| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc -mtriple=riscv32 -mattr=+v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV32 |
| ; RUN: llc -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64 |
| |
| define <2 x i16> @vwmulsu_v2i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v2i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vle8.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i8>, ptr %x |
| %b = load <2 x i8>, ptr %y |
| %c = zext <2 x i8> %a to <2 x i16> |
| %d = sext <2 x i8> %b to <2 x i16> |
| %e = mul <2 x i16> %c, %d |
| ret <2 x i16> %e |
| } |
| |
| define <2 x i16> @vwmulsu_v2i16_swap(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v2i16_swap: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vle8.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v9, v10 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i8>, ptr %x |
| %b = load <2 x i8>, ptr %y |
| %c = sext <2 x i8> %a to <2 x i16> |
| %d = zext <2 x i8> %b to <2 x i16> |
| %e = mul <2 x i16> %c, %d |
| ret <2 x i16> %e |
| } |
| |
| define <4 x i16> @vwmulsu_v4i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v4i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vle8.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i8>, ptr %x |
| %b = load <4 x i8>, ptr %y |
| %c = zext <4 x i8> %a to <4 x i16> |
| %d = sext <4 x i8> %b to <4 x i16> |
| %e = mul <4 x i16> %c, %d |
| ret <4 x i16> %e |
| } |
| |
| define <2 x i32> @vwmulsu_v2i32(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v2i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: vle16.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i16>, ptr %x |
| %b = load <2 x i16>, ptr %y |
| %c = zext <2 x i16> %a to <2 x i32> |
| %d = sext <2 x i16> %b to <2 x i32> |
| %e = mul <2 x i32> %c, %d |
| ret <2 x i32> %e |
| } |
| |
| define <8 x i16> @vwmulsu_v8i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v8i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vle8.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i8>, ptr %x |
| %b = load <8 x i8>, ptr %y |
| %c = zext <8 x i8> %a to <8 x i16> |
| %d = sext <8 x i8> %b to <8 x i16> |
| %e = mul <8 x i16> %c, %d |
| ret <8 x i16> %e |
| } |
| |
| define <4 x i32> @vwmulsu_v4i32(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v4i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: vle16.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i16>, ptr %x |
| %b = load <4 x i16>, ptr %y |
| %c = zext <4 x i16> %a to <4 x i32> |
| %d = sext <4 x i16> %b to <4 x i32> |
| %e = mul <4 x i32> %c, %d |
| ret <4 x i32> %e |
| } |
| |
| define <2 x i64> @vwmulsu_v2i64(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v2i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma |
| ; CHECK-NEXT: vle32.v v9, (a0) |
| ; CHECK-NEXT: vle32.v v10, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i32>, ptr %x |
| %b = load <2 x i32>, ptr %y |
| %c = zext <2 x i32> %a to <2 x i64> |
| %d = sext <2 x i32> %b to <2 x i64> |
| %e = mul <2 x i64> %c, %d |
| ret <2 x i64> %e |
| } |
| |
| define <16 x i16> @vwmulsu_v16i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v16i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma |
| ; CHECK-NEXT: vle8.v v10, (a0) |
| ; CHECK-NEXT: vle8.v v11, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v11, v10 |
