; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64-none-eabi -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-SD
; RUN: llc -mtriple=aarch64-none-eabi -global-isel -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-GI
define i8 @i8(i8 %a, i8 %b) {
; CHECK-LABEL: i8:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul w0, w0, w1
; CHECK-NEXT: ret
entry:
%s = mul i8 %a, %b
ret i8 %s
}
define i16 @i16(i16 %a, i16 %b) {
; CHECK-LABEL: i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul w0, w0, w1
; CHECK-NEXT: ret
entry:
%s = mul i16 %a, %b
ret i16 %s
}
define i32 @i32(i32 %a, i32 %b) {
; CHECK-LABEL: i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul w0, w0, w1
; CHECK-NEXT: ret
entry:
%s = mul i32 %a, %b
ret i32 %s
}
define i64 @i64(i64 %a, i64 %b) {
; CHECK-LABEL: i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul x0, x0, x1
; CHECK-NEXT: ret
entry:
%s = mul i64 %a, %b
ret i64 %s
}
define i128 @i128(i128 %a, i128 %b) {
; CHECK-SD-LABEL: i128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: umulh x8, x0, x2
; CHECK-SD-NEXT: madd x8, x0, x3, x8
; CHECK-SD-NEXT: mul x0, x0, x2
; CHECK-SD-NEXT: madd x1, x1, x2, x8
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: i128:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: mul x9, x0, x3
; CHECK-GI-NEXT: mul x8, x0, x2
; CHECK-GI-NEXT: umulh x10, x0, x2
; CHECK-GI-NEXT: madd x9, x1, x2, x9
; CHECK-GI-NEXT: mov x0, x8
; CHECK-GI-NEXT: add x1, x9, x10
; CHECK-GI-NEXT: ret
entry:
%s = mul i128 %a, %b
ret i128 %s
}
define void @v2i8(ptr %p1, ptr %p2) {
; CHECK-SD-LABEL: v2i8:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: ld1 { v0.b }[0], [x0]
; CHECK-SD-NEXT: ld1 { v1.b }[0], [x1]
; CHECK-SD-NEXT: add x8, x0, #1
; CHECK-SD-NEXT: add x9, x1, #1
; CHECK-SD-NEXT: ld1 { v0.b }[4], [x8]
; CHECK-SD-NEXT: ld1 { v1.b }[4], [x9]
; CHECK-SD-NEXT: mul v0.2s, v0.2s, v1.2s
; CHECK-SD-NEXT: mov w8, v0.s[1]
; CHECK-SD-NEXT: fmov w9, s0
; CHECK-SD-NEXT: strb w9, [x0]
; CHECK-SD-NEXT: strb w8, [x0, #1]
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v2i8:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ld1 { v0.b }[0], [x0]
; CHECK-GI-NEXT: ld1 { v1.b }[0], [x1]
; CHECK-GI-NEXT: ldr b2, [x0, #1]
; CHECK-GI-NEXT: ldr b3, [x1, #1]
; CHECK-GI-NEXT: mov v0.s[1], v2.s[0]
; CHECK-GI-NEXT: mov v1.s[1], v3.s[0]
; CHECK-GI-NEXT: mul v0.2s, v0.2s, v1.2s
; CHECK-GI-NEXT: mov s1, v0.s[1]
; CHECK-GI-NEXT: str b0, [x0]
; CHECK-GI-NEXT: str b1, [x0, #1]
; CHECK-GI-NEXT: ret
entry:
%d = load <2 x i8>, ptr %p1
%e = load <2 x i8>, ptr %p2
%s = mul <2 x i8> %d, %e
store <2 x i8> %s, ptr %p1
ret void
}
define void @v3i8(ptr %p1, ptr %p2) {
