forked from OSchip/llvm-project
[X86] Add broadcast load unfold tests for VCMPPS/PD.
llvm-svn: 371486
This commit is contained in:
Craig Topper
parent
a6e5a7b637
commit
7c2fdf2779
|
|
@ -4222,3 +4222,224 @@ bb1: ; preds = %bb1, %bb
|
|||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @bcast_unfold_cmp_v4f32(float* %arg) {
|
||||
; CHECK-LABEL: bcast_unfold_cmp_v4f32:
|
||||
; CHECK: # %bb.0: # %bb
|
||||
; CHECK-NEXT: movq $-4096, %rax # imm = 0xF000
|
||||
; CHECK-NEXT: vbroadcastss {{.*#+}} xmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB120_1: # %bb1
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: vmovups 4096(%rdi,%rax), %xmm1
|
||||
; CHECK-NEXT: vcmpltps {{.*}}(%rip){1to4}, %xmm1, %k1
|
||||
; CHECK-NEXT: vblendmps %xmm1, %xmm0, %xmm1 {%k1}
|
||||
; CHECK-NEXT: vmovups %xmm1, 4096(%rdi,%rax)
|
||||
; CHECK-NEXT: addq $16, %rax
|
||||
; CHECK-NEXT: jne .LBB120_1
|
||||
; CHECK-NEXT: # %bb.2: # %bb10
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
br label %bb1
|
||||
|
||||
bb1: ; preds = %bb1, %bb
|
||||
%tmp = phi i64 [ 0, %bb ], [ %tmp8, %bb1 ]
|
||||
%tmp2 = getelementptr inbounds float, float* %arg, i64 %tmp
|
||||
%tmp3 = bitcast float* %tmp2 to <4 x float>*
|
||||
%tmp4 = load <4 x float>, <4 x float>* %tmp3, align 4
|
||||
%tmp5 = fcmp olt <4 x float> %tmp4, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
|
||||
%tmp6 = select <4 x i1> %tmp5, <4 x float> %tmp4, <4 x float> <float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00>
|
||||
%tmp7 = bitcast float* %tmp2 to <4 x float>*
|
||||
store <4 x float> %tmp6, <4 x float>* %tmp7, align 4
|
||||
%tmp8 = add i64 %tmp, 4
|
||||
%tmp9 = icmp eq i64 %tmp8, 1024
|
||||
br i1 %tmp9, label %bb10, label %bb1
|
||||
|
||||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @bcast_unfold_cmp_v8f32(float* %arg) {
|
||||
; CHECK-LABEL: bcast_unfold_cmp_v8f32:
|
||||
; CHECK: # %bb.0: # %bb
|
||||
; CHECK-NEXT: movq $-4096, %rax # imm = 0xF000
|
||||
; CHECK-NEXT: vbroadcastss {{.*#+}} ymm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB121_1: # %bb1
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: vmovups 4096(%rdi,%rax), %ymm1
|
||||
; CHECK-NEXT: vcmpltps {{.*}}(%rip){1to8}, %ymm1, %k1
|
||||
; CHECK-NEXT: vblendmps %ymm1, %ymm0, %ymm1 {%k1}
|
||||
; CHECK-NEXT: vmovups %ymm1, 4096(%rdi,%rax)
|
||||
; CHECK-NEXT: addq $32, %rax
|
||||
; CHECK-NEXT: jne .LBB121_1
|
||||
; CHECK-NEXT: # %bb.2: # %bb10
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
br label %bb1
|
||||
|
||||
bb1: ; preds = %bb1, %bb
|
||||
%tmp = phi i64 [ 0, %bb ], [ %tmp8, %bb1 ]
|
||||
%tmp2 = getelementptr inbounds float, float* %arg, i64 %tmp
|
||||
%tmp3 = bitcast float* %tmp2 to <8 x float>*
|
||||
%tmp4 = load <8 x float>, <8 x float>* %tmp3, align 4
|
||||
%tmp5 = fcmp olt <8 x float> %tmp4, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
|
||||
%tmp6 = select <8 x i1> %tmp5, <8 x float> %tmp4, <8 x float> <float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00>
|
||||
%tmp7 = bitcast float* %tmp2 to <8 x float>*
|
||||
store <8 x float> %tmp6, <8 x float>* %tmp7, align 4
|
||||
%tmp8 = add i64 %tmp, 8
|
||||
%tmp9 = icmp eq i64 %tmp8, 1024
|
||||
