| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc -aarch64-sve-vector-bits-min=256 < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_256 |
| ; RUN: llc -aarch64-sve-vector-bits-min=512 < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512 |
| ; RUN: llc -aarch64-sve-vector-bits-min=2048 < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512 |
| |
| target triple = "aarch64-unknown-linux-gnu" |
| |
| ; |
| ; CLZ |
| ; |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <8 x i8> @ctlz_v8i8(<8 x i8> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v8i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: clz v0.8b, v0.8b |
| ; CHECK-NEXT: ret |
| %res = call <8 x i8> @llvm.ctlz.v8i8(<8 x i8> %op) |
| ret <8 x i8> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <16 x i8> @ctlz_v16i8(<16 x i8> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v16i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: clz v0.16b, v0.16b |
| ; CHECK-NEXT: ret |
| %res = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> %op) |
| ret <16 x i8> %res |
| } |
| |
| define void @ctlz_v32i8(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v32i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl32 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i8>, ptr %a |
| %res = call <32 x i8> @llvm.ctlz.v32i8(<32 x i8> %op) |
| store <32 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v64i8(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctlz_v64i8: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.b, vl32 |
| ; VBITS_GE_256-NEXT: mov w8, #32 // =0x20 |
| ; VBITS_GE_256-NEXT: ld1b { z0.b }, p0/z, [x0, x8] |
| ; VBITS_GE_256-NEXT: ld1b { z1.b }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: clz z0.b, p0/m, z0.b |
| ; VBITS_GE_256-NEXT: clz z1.b, p0/m, z1.b |
| ; VBITS_GE_256-NEXT: st1b { z0.b }, p0, [x0, x8] |
| ; VBITS_GE_256-NEXT: st1b { z1.b }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctlz_v64i8: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.b, vl64 |
| ; VBITS_GE_512-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: clz z0.b, p0/m, z0.b |
| ; VBITS_GE_512-NEXT: st1b { z0.b }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <64 x i8>, ptr %a |
| %res = call <64 x i8> @llvm.ctlz.v64i8(<64 x i8> %op) |
| store <64 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v128i8(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctlz_v128i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl128 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <128 x i8>, ptr %a |
| %res = call <128 x i8> @llvm.ctlz.v128i8(<128 x i8> %op) |
| store <128 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v256i8(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctlz_v256i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl256 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <256 x i8>, ptr %a |
| %res = call <256 x i8> @llvm.ctlz.v256i8(<256 x i8> %op) |
| store <256 x i8> %res, ptr %a |
| ret void |
| } |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <4 x i16> @ctlz_v4i16(<4 x i16> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v4i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: clz v0.4h, v0.4h |
| ; CHECK-NEXT: ret |
| %res = call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> %op) |
| ret <4 x i16> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <8 x i16> @ctlz_v8i16(<8 x i16> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v8i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: clz v0.8h, v0.8h |
| ; CHECK-NEXT: ret |
| %res = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> %op) |
| ret <8 x i16> %res |
| } |
| |
| define void @ctlz_v16i16(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v16i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl16 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <16 x i16>, ptr %a |
| %res = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> %op) |
| store <16 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v32i16(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctlz_v32i16: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.h, vl16 |
| ; VBITS_GE_256-NEXT: mov x8, #16 // =0x10 |
| ; VBITS_GE_256-NEXT: ld1h { z0.h }, p0/z, [x0, x8, lsl #1] |
| ; VBITS_GE_256-NEXT: ld1h { z1.h }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: clz z0.h, p0/m, z0.h |
| ; VBITS_GE_256-NEXT: clz z1.h, p0/m, z1.h |
| ; VBITS_GE_256-NEXT: st1h { z0.h }, p0, [x0, x8, lsl #1] |
| ; VBITS_GE_256-NEXT: st1h { z1.h }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctlz_v32i16: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.h, vl32 |
| ; VBITS_GE_512-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: clz z0.h, p0/m, z0.h |
| ; VBITS_GE_512-NEXT: st1h { z0.h }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <32 x i16>, ptr %a |