; CHECK-SD-LABEL: v3i8:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: sub sp, sp, #16
; CHECK-SD-NEXT: .cfi_def_cfa_offset 16
; CHECK-SD-NEXT: ldr s0, [x0]
; CHECK-SD-NEXT: ldr s1, [x1]
; CHECK-SD-NEXT: zip1 v0.8b, v0.8b, v0.8b
; CHECK-SD-NEXT: zip1 v1.8b, v1.8b, v0.8b
; CHECK-SD-NEXT: mul v0.4h, v0.4h, v1.4h
; CHECK-SD-NEXT: uzp1 v1.8b, v0.8b, v0.8b
; CHECK-SD-NEXT: umov w8, v0.h[2]
; CHECK-SD-NEXT: str s1, [sp, #12]
; CHECK-SD-NEXT: ldrh w9, [sp, #12]
; CHECK-SD-NEXT: strb w8, [x0, #2]
; CHECK-SD-NEXT: strh w9, [x0]
; CHECK-SD-NEXT: add sp, sp, #16
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v3i8:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ldrb w8, [x0]
; CHECK-GI-NEXT: ldrb w9, [x1]
; CHECK-GI-NEXT: ldrb w10, [x0, #1]
; CHECK-GI-NEXT: ldrb w11, [x1, #1]
; CHECK-GI-NEXT: fmov s0, w8
; CHECK-GI-NEXT: fmov s1, w9
; CHECK-GI-NEXT: ldrb w8, [x0, #2]
; CHECK-GI-NEXT: ldrb w9, [x1, #2]
; CHECK-GI-NEXT: mov v0.h[1], w10
; CHECK-GI-NEXT: mov v1.h[1], w11
; CHECK-GI-NEXT: mov v0.h[2], w8
; CHECK-GI-NEXT: mov v1.h[2], w9
; CHECK-GI-NEXT: mul v0.4h, v0.4h, v1.4h
; CHECK-GI-NEXT: mov h1, v0.h[1]
; CHECK-GI-NEXT: mov h2, v0.h[2]
; CHECK-GI-NEXT: str b0, [x0]
; CHECK-GI-NEXT: str b1, [x0, #1]
; CHECK-GI-NEXT: str b2, [x0, #2]
; CHECK-GI-NEXT: ret
entry:
%d = load <3 x i8>, ptr %p1
%e = load <3 x i8>, ptr %p2
%s = mul <3 x i8> %d, %e
store <3 x i8> %s, ptr %p1
ret void
}
define void @v4i8(ptr %p1, ptr %p2) {
; CHECK-SD-LABEL: v4i8:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: ldr s0, [x0]
; CHECK-SD-NEXT: ldr s1, [x1]
; CHECK-SD-NEXT: umull v0.8h, v0.8b, v1.8b
; CHECK-SD-NEXT: xtn v0.8b, v0.8h
; CHECK-SD-NEXT: str s0, [x0]
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v4i8:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ldr w8, [x0]
; CHECK-GI-NEXT: ldr w9, [x1]
; CHECK-GI-NEXT: fmov s0, w8
; CHECK-GI-NEXT: fmov s1, w9
; CHECK-GI-NEXT: mov b2, v0.b[1]
; CHECK-GI-NEXT: mov v3.b[0], v0.b[0]
; CHECK-GI-NEXT: mov b4, v1.b[1]
; CHECK-GI-NEXT: mov v5.b[0], v1.b[0]
; CHECK-GI-NEXT: mov v3.b[1], v2.b[0]
; CHECK-GI-NEXT: mov b2, v0.b[2]
; CHECK-GI-NEXT: mov b0, v0.b[3]
; CHECK-GI-NEXT: mov v5.b[1], v4.b[0]
; CHECK-GI-NEXT: mov b4, v1.b[2]
; CHECK-GI-NEXT: mov b1, v1.b[3]
; CHECK-GI-NEXT: mov v3.b[2], v2.b[0]
; CHECK-GI-NEXT: mov v5.b[2], v4.b[0]
; CHECK-GI-NEXT: mov v3.b[3], v0.b[0]
; CHECK-GI-NEXT: mov v5.b[3], v1.b[0]
; CHECK-GI-NEXT: ushll v0.8h, v3.8b, #0
; CHECK-GI-NEXT: ushll v1.8h, v5.8b, #0
; CHECK-GI-NEXT: mul v0.4h, v0.4h, v1.4h
; CHECK-GI-NEXT: mov v1.h[0], v0.h[0]
; CHECK-GI-NEXT: mov v1.h[1], v0.h[1]
; CHECK-GI-NEXT: mov v1.h[2], v0.h[2]
; CHECK-GI-NEXT: mov v1.h[3], v0.h[3]
; CHECK-GI-NEXT: xtn v0.8b, v1.8h
; CHECK-GI-NEXT: fmov w8, s0