br i1 %tmp9, label %bb10, label %bb1
|
||||
|
||||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @bcast_unfold_cmp_v16f32(float* %arg) {
|
||||
; CHECK-LABEL: bcast_unfold_cmp_v16f32:
|
||||
; CHECK: # %bb.0: # %bb
|
||||
; CHECK-NEXT: movq $-4096, %rax # imm = 0xF000
|
||||
; CHECK-NEXT: vbroadcastss {{.*#+}} zmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB122_1: # %bb1
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: vmovups 4096(%rdi,%rax), %zmm1
|
||||
; CHECK-NEXT: vcmpltps {{.*}}(%rip){1to16}, %zmm1, %k1
|
||||
; CHECK-NEXT: vblendmps %zmm1, %zmm0, %zmm1 {%k1}
|
||||
; CHECK-NEXT: vmovups %zmm1, 4096(%rdi,%rax)
|
||||
; CHECK-NEXT: addq $64, %rax
|
||||
; CHECK-NEXT: jne .LBB122_1
|
||||
; CHECK-NEXT: # %bb.2: # %bb10
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
br label %bb1
|
||||
|
||||
bb1: ; preds = %bb1, %bb
|
||||
%tmp = phi i64 [ 0, %bb ], [ %tmp8, %bb1 ]
|
||||
%tmp2 = getelementptr inbounds float, float* %arg, i64 %tmp
|
||||
%tmp3 = bitcast float* %tmp2 to <16 x float>*
|
||||
%tmp4 = load <16 x float>, <16 x float>* %tmp3, align 4
|
||||
%tmp5 = fcmp olt <16 x float> %tmp4, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
|
||||
%tmp6 = select <16 x i1> %tmp5, <16 x float> %tmp4, <16 x float> <float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00, float 3.000000e+00>
|
||||
%tmp7 = bitcast float* %tmp2 to <16 x float>*
|
||||
store <16 x float> %tmp6, <16 x float>* %tmp7, align 4
|
||||
%tmp8 = add i64 %tmp, 16
|
||||
%tmp9 = icmp eq i64 %tmp8, 1024
|
||||
br i1 %tmp9, label %bb10, label %bb1
|
||||
|
||||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @bcast_unfold_cmp_v2f64(double* %arg) {
|
||||
; CHECK-LABEL: bcast_unfold_cmp_v2f64:
|
||||
; CHECK: # %bb.0: # %bb
|
||||
; CHECK-NEXT: movq $-8192, %rax # imm = 0xE000
|
||||
; CHECK-NEXT: vmovapd {{.*#+}} xmm0 = [2.0E+0,2.0E+0]
|
||||
; CHECK-NEXT: vmovapd {{.*#+}} xmm1 = [3.0E+0,3.0E+0]
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB123_1: # %bb1
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: vmovupd 8192(%rdi,%rax), %xmm2
|
||||
; CHECK-NEXT: vcmpltpd %xmm0, %xmm2, %k1
|
||||
; CHECK-NEXT: vblendmpd %xmm2, %xmm1, %xmm2 {%k1}
|
||||
; CHECK-NEXT: vmovupd %xmm2, 8192(%rdi,%rax)
|
||||
; CHECK-NEXT: addq $16, %rax
|
||||
; CHECK-NEXT: jne .LBB123_1
|
||||
; CHECK-NEXT: # %bb.2: # %bb10
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
br label %bb1
|
||||
|
||||
bb1: ; preds = %bb1, %bb
|
||||
%tmp = phi i64 [ 0, %bb ], [ %tmp8, %bb1 ]
|
||||
%tmp2 = getelementptr inbounds double, double* %arg, i64 %tmp
|
||||
%tmp3 = bitcast double* %tmp2 to <2 x double>*
|
||||
%tmp4 = load <2 x double>, <2 x double>* %tmp3, align 8
|
||||
%tmp5 = fcmp olt <2 x double> %tmp4, <double 2.000000e+00, double 2.000000e+00>
|
||||
%tmp6 = select <2 x i1> %tmp5, <2 x double> %tmp4, <2 x double> <double 3.000000e+00, double 3.000000e+00>
|
||||
%tmp7 = bitcast double* %tmp2 to <2 x double>*
|
||||
store <2 x double> %tmp6, <2 x double>* %tmp7, align 8
|
||||
%tmp8 = add i64 %tmp, 2
|
||||
%tmp9 = icmp eq i64 %tmp8, 1024
|
||||
br i1 %tmp9, label %bb10, label %bb1
|
||||
|
||||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @bcast_unfold_cmp_v4f64(double* %arg) {
