16 = phi <8 x double> [ zeroinitializer, %bb ], [ %tmp39, %bb15 ]
|
|
%tmp17 = phi <8 x double> [ zeroinitializer, %bb ], [ %tmp40, %bb15 ]
|
|
%tmp18 = phi <8 x double> [ zeroinitializer, %bb ], [ %tmp46, %bb15 ]
|
|
%tmp19 = phi <8 x double> [ zeroinitializer, %bb ], [ %tmp47, %bb15 ]
|
|
%tmp20 = phi <8 x double> [ zeroinitializer, %bb ], [ %tmp48, %bb15 ]
|
|
%tmp21 = phi i64 [ 0, %bb ], [ %tmp49, %bb15 ]
|
|
%tmp22 = getelementptr inbounds double, double* %arg14, i64 %arg11
|
|
%tmp23 = bitcast double* %tmp22 to <8 x double>*
|
|
%tmp24 = load <8 x double>, <8 x double>* %tmp23, align 8
|
|
%tmp25 = add i64 %arg10, %arg6
|
|
%tmp26 = getelementptr inbounds double, double* %arg14, i64 %tmp25
|
|
%tmp27 = bitcast double* %tmp26 to <8 x double>*
|
|
%tmp28 = load <8 x double>, <8 x double>* %tmp27, align 8
|
|
%tmp29 = add i64 %arg10, %arg7
|
|
%tmp30 = getelementptr inbounds double, double* %arg14, i64 %tmp29
|
|
%tmp31 = bitcast double* %tmp30 to <8 x double>*
|
|
%tmp32 = load <8 x double>, <8 x double>* %tmp31, align 8
|
|
%tmp33 = add i64 %tmp21, %arg8
|
|
%tmp34 = getelementptr inbounds double, double* %arg13, i64 %tmp33
|
|
%tmp35 = load double, double* %tmp34, align 8
|
|
%tmp36 = insertelement <8 x double> undef, double %tmp35, i32 0
|
|
%tmp37 = shufflevector <8 x double> %tmp36, <8 x double> undef, <8 x i32> zeroinitializer
|
|
%tmp38 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> %tmp24, <8 x double> %tmp37, <8 x double> %tmp)
|
|
%tmp39 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> %tmp28, <8 x double> %tmp37, <8 x double> %tmp16)
|
|
%tmp40 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> %tmp32, <8 x double> %tmp37, <8 x double> %tmp17)
|
|
%tmp41 = add i64 %tmp21, %arg9
|
|
%tmp42 = getelementptr inbounds double, double* %arg13, i64 %tmp41
|
|
%tmp43 = load double, double* %tmp42, align 8
|
|
%tmp44 = insertelement <8 x double> undef, double %tmp43, i32 0
|
|
%tmp45 = shufflevector <8 x double> %tmp44, <8 x double> undef, <8 x i32> zeroinitializer
|
|
%tmp46 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> %tmp24, <8 x double> %tmp45, <8 x double> %tmp18)
|
|
%tmp47 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> %tmp28, <8 x double> %tmp45, <8 x double> %tmp19)
|
|
%tmp48 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> %tmp32, <8 x double> %tmp45, <8 x double> %tmp20)
|
|
%tmp49 = add nuw nsw i64 %tmp21, 1
|
|
%tmp50 = icmp eq i64 %tmp49, %arg12
|
|
br i1 %tmp50, label %bb51, label %bb15
|
|
|
|
bb51: ; preds = %bb15
|
|
store <8 x double> %tmp38, <8 x double>* %arg
|
|
store <8 x double> %tmp39, <8 x double>* %arg1
|
|
store <8 x double> %tmp40, <8 x double>* %arg2
|
|
store <8 x double> %tmp46, <8 x double>* %arg3
|
|
store <8 x double> %tmp47, <8 x double>* %arg4
|
|
store <8 x double> %tmp48, <8 x double>* %arg5
|
|
ret void
|
|
}
|
|
|
|
declare <8 x double> @llvm.fmuladd.v8f64(<8 x double>, <8 x double>, <8 x double>)
|