; CHECK-GI-NEXT: str w8, [x0]
; CHECK-GI-NEXT: ret
entry:
%d = load <4 x i8>, ptr %p1
%e = load <4 x i8>, ptr %p2
%s = mul <4 x i8> %d, %e
store <4 x i8> %s, ptr %p1
ret void
}
define <8 x i8> @v8i8(<8 x i8> %d, <8 x i8> %e) {
; CHECK-LABEL: v8i8:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.8b, v0.8b, v1.8b
; CHECK-NEXT: ret
entry:
%s = mul <8 x i8> %d, %e
ret <8 x i8> %s
}
define <16 x i8> @v16i8(<16 x i8> %d, <16 x i8> %e) {
; CHECK-LABEL: v16i8:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%s = mul <16 x i8> %d, %e
ret <16 x i8> %s
}
define <32 x i8> @v32i8(<32 x i8> %d, <32 x i8> %e) {
; CHECK-SD-LABEL: v32i8:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: mul v1.16b, v1.16b, v3.16b
; CHECK-SD-NEXT: mul v0.16b, v0.16b, v2.16b
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v32i8:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: mul v0.16b, v0.16b, v2.16b
; CHECK-GI-NEXT: mul v1.16b, v1.16b, v3.16b
; CHECK-GI-NEXT: ret
entry:
%s = mul <32 x i8> %d, %e
ret <32 x i8> %s
}
define void @v2i16(ptr %p1, ptr %p2) {
; CHECK-SD-LABEL: v2i16:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: ld1 { v0.h }[0], [x0]
; CHECK-SD-NEXT: ld1 { v1.h }[0], [x1]
; CHECK-SD-NEXT: add x8, x0, #2
; CHECK-SD-NEXT: add x9, x1, #2
; CHECK-SD-NEXT: ld1 { v0.h }[2], [x8]
; CHECK-SD-NEXT: ld1 { v1.h }[2], [x9]
; CHECK-SD-NEXT: mul v0.2s, v0.2s, v1.2s
; CHECK-SD-NEXT: mov w8, v0.s[1]
; CHECK-SD-NEXT: fmov w9, s0
; CHECK-SD-NEXT: strh w9, [x0]
; CHECK-SD-NEXT: strh w8, [x0, #2]
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v2i16:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ldr h0, [x0]
; CHECK-GI-NEXT: ldr h1, [x1]
; CHECK-GI-NEXT: add x8, x0, #2
; CHECK-GI-NEXT: add x9, x1, #2
; CHECK-GI-NEXT: ld1 { v0.h }[1], [x8]
; CHECK-GI-NEXT: ld1 { v1.h }[1], [x9]
; CHECK-GI-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-GI-NEXT: ushll v1.4s, v1.4h, #0
; CHECK-GI-NEXT: mul v0.2s, v0.2s, v1.2s
; CHECK-GI-NEXT: mov s1, v0.s[1]
; CHECK-GI-NEXT: str h0, [x0]
; CHECK-GI-NEXT: str h1, [x0, #2]
; CHECK-GI-NEXT: ret
entry:
%d = load <2 x i16>, ptr %p1
%e = load <2 x i16>, ptr %p2
%s = mul <2 x i16> %d, %e
store <2 x i16> %s, ptr %p1
ret void
}
define void @v3i16(ptr %p1, ptr %p2) {
; CHECK-SD-LABEL: v3i16:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: ldr d0, [x0]
; CHECK-SD-NEXT: ldr d1, [x1]
; CHECK-SD-NEXT: add x8, x0, #4
; CHECK-SD-NEXT: mul v0.4h, v0.4h, v1.4h
; CHECK-SD-NEXT: st1 { v0.h }[2], [x8]
; CHECK-SD-NEXT: str s0, [x0]
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v3i16:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ldr h0, [x0]
; CHECK-GI-NEXT: ldr h1, [x1]
; CHECK-GI-NEXT: add x8, x0, #2
; CHECK-GI-NEXT: add x9, x1, #2
; CHECK-GI-NEXT: add x10, x1, #4
; CHECK-GI-NEXT: ld1 { v0.h }[1], [x8]
; CHECK-GI-NEXT: ld1 { v1.h }[1], [x9]
; CHECK-GI-NEXT: add x9, x0, #4
; CHECK-GI-NEXT: ld1 { v0.h }[2], [x9]
; CHECK-GI-NEXT: ld1 { v1.h }[2], [x10]
; CHECK-GI-NEXT: mul v0.4h, v0.4h, v1.4h
; CHECK-GI-NEXT: str h0, [x0]
; CHECK-GI-NEXT: st1 { v0.h }[1], [x8]
; CHECK-GI-NEXT: st1 { v0.h }[2], [x9]
; CHECK-GI-NEXT: ret
entry:
%d = load <3 x i16>, ptr %p1
%e = load <3 x i16>, ptr %p2
%s = mul <3 x i16> %d, %e
store <3 x i16> %s, ptr %p1
ret void
}
define <4 x i16> @v4i16(<4 x i16> %d, <4 x i16> %e) {
; CHECK-LABEL: v4i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.4h, v0.4h, v1.4h
; CHECK-NEXT: ret
entry:
%s = mul <4 x i16> %d, %e
ret <4 x i16> %s
}
define <8 x i16> @v8i16(<8 x i16> %d, <8 x i16> %e) {
; CHECK-LABEL: v8i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.8h, v0.8h, v1.8h
; CHECK-NEXT: ret
entry:
%s = mul <8 x i16> %d, %e
ret <8 x i16> %s
}
define <16 x i16> @v16i16(<16 x i16> %d, <16 x i16> %e) {
; CHECK-SD-LABEL: v16i16:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: mul v1.8h, v1.8h, v3.8h
; CHECK-SD-NEXT: mul v0.8h, v0.8h, v2.8h
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v16i16:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: mul v0.8h, v0.8h, v2.8h
; CHECK-GI-NEXT: mul v1.8h, v1.8h, v3.8h
; CHECK-GI-NEXT: ret
entry:
%s = mul <16 x i16> %d, %e
ret <16 x i16> %s
}
define <2 x i32> @v2i32(<2 x i32> %d, <2 x i32> %e) {
; CHECK-LABEL: v2i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.2s, v0.2s, v1.2s
; CHECK-NEXT: ret
entry:
%s = mul <2 x i32> %d, %e
ret <2 x i32> %s
}
define <3 x i32> @v3i32(<3 x i32> %d, <3 x i32> %e) {
; CHECK-LABEL: v3i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
entry:
%s = mul <3 x i32> %d, %e
ret <3 x i32> %s
}
define <4 x i32> @v4i32(<4 x i32> %d, <4 x i32> %e) {
; CHECK-LABEL: v4i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mul v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
entry:
%s = mul <4 x i32> %d, %e
ret <4 x i32> %s
}
define <8 x i32> @v8i32(<8 x i32> %d, <8 x i32> %e) {
; CHECK-SD-LABEL: v8i32:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: mul v1.4s, v1.4s, v3.4s
; CHECK-SD-NEXT: mul v0.4s, v0.4s, v2.4s
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v8i32:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: mul v0.4s, v0.4s, v2.4s
; CHECK-GI-NEXT: mul v1.4s, v1.4s, v3.4s
; CHECK-GI-NEXT: ret
entry:
%s = mul <8 x i32> %d, %e
ret <8 x i32> %s
}
define <2 x i64> @v2i64(<2 x i64> %d, <2 x i64> %e) {
; CHECK-SD-LABEL: v2i64:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: fmov x10, d1
; CHECK-SD-NEXT: fmov x11, d0
; CHECK-SD-NEXT: mov x8, v1.d[1]
; CHECK-SD-NEXT: mov x9, v0.d[1]
; CHECK-SD-NEXT: mul x10, x11, x10
; CHECK-SD-NEXT: mul x8, x9, x8
; CHECK-SD-NEXT: fmov d0, x10
; CHECK-SD-NEXT: mov v0.d[1], x8
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v2i64:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: fmov x8, d0
; CHECK-GI-NEXT: fmov x9, d1
; CHECK-GI-NEXT: mov x10, v0.d[1]
; CHECK-GI-NEXT: mov x11, v1.d[1]
; CHECK-GI-NEXT: mul x8, x8, x9
; CHECK-GI-NEXT: mul x9, x10, x11
; CHECK-GI-NEXT: mov v0.d[0], x8
; CHECK-GI-NEXT: mov v0.d[1], x9
; CHECK-GI-NEXT: ret
entry:
%s = mul <2 x i64> %d, %e
ret <2 x i64> %s
}
define <3 x i64> @v3i64(<3 x i64> %d, <3 x i64> %e) {
; CHECK-SD-LABEL: v3i64:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: // kill: def $d3 killed $d3 def $q3
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-SD-NEXT: fmov x8, d3
; CHECK-SD-NEXT: fmov x9, d0
; CHECK-SD-NEXT: // kill: def $d4 killed $d4 def $q4
; CHECK-SD-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-SD-NEXT: // kill: def $d5 killed $d5 def $q5
; CHECK-SD-NEXT: // kill: def $d2 killed $d2 def $q2
; CHECK-SD-NEXT: fmov x10, d1
; CHECK-SD-NEXT: fmov x11, d2
; CHECK-SD-NEXT: mul x8, x9, x8
; CHECK-SD-NEXT: fmov x9, d4
; CHECK-SD-NEXT: mul x9, x10, x9
; CHECK-SD-NEXT: fmov x10, d5
; CHECK-SD-NEXT: fmov d0, x8
; CHECK-SD-NEXT: mul x10, x11, x10
; CHECK-SD-NEXT: fmov d1, x9
; CHECK-SD-NEXT: fmov d2, x10
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v3i64:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-GI-NEXT: // kill: def $d3 killed $d3 def $q3
; CHECK-GI-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-GI-NEXT: // kill: def $d4 killed $d4 def $q4
; CHECK-GI-NEXT: mov v0.d[1], v1.d[0]
; CHECK-GI-NEXT: mov v3.d[1], v4.d[0]
; CHECK-GI-NEXT: fmov x8, d0
; CHECK-GI-NEXT: fmov x9, d3
; CHECK-GI-NEXT: mov x10, v0.d[1]
; CHECK-GI-NEXT: mov x11, v3.d[1]
; CHECK-GI-NEXT: mul x8, x8, x9
; CHECK-GI-NEXT: mul x9, x10, x11
; CHECK-GI-NEXT: mov v0.d[0], x8
; CHECK-GI-NEXT: fmov x8, d2
; CHECK-GI-NEXT: mov v0.d[1], x9
; CHECK-GI-NEXT: fmov x9, d5
; CHECK-GI-NEXT: mul x8, x8, x9
; CHECK-GI-NEXT: mov d1, v0.d[1]
; CHECK-GI-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-GI-NEXT: fmov d2, x8
; CHECK-GI-NEXT: ret
entry:
%s = mul <3 x i64> %d, %e
ret <3 x i64> %s
}
define <4 x i64> @v4i64(<4 x i64> %d, <4 x i64> %e) {
; CHECK-SD-LABEL: v4i64:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: fmov x8, d2
; CHECK-SD-NEXT: fmov x9, d0
; CHECK-SD-NEXT: fmov x12, d1
; CHECK-SD-NEXT: mov x10, v2.d[1]
; CHECK-SD-NEXT: mov x11, v0.d[1]
; CHECK-SD-NEXT: mov x13, v3.d[1]
; CHECK-SD-NEXT: mov x14, v1.d[1]
; CHECK-SD-NEXT: mul x8, x9, x8
; CHECK-SD-NEXT: fmov x9, d3
; CHECK-SD-NEXT: mul x10, x11, x10
; CHECK-SD-NEXT: mul x9, x12, x9
; CHECK-SD-NEXT: fmov d0, x8
; CHECK-SD-NEXT: mul x11, x14, x13
; CHECK-SD-NEXT: mov v0.d[1], x10
; CHECK-SD-NEXT: fmov d1, x9
; CHECK-SD-NEXT: mov v1.d[1], x11
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v4i64:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: fmov x8, d0
; CHECK-GI-NEXT: fmov x9, d2
; CHECK-GI-NEXT: fmov x12, d3
; CHECK-GI-NEXT: mov x10, v0.d[1]
; CHECK-GI-NEXT: mov x11, v2.d[1]
; CHECK-GI-NEXT: mov x13, v1.d[1]
; CHECK-GI-NEXT: mov x14, v3.d[1]
; CHECK-GI-NEXT: mul x8, x8, x9
; CHECK-GI-NEXT: fmov x9, d1
; CHECK-GI-NEXT: mul x10, x10, x11
; CHECK-GI-NEXT: mul x9, x9, x12
; CHECK-GI-NEXT: mov v0.d[0], x8
; CHECK-GI-NEXT: mul x11, x13, x14
; CHECK-GI-NEXT: mov v1.d[0], x9
; CHECK-GI-NEXT: mov v0.d[1], x10
; CHECK-GI-NEXT: mov v1.d[1], x11
; CHECK-GI-NEXT: ret
entry:
%s = mul <4 x i64> %d, %e
ret <4 x i64> %s
}
define <2 x i128> @v2i128(<2 x i128> %d, <2 x i128> %e) {
; CHECK-SD-LABEL: v2i128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: umulh x8, x2, x6
; CHECK-SD-NEXT: umulh x9, x0, x4
; CHECK-SD-NEXT: madd x8, x2, x7, x8
; CHECK-SD-NEXT: madd x9, x0, x5, x9
; CHECK-SD-NEXT: madd x3, x3, x6, x8
; CHECK-SD-NEXT: madd x1, x1, x4, x9
; CHECK-SD-NEXT: mul x0, x0, x4
; CHECK-SD-NEXT: mul x2, x2, x6
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v2i128:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: mul x9, x0, x5
; CHECK-GI-NEXT: mul x12, x2, x7
; CHECK-GI-NEXT: mul x8, x0, x4
; CHECK-GI-NEXT: umulh x10, x0, x4
; CHECK-GI-NEXT: madd x11, x1, x4, x9
; CHECK-GI-NEXT: mov x0, x8
; CHECK-GI-NEXT: mul x9, x2, x6
; CHECK-GI-NEXT: umulh x13, x2, x6
; CHECK-GI-NEXT: add x1, x11, x10
; CHECK-GI-NEXT: madd x12, x3, x6, x12
; CHECK-GI-NEXT: mov x2, x9
; CHECK-GI-NEXT: add x3, x12, x13
; CHECK-GI-NEXT: ret
entry:
%s = mul <2 x i128> %d, %e
ret <2 x i128> %s
}
define <3 x i128> @v3i128(<3 x i128> %d, <3 x i128> %e) {
; CHECK-SD-LABEL: v3i128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: umulh x9, x0, x6
; CHECK-SD-NEXT: ldp x8, x10, [sp]
; CHECK-SD-NEXT: madd x9, x0, x7, x9
; CHECK-SD-NEXT: umulh x11, x2, x8
; CHECK-SD-NEXT: madd x1, x1, x6, x9
; CHECK-SD-NEXT: ldp x9, x12, [sp, #16]
; CHECK-SD-NEXT: madd x10, x2, x10, x11
; CHECK-SD-NEXT: umulh x13, x4, x9
; CHECK-SD-NEXT: madd x3, x3, x8, x10
; CHECK-SD-NEXT: madd x11, x4, x12, x13
; CHECK-SD-NEXT: mul x0, x0, x6
; CHECK-SD-NEXT: madd x5, x5, x9, x11
; CHECK-SD-NEXT: mul x2, x2, x8
; CHECK-SD-NEXT: mul x4, x4, x9
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v3i128:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ldp x10, x13, [sp]
; CHECK-GI-NEXT: mul x9, x0, x7
; CHECK-GI-NEXT: mul x8, x0, x6
; CHECK-GI-NEXT: mul x13, x2, x13
; CHECK-GI-NEXT: madd x12, x1, x6, x9
; CHECK-GI-NEXT: mul x9, x2, x10
; CHECK-GI-NEXT: umulh x14, x2, x10
; CHECK-GI-NEXT: madd x10, x3, x10, x13
; CHECK-GI-NEXT: ldp x13, x15, [sp, #16]
; CHECK-GI-NEXT: mov x2, x9
; CHECK-GI-NEXT: umulh x11, x0, x6
; CHECK-GI-NEXT: mov x0, x8
; CHECK-GI-NEXT: mul x15, x4, x15
; CHECK-GI-NEXT: add x3, x10, x14
; CHECK-GI-NEXT: umulh x16, x4, x13
; CHECK-GI-NEXT: add x1, x12, x11
; CHECK-GI-NEXT: madd x15, x5, x13, x15
; CHECK-GI-NEXT: mul x4, x4, x13
; CHECK-GI-NEXT: add x5, x15, x16
; CHECK-GI-NEXT: ret
entry:
%s = mul <3 x i128> %d, %e
ret <3 x i128> %s
}
define <4 x i128> @v4i128(<4 x i128> %d, <4 x i128> %e) {
; CHECK-SD-LABEL: v4i128:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: ldp x8, x9, [sp]
; CHECK-SD-NEXT: ldp x11, x12, [sp, #16]
; CHECK-SD-NEXT: umulh x10, x0, x8
; CHECK-SD-NEXT: umulh x13, x2, x11
; CHECK-SD-NEXT: madd x9, x0, x9, x10
; CHECK-SD-NEXT: madd x10, x2, x12, x13
; CHECK-SD-NEXT: ldp x13, x14, [sp, #48]
; CHECK-SD-NEXT: madd x1, x1, x8, x9
; CHECK-SD-NEXT: madd x3, x3, x11, x10
; CHECK-SD-NEXT: ldp x9, x10, [sp, #32]
; CHECK-SD-NEXT: umulh x15, x6, x13
; CHECK-SD-NEXT: umulh x12, x4, x9
; CHECK-SD-NEXT: mul x0, x0, x8
; CHECK-SD-NEXT: madd x10, x4, x10, x12
; CHECK-SD-NEXT: madd x12, x6, x14, x15
; CHECK-SD-NEXT: madd x5, x5, x9, x10
; CHECK-SD-NEXT: madd x7, x7, x13, x12
; CHECK-SD-NEXT: mul x2, x2, x11
; CHECK-SD-NEXT: mul x4, x4, x9
; CHECK-SD-NEXT: mul x6, x6, x13
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: v4i128:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: ldp x9, x10, [sp]
; CHECK-GI-NEXT: ldp x15, x16, [sp, #32]
; CHECK-GI-NEXT: mul x10, x0, x10
; CHECK-GI-NEXT: mul x16, x4, x16
; CHECK-GI-NEXT: madd x12, x1, x9, x10
; CHECK-GI-NEXT: ldp x10, x13, [sp, #16]
; CHECK-GI-NEXT: mul x8, x0, x9
; CHECK-GI-NEXT: mul x13, x2, x13
; CHECK-GI-NEXT: umulh x11, x0, x9
; CHECK-GI-NEXT: mul x9, x2, x10
; CHECK-GI-NEXT: umulh x14, x2, x10
; CHECK-GI-NEXT: add x1, x12, x11
; CHECK-GI-NEXT: madd x13, x3, x10, x13
; CHECK-GI-NEXT: mov x2, x9
; CHECK-GI-NEXT: mul x10, x4, x15
; CHECK-GI-NEXT: umulh x17, x4, x15
; CHECK-GI-NEXT: add x3, x13, x14
; CHECK-GI-NEXT: madd x15, x5, x15, x16
; CHECK-GI-NEXT: ldp x16, x18, [sp, #48]
; CHECK-GI-NEXT: mov x4, x10
; CHECK-GI-NEXT: mul x18, x6, x18
; CHECK-GI-NEXT: umulh x0, x6, x16
; CHECK-GI-NEXT: add x5, x15, x17
; CHECK-GI-NEXT: madd x18, x7, x16, x18
; CHECK-GI-NEXT: mul x6, x6, x16
; CHECK-GI-NEXT: add x7, x18, x0
; CHECK-GI-NEXT: mov x0, x8
; CHECK-GI-NEXT: ret
entry:
%s = mul <4 x i128> %d, %e
ret <4 x i128> %s
}
Codebase Browser
llvm