| %res = call <32 x i16> @llvm.ctlz.v32i16(<32 x i16> %op) |
| store <32 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v64i16(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctlz_v64i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl64 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <64 x i16>, ptr %a |
| %res = call <64 x i16> @llvm.ctlz.v64i16(<64 x i16> %op) |
| store <64 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v128i16(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctlz_v128i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl128 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <128 x i16>, ptr %a |
| %res = call <128 x i16> @llvm.ctlz.v128i16(<128 x i16> %op) |
| store <128 x i16> %res, ptr %a |
| ret void |
| } |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <2 x i32> @ctlz_v2i32(<2 x i32> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v2i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: clz v0.2s, v0.2s |
| ; CHECK-NEXT: ret |
| %res = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> %op) |
| ret <2 x i32> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <4 x i32> @ctlz_v4i32(<4 x i32> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v4i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: clz v0.4s, v0.4s |
| ; CHECK-NEXT: ret |
| %res = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> %op) |
| ret <4 x i32> %res |
| } |
| |
| define void @ctlz_v8i32(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v8i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl8 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <8 x i32>, ptr %a |
| %res = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> %op) |
| store <8 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v16i32(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctlz_v16i32: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.s, vl8 |
| ; VBITS_GE_256-NEXT: mov x8, #8 // =0x8 |
| ; VBITS_GE_256-NEXT: ld1w { z0.s }, p0/z, [x0, x8, lsl #2] |
| ; VBITS_GE_256-NEXT: ld1w { z1.s }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: clz z0.s, p0/m, z0.s |
| ; VBITS_GE_256-NEXT: clz z1.s, p0/m, z1.s |
| ; VBITS_GE_256-NEXT: st1w { z0.s }, p0, [x0, x8, lsl #2] |
| ; VBITS_GE_256-NEXT: st1w { z1.s }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctlz_v16i32: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.s, vl16 |
| ; VBITS_GE_512-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: clz z0.s, p0/m, z0.s |
| ; VBITS_GE_512-NEXT: st1w { z0.s }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <16 x i32>, ptr %a |
| %res = call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> %op) |
| store <16 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v32i32(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctlz_v32i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl32 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i32>, ptr %a |
| %res = call <32 x i32> @llvm.ctlz.v32i32(<32 x i32> %op) |
| store <32 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v64i32(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctlz_v64i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl64 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <64 x i32>, ptr %a |
| %res = call <64 x i32> @llvm.ctlz.v64i32(<64 x i32> %op) |
| store <64 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define <1 x i64> @ctlz_v1i64(<1 x i64> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v1i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl1 |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0 |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0 |
| ; CHECK-NEXT: ret |
| %res = call <1 x i64> @llvm.ctlz.v1i64(<1 x i64> %op) |
| ret <1 x i64> %res |
| } |
| |
| define <2 x i64> @ctlz_v2i64(<2 x i64> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v2i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl2 |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0 |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 killed $z0 |
| ; CHECK-NEXT: ret |
| %res = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> %op) |
| ret <2 x i64> %res |
| } |
| |
| define void @ctlz_v4i64(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctlz_v4i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl4 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <4 x i64>, ptr %a |
| %res = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> %op) |
| store <4 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v8i64(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctlz_v8i64: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.d, vl4 |
| ; VBITS_GE_256-NEXT: mov x8, #4 // =0x4 |
| ; VBITS_GE_256-NEXT: ld1d { z0.d }, p0/z, [x0, x8, lsl #3] |
| ; VBITS_GE_256-NEXT: ld1d { z1.d }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: clz z0.d, p0/m, z0.d |
| ; VBITS_GE_256-NEXT: clz z1.d, p0/m, z1.d |
| ; VBITS_GE_256-NEXT: st1d { z0.d }, p0, [x0, x8, lsl #3] |
| ; VBITS_GE_256-NEXT: st1d { z1.d }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctlz_v8i64: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.d, vl8 |
| ; VBITS_GE_512-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: clz z0.d, p0/m, z0.d |
| ; VBITS_GE_512-NEXT: st1d { z0.d }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <8 x i64>, ptr %a |
| %res = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> %op) |
| store <8 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v16i64(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctlz_v16i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl16 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <16 x i64>, ptr %a |
| %res = call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> %op) |
| store <16 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctlz_v32i64(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctlz_v32i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl32 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i64>, ptr %a |
| %res = call <32 x i64> @llvm.ctlz.v32i64(<32 x i64> %op) |
| store <32 x i64> %res, ptr %a |
| ret void |
| } |
| |
| ; |
| ; CNT |
| ; |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <8 x i8> @ctpop_v8i8(<8 x i8> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v8i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.8b, v0.8b |
| ; CHECK-NEXT: ret |
| %res = call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> %op) |
| ret <8 x i8> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <16 x i8> @ctpop_v16i8(<16 x i8> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v16i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.16b, v0.16b |
| ; CHECK-NEXT: ret |
| %res = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %op) |
| ret <16 x i8> %res |
| } |
| |
| define void @ctpop_v32i8(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v32i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl32 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i8>, ptr %a |
| %res = call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> %op) |
| store <32 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v64i8(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctpop_v64i8: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.b, vl32 |
| ; VBITS_GE_256-NEXT: mov w8, #32 // =0x20 |
| ; VBITS_GE_256-NEXT: ld1b { z0.b }, p0/z, [x0, x8] |
| ; VBITS_GE_256-NEXT: ld1b { z1.b }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: cnt z0.b, p0/m, z0.b |
| ; VBITS_GE_256-NEXT: cnt z1.b, p0/m, z1.b |
| ; VBITS_GE_256-NEXT: st1b { z0.b }, p0, [x0, x8] |
| ; VBITS_GE_256-NEXT: st1b { z1.b }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctpop_v64i8: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.b, vl64 |
| ; VBITS_GE_512-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: cnt z0.b, p0/m, z0.b |
| ; VBITS_GE_512-NEXT: st1b { z0.b }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <64 x i8>, ptr %a |
| %res = call <64 x i8> @llvm.ctpop.v64i8(<64 x i8> %op) |
| store <64 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v128i8(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctpop_v128i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl128 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <128 x i8>, ptr %a |
| %res = call <128 x i8> @llvm.ctpop.v128i8(<128 x i8> %op) |
| store <128 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v256i8(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctpop_v256i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl256 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <256 x i8>, ptr %a |
| %res = call <256 x i8> @llvm.ctpop.v256i8(<256 x i8> %op) |
| store <256 x i8> %res, ptr %a |
| ret void |
| } |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <4 x i16> @ctpop_v4i16(<4 x i16> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v4i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.8b, v0.8b |
| ; CHECK-NEXT: uaddlp v0.4h, v0.8b |
| ; CHECK-NEXT: ret |
| %res = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> %op) |
| ret <4 x i16> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <8 x i16> @ctpop_v8i16(<8 x i16> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v8i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.16b, v0.16b |
| ; CHECK-NEXT: uaddlp v0.8h, v0.16b |
| ; CHECK-NEXT: ret |
| %res = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %op) |
| ret <8 x i16> %res |
| } |
| |
| define void @ctpop_v16i16(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v16i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl16 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <16 x i16>, ptr %a |
| %res = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> %op) |
| store <16 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v32i16(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctpop_v32i16: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.h, vl16 |
| ; VBITS_GE_256-NEXT: mov x8, #16 // =0x10 |
| ; VBITS_GE_256-NEXT: ld1h { z0.h }, p0/z, [x0, x8, lsl #1] |
| ; VBITS_GE_256-NEXT: ld1h { z1.h }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: cnt z0.h, p0/m, z0.h |
| ; VBITS_GE_256-NEXT: cnt z1.h, p0/m, z1.h |
| ; VBITS_GE_256-NEXT: st1h { z0.h }, p0, [x0, x8, lsl #1] |
| ; VBITS_GE_256-NEXT: st1h { z1.h }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctpop_v32i16: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.h, vl32 |
| ; VBITS_GE_512-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: cnt z0.h, p0/m, z0.h |
| ; VBITS_GE_512-NEXT: st1h { z0.h }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <32 x i16>, ptr %a |
| %res = call <32 x i16> @llvm.ctpop.v32i16(<32 x i16> %op) |
| store <32 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v64i16(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctpop_v64i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl64 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <64 x i16>, ptr %a |
| %res = call <64 x i16> @llvm.ctpop.v64i16(<64 x i16> %op) |
| store <64 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v128i16(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctpop_v128i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl128 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <128 x i16>, ptr %a |
| %res = call <128 x i16> @llvm.ctpop.v128i16(<128 x i16> %op) |
| store <128 x i16> %res, ptr %a |
| ret void |
| } |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <2 x i32> @ctpop_v2i32(<2 x i32> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v2i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.8b, v0.8b |
| ; CHECK-NEXT: uaddlp v0.4h, v0.8b |
| ; CHECK-NEXT: uaddlp v0.2s, v0.4h |
| ; CHECK-NEXT: ret |
| %res = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> %op) |
| ret <2 x i32> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <4 x i32> @ctpop_v4i32(<4 x i32> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v4i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.16b, v0.16b |
| ; CHECK-NEXT: uaddlp v0.8h, v0.16b |
| ; CHECK-NEXT: uaddlp v0.4s, v0.8h |
| ; CHECK-NEXT: ret |
| %res = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %op) |
| ret <4 x i32> %res |
| } |
| |
| define void @ctpop_v8i32(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v8i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl8 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <8 x i32>, ptr %a |
| %res = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> %op) |
| store <8 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v16i32(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctpop_v16i32: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.s, vl8 |
| ; VBITS_GE_256-NEXT: mov x8, #8 // =0x8 |
| ; VBITS_GE_256-NEXT: ld1w { z0.s }, p0/z, [x0, x8, lsl #2] |
| ; VBITS_GE_256-NEXT: ld1w { z1.s }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: cnt z0.s, p0/m, z0.s |
| ; VBITS_GE_256-NEXT: cnt z1.s, p0/m, z1.s |
| ; VBITS_GE_256-NEXT: st1w { z0.s }, p0, [x0, x8, lsl #2] |
| ; VBITS_GE_256-NEXT: st1w { z1.s }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctpop_v16i32: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.s, vl16 |
| ; VBITS_GE_512-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: cnt z0.s, p0/m, z0.s |
| ; VBITS_GE_512-NEXT: st1w { z0.s }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <16 x i32>, ptr %a |
| %res = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %op) |
| store <16 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v32i32(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctpop_v32i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl32 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i32>, ptr %a |
| %res = call <32 x i32> @llvm.ctpop.v32i32(<32 x i32> %op) |
| store <32 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v64i32(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctpop_v64i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl64 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <64 x i32>, ptr %a |
| %res = call <64 x i32> @llvm.ctpop.v64i32(<64 x i32> %op) |
| store <64 x i32> %res, ptr %a |
| ret void |
| } |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <1 x i64> @ctpop_v1i64(<1 x i64> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v1i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.8b, v0.8b |
| ; CHECK-NEXT: uaddlp v0.4h, v0.8b |
| ; CHECK-NEXT: uaddlp v0.2s, v0.4h |
| ; CHECK-NEXT: uaddlp v0.1d, v0.2s |
| ; CHECK-NEXT: ret |
| %res = call <1 x i64> @llvm.ctpop.v1i64(<1 x i64> %op) |
| ret <1 x i64> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <2 x i64> @ctpop_v2i64(<2 x i64> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v2i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: cnt v0.16b, v0.16b |
| ; CHECK-NEXT: uaddlp v0.8h, v0.16b |
| ; CHECK-NEXT: uaddlp v0.4s, v0.8h |
| ; CHECK-NEXT: uaddlp v0.2d, v0.4s |
| ; CHECK-NEXT: ret |
| %res = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %op) |
| ret <2 x i64> %res |
| } |
| |
| define void @ctpop_v4i64(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: ctpop_v4i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl4 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <4 x i64>, ptr %a |
| %res = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> %op) |
| store <4 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v8i64(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: ctpop_v8i64: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.d, vl4 |
| ; VBITS_GE_256-NEXT: mov x8, #4 // =0x4 |
| ; VBITS_GE_256-NEXT: ld1d { z0.d }, p0/z, [x0, x8, lsl #3] |
| ; VBITS_GE_256-NEXT: ld1d { z1.d }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: cnt z0.d, p0/m, z0.d |
| ; VBITS_GE_256-NEXT: cnt z1.d, p0/m, z1.d |
| ; VBITS_GE_256-NEXT: st1d { z0.d }, p0, [x0, x8, lsl #3] |
| ; VBITS_GE_256-NEXT: st1d { z1.d }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: ctpop_v8i64: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.d, vl8 |
| ; VBITS_GE_512-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: cnt z0.d, p0/m, z0.d |
| ; VBITS_GE_512-NEXT: st1d { z0.d }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <8 x i64>, ptr %a |
| %res = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> %op) |
| store <8 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v16i64(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: ctpop_v16i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl16 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <16 x i64>, ptr %a |
| %res = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> %op) |
| store <16 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @ctpop_v32i64(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: ctpop_v32i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl32 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: cnt z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i64>, ptr %a |
| %res = call <32 x i64> @llvm.ctpop.v32i64(<32 x i64> %op) |
| store <32 x i64> %res, ptr %a |
| ret void |
| } |
| |
| ; |
| ; Count trailing zeros |
| ; |
| |
| define <8 x i8> @cttz_v8i8(<8 x i8> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v8i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl8 |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0 |
| ; CHECK-NEXT: rbit z0.b, p0/m, z0.b |
| ; CHECK-NEXT: clz v0.8b, v0.8b |
| ; CHECK-NEXT: ret |
| %res = call <8 x i8> @llvm.cttz.v8i8(<8 x i8> %op) |
| ret <8 x i8> %res |
| } |
| |
| define <16 x i8> @cttz_v16i8(<16 x i8> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v16i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl16 |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0 |
| ; CHECK-NEXT: rbit z0.b, p0/m, z0.b |
| ; CHECK-NEXT: clz v0.16b, v0.16b |
| ; CHECK-NEXT: ret |
| %res = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> %op) |
| ret <16 x i8> %res |
| } |
| |
| define void @cttz_v32i8(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v32i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl32 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.b, p0/m, z0.b |
| ; CHECK-NEXT: clz z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i8>, ptr %a |
| %res = call <32 x i8> @llvm.cttz.v32i8(<32 x i8> %op) |
| store <32 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v64i8(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: cttz_v64i8: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.b, vl32 |
| ; VBITS_GE_256-NEXT: mov w8, #32 // =0x20 |
| ; VBITS_GE_256-NEXT: ld1b { z0.b }, p0/z, [x0, x8] |
| ; VBITS_GE_256-NEXT: ld1b { z1.b }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: rbit z0.b, p0/m, z0.b |
| ; VBITS_GE_256-NEXT: rbit z1.b, p0/m, z1.b |
| ; VBITS_GE_256-NEXT: clz z0.b, p0/m, z0.b |
| ; VBITS_GE_256-NEXT: clz z1.b, p0/m, z1.b |
| ; VBITS_GE_256-NEXT: st1b { z0.b }, p0, [x0, x8] |
| ; VBITS_GE_256-NEXT: st1b { z1.b }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: cttz_v64i8: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.b, vl64 |
| ; VBITS_GE_512-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: rbit z0.b, p0/m, z0.b |
| ; VBITS_GE_512-NEXT: clz z0.b, p0/m, z0.b |
| ; VBITS_GE_512-NEXT: st1b { z0.b }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <64 x i8>, ptr %a |
| %res = call <64 x i8> @llvm.cttz.v64i8(<64 x i8> %op) |
| store <64 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v128i8(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: cttz_v128i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl128 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.b, p0/m, z0.b |
| ; CHECK-NEXT: clz z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <128 x i8>, ptr %a |
| %res = call <128 x i8> @llvm.cttz.v128i8(<128 x i8> %op) |
| store <128 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v256i8(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: cttz_v256i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.b, vl256 |
| ; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.b, p0/m, z0.b |
| ; CHECK-NEXT: clz z0.b, p0/m, z0.b |
| ; CHECK-NEXT: st1b { z0.b }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <256 x i8>, ptr %a |
| %res = call <256 x i8> @llvm.cttz.v256i8(<256 x i8> %op) |
| store <256 x i8> %res, ptr %a |
| ret void |
| } |
| |
| define <4 x i16> @cttz_v4i16(<4 x i16> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v4i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl4 |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0 |
| ; CHECK-NEXT: rbit z0.h, p0/m, z0.h |
| ; CHECK-NEXT: clz v0.4h, v0.4h |
| ; CHECK-NEXT: ret |
| %res = call <4 x i16> @llvm.cttz.v4i16(<4 x i16> %op) |
| ret <4 x i16> %res |
| } |
| |
| define <8 x i16> @cttz_v8i16(<8 x i16> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v8i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl8 |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0 |
| ; CHECK-NEXT: rbit z0.h, p0/m, z0.h |
| ; CHECK-NEXT: clz v0.8h, v0.8h |
| ; CHECK-NEXT: ret |
| %res = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> %op) |
| ret <8 x i16> %res |
| } |
| |
| define void @cttz_v16i16(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v16i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl16 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.h, p0/m, z0.h |
| ; CHECK-NEXT: clz z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <16 x i16>, ptr %a |
| %res = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> %op) |
| store <16 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v32i16(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: cttz_v32i16: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.h, vl16 |
| ; VBITS_GE_256-NEXT: mov x8, #16 // =0x10 |
| ; VBITS_GE_256-NEXT: ld1h { z0.h }, p0/z, [x0, x8, lsl #1] |
| ; VBITS_GE_256-NEXT: ld1h { z1.h }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: rbit z0.h, p0/m, z0.h |
| ; VBITS_GE_256-NEXT: rbit z1.h, p0/m, z1.h |
| ; VBITS_GE_256-NEXT: clz z0.h, p0/m, z0.h |
| ; VBITS_GE_256-NEXT: clz z1.h, p0/m, z1.h |
| ; VBITS_GE_256-NEXT: st1h { z0.h }, p0, [x0, x8, lsl #1] |
| ; VBITS_GE_256-NEXT: st1h { z1.h }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: cttz_v32i16: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.h, vl32 |
| ; VBITS_GE_512-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: rbit z0.h, p0/m, z0.h |
| ; VBITS_GE_512-NEXT: clz z0.h, p0/m, z0.h |
| ; VBITS_GE_512-NEXT: st1h { z0.h }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <32 x i16>, ptr %a |
| %res = call <32 x i16> @llvm.cttz.v32i16(<32 x i16> %op) |
| store <32 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v64i16(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: cttz_v64i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl64 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.h, p0/m, z0.h |
| ; CHECK-NEXT: clz z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <64 x i16>, ptr %a |
| %res = call <64 x i16> @llvm.cttz.v64i16(<64 x i16> %op) |
| store <64 x i16> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v128i16(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: cttz_v128i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.h, vl128 |
| ; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.h, p0/m, z0.h |
| ; CHECK-NEXT: clz z0.h, p0/m, z0.h |
| ; CHECK-NEXT: st1h { z0.h }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <128 x i16>, ptr %a |
| %res = call <128 x i16> @llvm.cttz.v128i16(<128 x i16> %op) |
| store <128 x i16> %res, ptr %a |
| ret void |
| } |
| |
| ; Don't use SVE for 64-bit vectors. |
| define <2 x i32> @cttz_v2i32(<2 x i32> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v2i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl2 |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0 |
| ; CHECK-NEXT: rbit z0.s, p0/m, z0.s |
| ; CHECK-NEXT: clz v0.2s, v0.2s |
| ; CHECK-NEXT: ret |
| %res = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> %op) |
| ret <2 x i32> %res |
| } |
| |
| ; Don't use SVE for 128-bit vectors. |
| define <4 x i32> @cttz_v4i32(<4 x i32> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v4i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl4 |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0 |
| ; CHECK-NEXT: rbit z0.s, p0/m, z0.s |
| ; CHECK-NEXT: clz v0.4s, v0.4s |
| ; CHECK-NEXT: ret |
| %res = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> %op) |
| ret <4 x i32> %res |
| } |
| |
| define void @cttz_v8i32(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v8i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl8 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.s, p0/m, z0.s |
| ; CHECK-NEXT: clz z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <8 x i32>, ptr %a |
| %res = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> %op) |
| store <8 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v16i32(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: cttz_v16i32: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.s, vl8 |
| ; VBITS_GE_256-NEXT: mov x8, #8 // =0x8 |
| ; VBITS_GE_256-NEXT: ld1w { z0.s }, p0/z, [x0, x8, lsl #2] |
| ; VBITS_GE_256-NEXT: ld1w { z1.s }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: rbit z0.s, p0/m, z0.s |
| ; VBITS_GE_256-NEXT: rbit z1.s, p0/m, z1.s |
| ; VBITS_GE_256-NEXT: clz z0.s, p0/m, z0.s |
| ; VBITS_GE_256-NEXT: clz z1.s, p0/m, z1.s |
| ; VBITS_GE_256-NEXT: st1w { z0.s }, p0, [x0, x8, lsl #2] |
| ; VBITS_GE_256-NEXT: st1w { z1.s }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: cttz_v16i32: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.s, vl16 |
| ; VBITS_GE_512-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: rbit z0.s, p0/m, z0.s |
| ; VBITS_GE_512-NEXT: clz z0.s, p0/m, z0.s |
| ; VBITS_GE_512-NEXT: st1w { z0.s }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <16 x i32>, ptr %a |
| %res = call <16 x i32> @llvm.cttz.v16i32(<16 x i32> %op) |
| store <16 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v32i32(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: cttz_v32i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl32 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.s, p0/m, z0.s |
| ; CHECK-NEXT: clz z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i32>, ptr %a |
| %res = call <32 x i32> @llvm.cttz.v32i32(<32 x i32> %op) |
| store <32 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v64i32(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: cttz_v64i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.s, vl64 |
| ; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.s, p0/m, z0.s |
| ; CHECK-NEXT: clz z0.s, p0/m, z0.s |
| ; CHECK-NEXT: st1w { z0.s }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <64 x i32>, ptr %a |
| %res = call <64 x i32> @llvm.cttz.v64i32(<64 x i32> %op) |
| store <64 x i32> %res, ptr %a |
| ret void |
| } |
| |
| define <1 x i64> @cttz_v1i64(<1 x i64> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v1i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl1 |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0 |
| ; CHECK-NEXT: rbit z0.d, p0/m, z0.d |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0 |
| ; CHECK-NEXT: ret |
| %res = call <1 x i64> @llvm.cttz.v1i64(<1 x i64> %op) |
| ret <1 x i64> %res |
| } |
| |
| define <2 x i64> @cttz_v2i64(<2 x i64> %op) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v2i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl2 |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0 |
| ; CHECK-NEXT: rbit z0.d, p0/m, z0.d |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: // kill: def $q0 killed $q0 killed $z0 |
| ; CHECK-NEXT: ret |
| %res = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> %op) |
| ret <2 x i64> %res |
| } |
| |
| define void @cttz_v4i64(ptr %a) vscale_range(2,0) #0 { |
| ; CHECK-LABEL: cttz_v4i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl4 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.d, p0/m, z0.d |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <4 x i64>, ptr %a |
| %res = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> %op) |
| store <4 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v8i64(ptr %a) #0 { |
| ; VBITS_GE_256-LABEL: cttz_v8i64: |
| ; VBITS_GE_256: // %bb.0: |
| ; VBITS_GE_256-NEXT: ptrue p0.d, vl4 |
| ; VBITS_GE_256-NEXT: mov x8, #4 // =0x4 |
| ; VBITS_GE_256-NEXT: ld1d { z0.d }, p0/z, [x0, x8, lsl #3] |
| ; VBITS_GE_256-NEXT: ld1d { z1.d }, p0/z, [x0] |
| ; VBITS_GE_256-NEXT: rbit z0.d, p0/m, z0.d |
| ; VBITS_GE_256-NEXT: rbit z1.d, p0/m, z1.d |
| ; VBITS_GE_256-NEXT: clz z0.d, p0/m, z0.d |
| ; VBITS_GE_256-NEXT: clz z1.d, p0/m, z1.d |
| ; VBITS_GE_256-NEXT: st1d { z0.d }, p0, [x0, x8, lsl #3] |
| ; VBITS_GE_256-NEXT: st1d { z1.d }, p0, [x0] |
| ; VBITS_GE_256-NEXT: ret |
| ; |
| ; VBITS_GE_512-LABEL: cttz_v8i64: |
| ; VBITS_GE_512: // %bb.0: |
| ; VBITS_GE_512-NEXT: ptrue p0.d, vl8 |
| ; VBITS_GE_512-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; VBITS_GE_512-NEXT: rbit z0.d, p0/m, z0.d |
| ; VBITS_GE_512-NEXT: clz z0.d, p0/m, z0.d |
| ; VBITS_GE_512-NEXT: st1d { z0.d }, p0, [x0] |
| ; VBITS_GE_512-NEXT: ret |
| %op = load <8 x i64>, ptr %a |
| %res = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> %op) |
| store <8 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v16i64(ptr %a) vscale_range(8,0) #0 { |
| ; CHECK-LABEL: cttz_v16i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl16 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.d, p0/m, z0.d |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <16 x i64>, ptr %a |
| %res = call <16 x i64> @llvm.cttz.v16i64(<16 x i64> %op) |
| store <16 x i64> %res, ptr %a |
| ret void |
| } |
| |
| define void @cttz_v32i64(ptr %a) vscale_range(16,0) #0 { |
| ; CHECK-LABEL: cttz_v32i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ptrue p0.d, vl32 |
| ; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0] |
| ; CHECK-NEXT: rbit z0.d, p0/m, z0.d |
| ; CHECK-NEXT: clz z0.d, p0/m, z0.d |
| ; CHECK-NEXT: st1d { z0.d }, p0, [x0] |
| ; CHECK-NEXT: ret |
| %op = load <32 x i64>, ptr %a |
| %res = call <32 x i64> @llvm.cttz.v32i64(<32 x i64> %op) |
| store <32 x i64> %res, ptr %a |
| ret void |
| } |
| |
| attributes #0 = { "target-features"="+sve" } |
| |
| declare <8 x i8> @llvm.ctlz.v8i8(<8 x i8>) |
| declare <16 x i8> @llvm.ctlz.v16i8(<16 x i8>) |
| declare <32 x i8> @llvm.ctlz.v32i8(<32 x i8>) |
| declare <64 x i8> @llvm.ctlz.v64i8(<64 x i8>) |
| declare <128 x i8> @llvm.ctlz.v128i8(<128 x i8>) |
| declare <256 x i8> @llvm.ctlz.v256i8(<256 x i8>) |
| declare <4 x i16> @llvm.ctlz.v4i16(<4 x i16>) |
| declare <8 x i16> @llvm.ctlz.v8i16(<8 x i16>) |
| declare <16 x i16> @llvm.ctlz.v16i16(<16 x i16>) |
| declare <32 x i16> @llvm.ctlz.v32i16(<32 x i16>) |
| declare <64 x i16> @llvm.ctlz.v64i16(<64 x i16>) |
| declare <128 x i16> @llvm.ctlz.v128i16(<128 x i16>) |
| declare <2 x i32> @llvm.ctlz.v2i32(<2 x i32>) |
| declare <4 x i32> @llvm.ctlz.v4i32(<4 x i32>) |
| declare <8 x i32> @llvm.ctlz.v8i32(<8 x i32>) |
| declare <16 x i32> @llvm.ctlz.v16i32(<16 x i32>) |
| declare <32 x i32> @llvm.ctlz.v32i32(<32 x i32>) |
| declare <64 x i32> @llvm.ctlz.v64i32(<64 x i32>) |
| declare <1 x i64> @llvm.ctlz.v1i64(<1 x i64>) |
| declare <2 x i64> @llvm.ctlz.v2i64(<2 x i64>) |
| declare <4 x i64> @llvm.ctlz.v4i64(<4 x i64>) |
| declare <8 x i64> @llvm.ctlz.v8i64(<8 x i64>) |
| declare <16 x i64> @llvm.ctlz.v16i64(<16 x i64>) |
| declare <32 x i64> @llvm.ctlz.v32i64(<32 x i64>) |
| |
| declare <8 x i8> @llvm.ctpop.v8i8(<8 x i8>) |
| declare <16 x i8> @llvm.ctpop.v16i8(<16 x i8>) |
| declare <32 x i8> @llvm.ctpop.v32i8(<32 x i8>) |
| declare <64 x i8> @llvm.ctpop.v64i8(<64 x i8>) |
| declare <128 x i8> @llvm.ctpop.v128i8(<128 x i8>) |
| declare <256 x i8> @llvm.ctpop.v256i8(<256 x i8>) |
| declare <4 x i16> @llvm.ctpop.v4i16(<4 x i16>) |
| declare <8 x i16> @llvm.ctpop.v8i16(<8 x i16>) |
| declare <16 x i16> @llvm.ctpop.v16i16(<16 x i16>) |
| declare <32 x i16> @llvm.ctpop.v32i16(<32 x i16>) |
| declare <64 x i16> @llvm.ctpop.v64i16(<64 x i16>) |
| declare <128 x i16> @llvm.ctpop.v128i16(<128 x i16>) |
| declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32>) |
| declare <4 x i32> @llvm.ctpop.v4i32(<4 x i32>) |
| declare <8 x i32> @llvm.ctpop.v8i32(<8 x i32>) |
| declare <16 x i32> @llvm.ctpop.v16i32(<16 x i32>) |
| declare <32 x i32> @llvm.ctpop.v32i32(<32 x i32>) |
| declare <64 x i32> @llvm.ctpop.v64i32(<64 x i32>) |
| declare <1 x i64> @llvm.ctpop.v1i64(<1 x i64>) |
| declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>) |
| declare <4 x i64> @llvm.ctpop.v4i64(<4 x i64>) |
| declare <8 x i64> @llvm.ctpop.v8i64(<8 x i64>) |
| declare <16 x i64> @llvm.ctpop.v16i64(<16 x i64>) |
| declare <32 x i64> @llvm.ctpop.v32i64(<32 x i64>) |
| |
| declare <8 x i8> @llvm.cttz.v8i8(<8 x i8>) |
| declare <16 x i8> @llvm.cttz.v16i8(<16 x i8>) |
| declare <32 x i8> @llvm.cttz.v32i8(<32 x i8>) |
| declare <64 x i8> @llvm.cttz.v64i8(<64 x i8>) |
| declare <128 x i8> @llvm.cttz.v128i8(<128 x i8>) |
| declare <256 x i8> @llvm.cttz.v256i8(<256 x i8>) |
| declare <4 x i16> @llvm.cttz.v4i16(<4 x i16>) |
| declare <8 x i16> @llvm.cttz.v8i16(<8 x i16>) |
| declare <16 x i16> @llvm.cttz.v16i16(<16 x i16>) |
| declare <32 x i16> @llvm.cttz.v32i16(<32 x i16>) |
| declare <64 x i16> @llvm.cttz.v64i16(<64 x i16>) |
| declare <128 x i16> @llvm.cttz.v128i16(<128 x i16>) |
| declare <2 x i32> @llvm.cttz.v2i32(<2 x i32>) |
| declare <4 x i32> @llvm.cttz.v4i32(<4 x i32>) |
| declare <8 x i32> @llvm.cttz.v8i32(<8 x i32>) |
| declare <16 x i32> @llvm.cttz.v16i32(<16 x i32>) |
| declare <32 x i32> @llvm.cttz.v32i32(<32 x i32>) |
| declare <64 x i32> @llvm.cttz.v64i32(<64 x i32>) |
| declare <1 x i64> @llvm.cttz.v1i64(<1 x i64>) |
| declare <2 x i64> @llvm.cttz.v2i64(<2 x i64>) |
| declare <4 x i64> @llvm.cttz.v4i64(<4 x i64>) |
| declare <8 x i64> @llvm.cttz.v8i64(<8 x i64>) |
| declare <16 x i64> @llvm.cttz.v16i64(<16 x i64>) |
| declare <32 x i64> @llvm.cttz.v32i64(<32 x i64>) |