|
||||
; CHECK-LABEL: bcast_unfold_cmp_v4f64:
|
||||
; CHECK: # %bb.0: # %bb
|
||||
; CHECK-NEXT: movq $-8192, %rax # imm = 0xE000
|
||||
; CHECK-NEXT: vbroadcastsd {{.*#+}} ymm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB124_1: # %bb1
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: vmovupd 8192(%rdi,%rax), %ymm1
|
||||
; CHECK-NEXT: vcmpltpd {{.*}}(%rip){1to4}, %ymm1, %k1
|
||||
; CHECK-NEXT: vblendmpd %ymm1, %ymm0, %ymm1 {%k1}
|
||||
; CHECK-NEXT: vmovupd %ymm1, 8192(%rdi,%rax)
|
||||
; CHECK-NEXT: addq $32, %rax
|
||||
; CHECK-NEXT: jne .LBB124_1
|
||||
; CHECK-NEXT: # %bb.2: # %bb10
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
br label %bb1
|
||||
|
||||
bb1: ; preds = %bb1, %bb
|
||||
%tmp = phi i64 [ 0, %bb ], [ %tmp8, %bb1 ]
|
||||
%tmp2 = getelementptr inbounds double, double* %arg, i64 %tmp
|
||||
%tmp3 = bitcast double* %tmp2 to <4 x double>*
|
||||
%tmp4 = load <4 x double>, <4 x double>* %tmp3, align 8
|
||||
%tmp5 = fcmp olt <4 x double> %tmp4, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
|
||||
%tmp6 = select <4 x i1> %tmp5, <4 x double> %tmp4, <4 x double> <double 3.000000e+00, double 3.000000e+00, double 3.000000e+00, double 3.000000e+00>
|
||||
%tmp7 = bitcast double* %tmp2 to <4 x double>*
|
||||
store <4 x double> %tmp6, <4 x double>* %tmp7, align 8
|
||||
%tmp8 = add i64 %tmp, 4
|
||||
%tmp9 = icmp eq i64 %tmp8, 1024
|
||||
br i1 %tmp9, label %bb10, label %bb1
|
||||
|
||||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @bcast_unfold_cmp_v8f64(double* %arg) {
|
||||
; CHECK-LABEL: bcast_unfold_cmp_v8f64:
|
||||
; CHECK: # %bb.0: # %bb
|
||||
; CHECK-NEXT: movq $-8192, %rax # imm = 0xE000
|
||||
; CHECK-NEXT: vbroadcastsd {{.*#+}} zmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB125_1: # %bb1
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: vmovupd 8192(%rdi,%rax), %zmm1
|
||||
; CHECK-NEXT: vcmpltpd {{.*}}(%rip){1to8}, %zmm1, %k1
|
||||
; CHECK-NEXT: vblendmpd %zmm1, %zmm0, %zmm1 {%k1}
|
||||
; CHECK-NEXT: vmovupd %zmm1, 8192(%rdi,%rax)
|
||||
; CHECK-NEXT: addq $64, %rax
|
||||
; CHECK-NEXT: jne .LBB125_1
|
||||
; CHECK-NEXT: # %bb.2: # %bb10
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
br label %bb1
|
||||
|
||||
bb1: ; preds = %bb1, %bb
|
||||
%tmp = phi i64 [ 0, %bb ], [ %tmp8, %bb1 ]
|
||||
%tmp2 = getelementptr inbounds double, double* %arg, i64 %tmp
|
||||
%tmp3 = bitcast double* %tmp2 to <8 x double>*
|
||||
%tmp4 = load <8 x double>, <8 x double>* %tmp3, align 8
|
||||
%tmp5 = fcmp olt <8 x double> %tmp4, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00>
|
||||
%tmp6 = select <8 x i1> %tmp5, <8 x double> %tmp4, <8 x double> <double 3.000000e+00, double 3.000000e+00, double 3.000000e+00, double 3.000000e+00, double 3.000000e+00, double 3.000000e+00, double 3.000000e+00, double 3.000000e+00>
|
||||
%tmp7 = bitcast double* %tmp2 to <8 x double>*
|
||||
store <8 x double> %tmp6, <8 x double>* %tmp7, align 8
|
||||
%tmp8 = add i64 %tmp, 8
|
||||
%tmp9 = icmp eq i64 %tmp8, 1024
|
||||
br i1 %tmp9, label %bb10, label %bb1
|
||||
|
||||
bb10: ; preds = %bb1
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue