; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
; RUN: llc -mtriple=aarch64 -verify-machineinstrs < %s -o - | FileCheck %s
;; This test exercises the default lowering of the histogram to scalarized code.
define void @histogram_i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask) {
; CHECK-LABEL: histogram_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT: fmov w8, s1
; CHECK-NEXT: tbnz w8, #0, .LBB0_3
; CHECK-NEXT: // %bb.1: // %else
; CHECK-NEXT: mov w8, v1.s[1]
; CHECK-NEXT: tbnz w8, #0, .LBB0_4
; CHECK-NEXT: .LBB0_2: // %else2
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB0_3: // %cond.histogram.update
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: ldr x9, [x8]
; CHECK-NEXT: add x9, x9, x0
; CHECK-NEXT: str x9, [x8]
; CHECK-NEXT: mov w8, v1.s[1]
; CHECK-NEXT: tbz w8, #0, .LBB0_2
; CHECK-NEXT: .LBB0_4: // %cond.histogram.update1
; CHECK-NEXT: mov x8, v0.d[1]
; CHECK-NEXT: ldr x9, [x8]
; CHECK-NEXT: add x9, x9, x0
; CHECK-NEXT: str x9, [x8]
; CHECK-NEXT: ret
call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<2 x ptr> %buckets, i64 %inc, <2 x i1> %mask)
ret void
}
define void @histogram_i32_literal(ptr %base, <4 x i32> %indices, <4 x i1> %mask) {
; CHECK-LABEL: histogram_i32_literal:
; CHECK: // %bb.0:
; CHECK-NEXT: dup v2.2d, x0
; CHECK-NEXT: sshll v3.2d, v0.2s, #2
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT: umov w8, v1.h[0]
; CHECK-NEXT: add v3.2d, v2.2d, v3.2d
; CHECK-NEXT: tbz w8, #0, .LBB1_2
; CHECK-NEXT: // %bb.1: // %cond.histogram.update
; CHECK-NEXT: fmov x8, d3
; CHECK-NEXT: ldr w9, [x8]
; CHECK-NEXT: add w9, w9, #1
; CHECK-NEXT: str w9, [x8]
; CHECK-NEXT: .LBB1_2: // %else
; CHECK-NEXT: umov w8, v1.h[1]
; CHECK-NEXT: sshll2 v0.2d, v0.4s, #2
; CHECK-NEXT: tbz w8, #0, .LBB1_4
; CHECK-NEXT: // %bb.3: // %cond.histogram.update1
; CHECK-NEXT: mov x8, v3.d[1]
; CHECK-NEXT: ldr w9, [x8]
; CHECK-NEXT: add w9, w9, #1
; CHECK-NEXT: str w9, [x8]
; CHECK-NEXT: .LBB1_4: // %else2
; CHECK-NEXT: umov w8, v1.h[2]
; CHECK-NEXT: add v0.2d, v2.2d, v0.2d
; CHECK-NEXT: tbnz w8, #0, .LBB1_7
; CHECK-NEXT: // %bb.5: // %else4
; CHECK-NEXT: umov w8, v1.h[3]
; CHECK-NEXT: tbnz w8, #0, .LBB1_8
; CHECK-NEXT: .LBB1_6: // %else6
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB1_7: // %cond.histogram.update3
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: ldr w9, [x8]
; CHECK-NEXT: add w9, w9, #1
; CHECK-NEXT: str w9, [x8]
; CHECK-NEXT: umov w8, v1.h[3]
; CHECK-NEXT: tbz w8, #0, .LBB1_6
; CHECK-NEXT: .LBB1_8: // %cond.histogram.update5
; CHECK-NEXT: mov x8, v0.d[1]
; CHECK-NEXT: ldr w9, [x8]
; CHECK-NEXT: add w9, w9, #1
; CHECK-NEXT: str w9, [x8]
; CHECK-NEXT: ret
%buckets = getelementptr i32, ptr %base, <4 x i32> %indices
call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
ret void
}
define void @histogram_i32_literal_alltruemask(ptr %base, <4 x i32> %indices) {
; CHECK-LABEL: histogram_i32_literal_alltruemask:
; CHECK: // %bb.0:
; CHECK-NEXT: dup v1.2d, x0
; CHECK-NEXT: sshll v2.2d, v0.2s, #2
; CHECK-NEXT: sshll2 v0.2d, v0.4s, #2
; CHECK-NEXT: add v2.2d, v1.2d, v2.2d
; CHECK-NEXT: add v0.2d, v1.2d, v0.2d
; CHECK-NEXT: fmov x8, d2
; CHECK-NEXT: mov x9, v2.d[1]
; CHECK-NEXT: ldr w10, [x8]
; CHECK-NEXT: add w10, w10, #1
; CHECK-NEXT: str w10, [x8]
; CHECK-NEXT: ldr w8, [x9]
; CHECK-NEXT: add w8, w8, #1
; CHECK-NEXT: str w8, [x9]
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: mov x9, v0.d[1]
; CHECK-NEXT: ldr w10, [x8]
; CHECK-NEXT: add w10, w10, #1
; CHECK-NEXT: str w10, [x8]
; CHECK-NEXT: ldr w8, [x9]
; CHECK-NEXT: add w8, w8, #1
; CHECK-NEXT: str w8, [x9]
; CHECK-NEXT: ret
%buckets = getelementptr i32, ptr %base, <4 x i32> %indices
call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
ret void
}
Codebase Browser
llvm