| ; CHECK-NEXT: ret |
| %a = load <16 x i8>, ptr %x |
| %b = load <16 x i8>, ptr %y |
| %c = zext <16 x i8> %a to <16 x i16> |
| %d = sext <16 x i8> %b to <16 x i16> |
| %e = mul <16 x i16> %c, %d |
| ret <16 x i16> %e |
| } |
| |
| define <8 x i32> @vwmulsu_v8i32(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v8i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma |
| ; CHECK-NEXT: vle16.v v10, (a0) |
| ; CHECK-NEXT: vle16.v v11, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v11, v10 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i16>, ptr %x |
| %b = load <8 x i16>, ptr %y |
| %c = zext <8 x i16> %a to <8 x i32> |
| %d = sext <8 x i16> %b to <8 x i32> |
| %e = mul <8 x i32> %c, %d |
| ret <8 x i32> %e |
| } |
| |
| define <4 x i64> @vwmulsu_v4i64(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v4i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma |
| ; CHECK-NEXT: vle32.v v10, (a0) |
| ; CHECK-NEXT: vle32.v v11, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v11, v10 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i32>, ptr %x |
| %b = load <4 x i32>, ptr %y |
| %c = zext <4 x i32> %a to <4 x i64> |
| %d = sext <4 x i32> %b to <4 x i64> |
| %e = mul <4 x i64> %c, %d |
| ret <4 x i64> %e |
| } |
| |
| define <32 x i16> @vwmulsu_v32i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v32i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: li a2, 32 |
| ; CHECK-NEXT: vsetvli zero, a2, e8, m2, ta, ma |
| ; CHECK-NEXT: vle8.v v12, (a0) |
| ; CHECK-NEXT: vle8.v v14, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v14, v12 |
| ; CHECK-NEXT: ret |
| %a = load <32 x i8>, ptr %x |
| %b = load <32 x i8>, ptr %y |
| %c = zext <32 x i8> %a to <32 x i16> |
| %d = sext <32 x i8> %b to <32 x i16> |
| %e = mul <32 x i16> %c, %d |
| ret <32 x i16> %e |
| } |
| |
| define <16 x i32> @vwmulsu_v16i32(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v16i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma |
| ; CHECK-NEXT: vle16.v v12, (a0) |
| ; CHECK-NEXT: vle16.v v14, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v14, v12 |
| ; CHECK-NEXT: ret |
| %a = load <16 x i16>, ptr %x |
| %b = load <16 x i16>, ptr %y |
| %c = zext <16 x i16> %a to <16 x i32> |
| %d = sext <16 x i16> %b to <16 x i32> |
| %e = mul <16 x i32> %c, %d |
| ret <16 x i32> %e |
| } |
| |
| define <8 x i64> @vwmulsu_v8i64(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v8i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma |
| ; CHECK-NEXT: vle32.v v12, (a0) |
| ; CHECK-NEXT: vle32.v v14, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v14, v12 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i32>, ptr %x |
| %b = load <8 x i32>, ptr %y |
| %c = zext <8 x i32> %a to <8 x i64> |
| %d = sext <8 x i32> %b to <8 x i64> |
| %e = mul <8 x i64> %c, %d |
| ret <8 x i64> %e |
| } |
| |
| define <64 x i16> @vwmulsu_v64i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v64i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: li a2, 64 |
| ; CHECK-NEXT: vsetvli zero, a2, e8, m4, ta, ma |
| ; CHECK-NEXT: vle8.v v16, (a0) |
| ; CHECK-NEXT: vle8.v v20, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v20, v16 |
| ; CHECK-NEXT: ret |
| %a = load <64 x i8>, ptr %x |
| %b = load <64 x i8>, ptr %y |
| %c = zext <64 x i8> %a to <64 x i16> |
| %d = sext <64 x i8> %b to <64 x i16> |
| %e = mul <64 x i16> %c, %d |
| ret <64 x i16> %e |
| } |
| |
| define <32 x i32> @vwmulsu_v32i32(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v32i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: li a2, 32 |
| ; CHECK-NEXT: vsetvli zero, a2, e16, m4, ta, ma |
| ; CHECK-NEXT: vle16.v v16, (a0) |
| ; CHECK-NEXT: vle16.v v20, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v20, v16 |
| ; CHECK-NEXT: ret |
| %a = load <32 x i16>, ptr %x |
| %b = load <32 x i16>, ptr %y |
| %c = zext <32 x i16> %a to <32 x i32> |
| %d = sext <32 x i16> %b to <32 x i32> |
| %e = mul <32 x i32> %c, %d |
| ret <32 x i32> %e |
| } |
| |
| define <16 x i64> @vwmulsu_v16i64(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v16i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma |
| ; CHECK-NEXT: vle32.v v16, (a0) |
| ; CHECK-NEXT: vle32.v v20, (a1) |
| ; CHECK-NEXT: vwmulsu.vv v8, v20, v16 |
| ; CHECK-NEXT: ret |
| %a = load <16 x i32>, ptr %x |
| %b = load <16 x i32>, ptr %y |
| %c = zext <16 x i32> %a to <16 x i64> |
| %d = sext <16 x i32> %b to <16 x i64> |
| %e = mul <16 x i64> %c, %d |
| ret <16 x i64> %e |
| } |
| |
| define <128 x i16> @vwmulsu_v128i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v128i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: addi sp, sp, -16 |
| ; CHECK-NEXT: .cfi_def_cfa_offset 16 |
| ; CHECK-NEXT: csrr a2, vlenb |
| ; CHECK-NEXT: slli a2, a2, 3 |
| ; CHECK-NEXT: sub sp, sp, a2 |
| ; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb |
| ; CHECK-NEXT: li a2, 128 |
| ; CHECK-NEXT: vsetvli zero, a2, e8, m8, ta, ma |
| ; CHECK-NEXT: vle8.v v16, (a0) |
| ; CHECK-NEXT: vle8.v v24, (a1) |
| ; CHECK-NEXT: li a0, 64 |
| ; CHECK-NEXT: vsetvli zero, a0, e8, m8, ta, ma |
| ; CHECK-NEXT: vslidedown.vx v8, v16, a0 |
| ; CHECK-NEXT: addi a1, sp, 16 |
| ; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill |
| ; CHECK-NEXT: vslidedown.vx v0, v24, a0 |
| ; CHECK-NEXT: vsetvli zero, a0, e8, m4, ta, ma |
| ; CHECK-NEXT: vwmulsu.vv v8, v24, v16 |
| ; CHECK-NEXT: addi a0, sp, 16 |
| ; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload |
| ; CHECK-NEXT: vwmulsu.vv v16, v0, v24 |
| ; CHECK-NEXT: csrr a0, vlenb |
| ; CHECK-NEXT: slli a0, a0, 3 |
| ; CHECK-NEXT: add sp, sp, a0 |
| ; CHECK-NEXT: addi sp, sp, 16 |
| ; CHECK-NEXT: ret |
| %a = load <128 x i8>, ptr %x |
| %b = load <128 x i8>, ptr %y |
| %c = zext <128 x i8> %a to <128 x i16> |
| %d = sext <128 x i8> %b to <128 x i16> |
| %e = mul <128 x i16> %c, %d |
| ret <128 x i16> %e |
| } |
| |
| define <64 x i32> @vwmulsu_v64i32(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v64i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: addi sp, sp, -16 |
| ; CHECK-NEXT: .cfi_def_cfa_offset 16 |
| ; CHECK-NEXT: csrr a2, vlenb |
| ; CHECK-NEXT: slli a2, a2, 3 |
| ; CHECK-NEXT: sub sp, sp, a2 |
| ; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb |
| ; CHECK-NEXT: li a2, 64 |
| ; CHECK-NEXT: vsetvli zero, a2, e16, m8, ta, ma |
| ; CHECK-NEXT: vle16.v v16, (a0) |
| ; CHECK-NEXT: vle16.v v24, (a1) |
| ; CHECK-NEXT: li a0, 32 |
| ; CHECK-NEXT: vsetvli zero, a0, e16, m8, ta, ma |
| ; CHECK-NEXT: vslidedown.vx v8, v16, a0 |
| ; CHECK-NEXT: addi a1, sp, 16 |
| ; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill |
| ; CHECK-NEXT: vslidedown.vx v0, v24, a0 |
| ; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma |
| ; CHECK-NEXT: vwmulsu.vv v8, v24, v16 |
| ; CHECK-NEXT: addi a0, sp, 16 |
| ; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload |
| ; CHECK-NEXT: vwmulsu.vv v16, v0, v24 |
| ; CHECK-NEXT: csrr a0, vlenb |
| ; CHECK-NEXT: slli a0, a0, 3 |
| ; CHECK-NEXT: add sp, sp, a0 |
| ; CHECK-NEXT: addi sp, sp, 16 |
| ; CHECK-NEXT: ret |
| %a = load <64 x i16>, ptr %x |
| %b = load <64 x i16>, ptr %y |
| %c = zext <64 x i16> %a to <64 x i32> |
| %d = sext <64 x i16> %b to <64 x i32> |
| %e = mul <64 x i32> %c, %d |
| ret <64 x i32> %e |
| } |
| |
| define <32 x i64> @vwmulsu_v32i64(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v32i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: addi sp, sp, -16 |
| ; CHECK-NEXT: .cfi_def_cfa_offset 16 |
| ; CHECK-NEXT: csrr a2, vlenb |
| ; CHECK-NEXT: slli a2, a2, 3 |
| ; CHECK-NEXT: sub sp, sp, a2 |
| ; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb |
| ; CHECK-NEXT: li a2, 32 |
| ; CHECK-NEXT: vsetvli zero, a2, e32, m8, ta, ma |
| ; CHECK-NEXT: vle32.v v16, (a0) |
| ; CHECK-NEXT: vle32.v v24, (a1) |
| ; CHECK-NEXT: vsetivli zero, 16, e32, m8, ta, ma |
| ; CHECK-NEXT: vslidedown.vi v8, v16, 16 |
| ; CHECK-NEXT: addi a0, sp, 16 |
| ; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill |
| ; CHECK-NEXT: vslidedown.vi v0, v24, 16 |
| ; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma |
| ; CHECK-NEXT: vwmulsu.vv v8, v24, v16 |
| ; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload |
| ; CHECK-NEXT: vwmulsu.vv v16, v0, v24 |
| ; CHECK-NEXT: csrr a0, vlenb |
| ; CHECK-NEXT: slli a0, a0, 3 |
| ; CHECK-NEXT: add sp, sp, a0 |
| ; CHECK-NEXT: addi sp, sp, 16 |
| ; CHECK-NEXT: ret |
| %a = load <32 x i32>, ptr %x |
| %b = load <32 x i32>, ptr %y |
| %c = zext <32 x i32> %a to <32 x i64> |
| %d = sext <32 x i32> %b to <32 x i64> |
| %e = mul <32 x i64> %c, %d |
| ret <32 x i64> %e |
| } |
| |
| define <2 x i32> @vwmulsu_v2i32_v2i8(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v2i32_v2i8: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma |
| ; CHECK-NEXT: vle8.v v8, (a0) |
| ; CHECK-NEXT: vle8.v v9, (a1) |
| ; CHECK-NEXT: vzext.vf2 v10, v8 |
| ; CHECK-NEXT: vsext.vf2 v11, v9 |
| ; CHECK-NEXT: vwmulsu.vv v8, v11, v10 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i8>, ptr %x |
| %b = load <2 x i8>, ptr %y |
| %c = zext <2 x i8> %a to <2 x i32> |
| %d = sext <2 x i8> %b to <2 x i32> |
| %e = mul <2 x i32> %c, %d |
| ret <2 x i32> %e |
| } |
| |
| define <4 x i32> @vwmulsu_v4i32_v4i8_v4i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v4i32_v4i8_v4i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v8, (a0) |
| ; CHECK-NEXT: vle16.v v9, (a1) |
| ; CHECK-NEXT: vzext.vf2 v10, v8 |
| ; CHECK-NEXT: vwmulsu.vv v8, v9, v10 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i8>, ptr %x |
| %b = load <4 x i16>, ptr %y |
| %c = zext <4 x i8> %a to <4 x i32> |
| %d = sext <4 x i16> %b to <4 x i32> |
| %e = mul <4 x i32> %c, %d |
| ret <4 x i32> %e |
| } |
| |
| define <4 x i64> @vwmulsu_v4i64_v4i32_v4i8(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_v4i64_v4i32_v4i8: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma |
| ; CHECK-NEXT: vle8.v v8, (a1) |
| ; CHECK-NEXT: vle32.v v10, (a0) |
| ; CHECK-NEXT: vsext.vf4 v11, v8 |
| ; CHECK-NEXT: vwmulsu.vv v8, v11, v10 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i32>, ptr %x |
| %b = load <4 x i8>, ptr %y |
| %c = zext <4 x i32> %a to <4 x i64> |
| %d = sext <4 x i8> %b to <4 x i64> |
| %e = mul <4 x i64> %c, %d |
| ret <4 x i64> %e |
| } |
| |
| define <2 x i16> @vwmulsu_vx_v2i16(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v2i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i8>, ptr %x |
| %b = insertelement <2 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <2 x i8> %b, <2 x i8> poison, <2 x i32> zeroinitializer |
| %d = sext <2 x i8> %a to <2 x i16> |
| %e = zext <2 x i8> %c to <2 x i16> |
| %f = mul <2 x i16> %d, %e |
| ret <2 x i16> %f |
| } |
| |
| define <2 x i16> @vwmulsu_vx_v2i16_swap(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v2i16_swap: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vmv.v.x v10, a1 |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i8>, ptr %x |
| %b = insertelement <2 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <2 x i8> %b, <2 x i8> poison, <2 x i32> zeroinitializer |
| %d = zext <2 x i8> %a to <2 x i16> |
| %e = sext <2 x i8> %c to <2 x i16> |
| %f = mul <2 x i16> %d, %e |
| ret <2 x i16> %f |
| } |
| |
| define <4 x i16> @vwmulsu_vx_v4i16(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i8>, ptr %x |
| %b = insertelement <4 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <4 x i8> %b, <4 x i8> poison, <4 x i32> zeroinitializer |
| %d = sext <4 x i8> %a to <4 x i16> |
| %e = zext <4 x i8> %c to <4 x i16> |
| %f = mul <4 x i16> %d, %e |
| ret <4 x i16> %f |
| } |
| |
| define <2 x i32> @vwmulsu_vx_v2i32(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v2i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i16>, ptr %x |
| %b = insertelement <2 x i16> poison, i16 %y, i32 0 |
| %c = shufflevector <2 x i16> %b, <2 x i16> poison, <2 x i32> zeroinitializer |
| %d = sext <2 x i16> %a to <2 x i32> |
| %e = zext <2 x i16> %c to <2 x i32> |
| %f = mul <2 x i32> %d, %e |
| ret <2 x i32> %f |
| } |
| |
| define <8 x i16> @vwmulsu_vx_v8i16(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i8>, ptr %x |
| %b = insertelement <8 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <8 x i8> %b, <8 x i8> poison, <8 x i32> zeroinitializer |
| %d = sext <8 x i8> %a to <8 x i16> |
| %e = zext <8 x i8> %c to <8 x i16> |
| %f = mul <8 x i16> %d, %e |
| ret <8 x i16> %f |
| } |
| |
| define <4 x i32> @vwmulsu_vx_v4i32(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i16>, ptr %x |
| %b = insertelement <4 x i16> poison, i16 %y, i32 0 |
| %c = shufflevector <4 x i16> %b, <4 x i16> poison, <4 x i32> zeroinitializer |
| %d = sext <4 x i16> %a to <4 x i32> |
| %e = zext <4 x i16> %c to <4 x i32> |
| %f = mul <4 x i32> %d, %e |
| ret <4 x i32> %f |
| } |
| |
| define <2 x i64> @vwmulsu_vx_v2i64(ptr %x, i32 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v2i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma |
| ; CHECK-NEXT: vle32.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <2 x i32>, ptr %x |
| %b = insertelement <2 x i32> poison, i32 %y, i64 0 |
| %c = shufflevector <2 x i32> %b, <2 x i32> poison, <2 x i32> zeroinitializer |
| %d = sext <2 x i32> %a to <2 x i64> |
| %e = zext <2 x i32> %c to <2 x i64> |
| %f = mul <2 x i64> %d, %e |
| ret <2 x i64> %f |
| } |
| |
| define <16 x i16> @vwmulsu_vx_v16i16(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v16i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma |
| ; CHECK-NEXT: vle8.v v10, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v10, a1 |
| ; CHECK-NEXT: ret |
| %a = load <16 x i8>, ptr %x |
| %b = insertelement <16 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <16 x i8> %b, <16 x i8> poison, <16 x i32> zeroinitializer |
| %d = sext <16 x i8> %a to <16 x i16> |
| %e = zext <16 x i8> %c to <16 x i16> |
| %f = mul <16 x i16> %d, %e |
| ret <16 x i16> %f |
| } |
| |
| define <8 x i32> @vwmulsu_vx_v8i32(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma |
| ; CHECK-NEXT: vle16.v v10, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v10, a1 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i16>, ptr %x |
| %b = insertelement <8 x i16> poison, i16 %y, i32 0 |
| %c = shufflevector <8 x i16> %b, <8 x i16> poison, <8 x i32> zeroinitializer |
| %d = sext <8 x i16> %a to <8 x i32> |
| %e = zext <8 x i16> %c to <8 x i32> |
| %f = mul <8 x i32> %d, %e |
| ret <8 x i32> %f |
| } |
| |
| define <4 x i64> @vwmulsu_vx_v4i64(ptr %x, i32 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma |
| ; CHECK-NEXT: vle32.v v10, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v10, a1 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i32>, ptr %x |
| %b = insertelement <4 x i32> poison, i32 %y, i64 0 |
| %c = shufflevector <4 x i32> %b, <4 x i32> poison, <4 x i32> zeroinitializer |
| %d = sext <4 x i32> %a to <4 x i64> |
| %e = zext <4 x i32> %c to <4 x i64> |
| %f = mul <4 x i64> %d, %e |
| ret <4 x i64> %f |
| } |
| |
| define <32 x i16> @vwmulsu_vx_v32i16(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v32i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: li a2, 32 |
| ; CHECK-NEXT: vsetvli zero, a2, e8, m2, ta, ma |
| ; CHECK-NEXT: vle8.v v12, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v12, a1 |
| ; CHECK-NEXT: ret |
| %a = load <32 x i8>, ptr %x |
| %b = insertelement <32 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <32 x i8> %b, <32 x i8> poison, <32 x i32> zeroinitializer |
| %d = sext <32 x i8> %a to <32 x i16> |
| %e = zext <32 x i8> %c to <32 x i16> |
| %f = mul <32 x i16> %d, %e |
| ret <32 x i16> %f |
| } |
| |
| define <16 x i32> @vwmulsu_vx_v16i32(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v16i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma |
| ; CHECK-NEXT: vle16.v v12, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v12, a1 |
| ; CHECK-NEXT: ret |
| %a = load <16 x i16>, ptr %x |
| %b = insertelement <16 x i16> poison, i16 %y, i32 0 |
| %c = shufflevector <16 x i16> %b, <16 x i16> poison, <16 x i32> zeroinitializer |
| %d = sext <16 x i16> %a to <16 x i32> |
| %e = zext <16 x i16> %c to <16 x i32> |
| %f = mul <16 x i32> %d, %e |
| ret <16 x i32> %f |
| } |
| |
| define <8 x i64> @vwmulsu_vx_v8i64(ptr %x, i32 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma |
| ; CHECK-NEXT: vle32.v v12, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v12, a1 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i32>, ptr %x |
| %b = insertelement <8 x i32> poison, i32 %y, i64 0 |
| %c = shufflevector <8 x i32> %b, <8 x i32> poison, <8 x i32> zeroinitializer |
| %d = sext <8 x i32> %a to <8 x i64> |
| %e = zext <8 x i32> %c to <8 x i64> |
| %f = mul <8 x i64> %d, %e |
| ret <8 x i64> %f |
| } |
| |
| define <64 x i16> @vwmulsu_vx_v64i16(ptr %x, i8 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v64i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: li a2, 64 |
| ; CHECK-NEXT: vsetvli zero, a2, e8, m4, ta, ma |
| ; CHECK-NEXT: vle8.v v16, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v16, a1 |
| ; CHECK-NEXT: ret |
| %a = load <64 x i8>, ptr %x |
| %b = insertelement <64 x i8> poison, i8 %y, i32 0 |
| %c = shufflevector <64 x i8> %b, <64 x i8> poison, <64 x i32> zeroinitializer |
| %d = sext <64 x i8> %a to <64 x i16> |
| %e = zext <64 x i8> %c to <64 x i16> |
| %f = mul <64 x i16> %d, %e |
| ret <64 x i16> %f |
| } |
| |
| define <32 x i32> @vwmulsu_vx_v32i32(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v32i32: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: li a2, 32 |
| ; CHECK-NEXT: vsetvli zero, a2, e16, m4, ta, ma |
| ; CHECK-NEXT: vle16.v v16, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v16, a1 |
| ; CHECK-NEXT: ret |
| %a = load <32 x i16>, ptr %x |
| %b = insertelement <32 x i16> poison, i16 %y, i32 0 |
| %c = shufflevector <32 x i16> %b, <32 x i16> poison, <32 x i32> zeroinitializer |
| %d = sext <32 x i16> %a to <32 x i32> |
| %e = zext <32 x i16> %c to <32 x i32> |
| %f = mul <32 x i32> %d, %e |
| ret <32 x i32> %f |
| } |
| |
| define <16 x i64> @vwmulsu_vx_v16i64(ptr %x, i32 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v16i64: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma |
| ; CHECK-NEXT: vle32.v v16, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v16, a1 |
| ; CHECK-NEXT: ret |
| %a = load <16 x i32>, ptr %x |
| %b = insertelement <16 x i32> poison, i32 %y, i64 0 |
| %c = shufflevector <16 x i32> %b, <16 x i32> poison, <16 x i32> zeroinitializer |
| %d = sext <16 x i32> %a to <16 x i64> |
| %e = zext <16 x i32> %c to <16 x i64> |
| %f = mul <16 x i64> %d, %e |
| ret <16 x i64> %f |
| } |
| |
| define <8 x i16> @vwmulsu_vx_v8i16_i8(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i16_i8: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: lbu a0, 0(a1) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a0 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i8>, ptr %x |
| %b = load i8, ptr %y |
| %c = zext i8 %b to i16 |
| %d = insertelement <8 x i16> poison, i16 %c, i32 0 |
| %e = shufflevector <8 x i16> %d, <8 x i16> poison, <8 x i32> zeroinitializer |
| %f = sext <8 x i8> %a to <8 x i16> |
| %g = mul <8 x i16> %e, %f |
| ret <8 x i16> %g |
| } |
| |
| define <8 x i16> @vwmulsu_vx_v8i16_i8_swap(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i16_i8_swap: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vlse8.v v10, (a1), zero |
| ; CHECK-NEXT: vwmulsu.vv v8, v10, v9 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i8>, ptr %x |
| %b = load i8, ptr %y |
| %c = sext i8 %b to i16 |
| %d = insertelement <8 x i16> poison, i16 %c, i32 0 |
| %e = shufflevector <8 x i16> %d, <8 x i16> poison, <8 x i32> zeroinitializer |
| %f = zext <8 x i8> %a to <8 x i16> |
| %g = mul <8 x i16> %e, %f |
| ret <8 x i16> %g |
| } |
| |
| define <4 x i32> @vwmulsu_vx_v4i32_i8(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i32_i8: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: lbu a0, 0(a1) |
| ; CHECK-NEXT: vwmul.vx v8, v9, a0 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i16>, ptr %x |
| %b = load i8, ptr %y |
| %c = zext i8 %b to i32 |
| %d = insertelement <4 x i32> poison, i32 %c, i32 0 |
| %e = shufflevector <4 x i32> %d, <4 x i32> poison, <4 x i32> zeroinitializer |
| %f = sext <4 x i16> %a to <4 x i32> |
| %g = mul <4 x i32> %e, %f |
| ret <4 x i32> %g |
| } |
| |
| define <4 x i32> @vwmulsu_vx_v4i32_i16(ptr %x, ptr %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i32_i16: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: lhu a0, 0(a1) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a0 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i16>, ptr %x |
| %b = load i16, ptr %y |
| %c = zext i16 %b to i32 |
| %d = insertelement <4 x i32> poison, i32 %c, i32 0 |
| %e = shufflevector <4 x i32> %d, <4 x i32> poison, <4 x i32> zeroinitializer |
| %f = sext <4 x i16> %a to <4 x i32> |
| %g = mul <4 x i32> %e, %f |
| ret <4 x i32> %g |
| } |
| |
| define <2 x i64> @vwmulsu_vx_v2i64_i8(ptr %x, ptr %y) { |
| ; RV32-LABEL: vwmulsu_vx_v2i64_i8: |
| ; RV32: # %bb.0: |
| ; RV32-NEXT: addi sp, sp, -16 |
| ; RV32-NEXT: .cfi_def_cfa_offset 16 |
| ; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma |
| ; RV32-NEXT: lbu a1, 0(a1) |
| ; RV32-NEXT: vle32.v v8, (a0) |
| ; RV32-NEXT: sw zero, 12(sp) |
| ; RV32-NEXT: sw a1, 8(sp) |
| ; RV32-NEXT: addi a0, sp, 8 |
| ; RV32-NEXT: vlse64.v v9, (a0), zero |
| ; RV32-NEXT: vsext.vf2 v10, v8 |
| ; RV32-NEXT: vmul.vv v8, v9, v10 |
| ; RV32-NEXT: addi sp, sp, 16 |
| ; RV32-NEXT: ret |
| ; |
| ; RV64-LABEL: vwmulsu_vx_v2i64_i8: |
| ; RV64: # %bb.0: |
| ; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, ma |
| ; RV64-NEXT: vle32.v v9, (a0) |
| ; RV64-NEXT: lbu a0, 0(a1) |
| ; RV64-NEXT: vwmul.vx v8, v9, a0 |
| ; RV64-NEXT: ret |
| %a = load <2 x i32>, ptr %x |
| %b = load i8, ptr %y |
| %c = zext i8 %b to i64 |
| %d = insertelement <2 x i64> poison, i64 %c, i64 0 |
| %e = shufflevector <2 x i64> %d, <2 x i64> poison, <2 x i32> zeroinitializer |
| %f = sext <2 x i32> %a to <2 x i64> |
| %g = mul <2 x i64> %e, %f |
| ret <2 x i64> %g |
| } |
| |
| define <2 x i64> @vwmulsu_vx_v2i64_i16(ptr %x, ptr %y) { |
| ; RV32-LABEL: vwmulsu_vx_v2i64_i16: |
| ; RV32: # %bb.0: |
| ; RV32-NEXT: addi sp, sp, -16 |
| ; RV32-NEXT: .cfi_def_cfa_offset 16 |
| ; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma |
| ; RV32-NEXT: lhu a1, 0(a1) |
| ; RV32-NEXT: vle32.v v8, (a0) |
| ; RV32-NEXT: sw zero, 12(sp) |
| ; RV32-NEXT: sw a1, 8(sp) |
| ; RV32-NEXT: addi a0, sp, 8 |
| ; RV32-NEXT: vlse64.v v9, (a0), zero |
| ; RV32-NEXT: vsext.vf2 v10, v8 |
| ; RV32-NEXT: vmul.vv v8, v9, v10 |
| ; RV32-NEXT: addi sp, sp, 16 |
| ; RV32-NEXT: ret |
| ; |
| ; RV64-LABEL: vwmulsu_vx_v2i64_i16: |
| ; RV64: # %bb.0: |
| ; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, ma |
| ; RV64-NEXT: vle32.v v9, (a0) |
| ; RV64-NEXT: lhu a0, 0(a1) |
| ; RV64-NEXT: vwmul.vx v8, v9, a0 |
| ; RV64-NEXT: ret |
| %a = load <2 x i32>, ptr %x |
| %b = load i16, ptr %y |
| %c = zext i16 %b to i64 |
| %d = insertelement <2 x i64> poison, i64 %c, i64 0 |
| %e = shufflevector <2 x i64> %d, <2 x i64> poison, <2 x i32> zeroinitializer |
| %f = sext <2 x i32> %a to <2 x i64> |
| %g = mul <2 x i64> %e, %f |
| ret <2 x i64> %g |
| } |
| |
| define <2 x i64> @vwmulsu_vx_v2i64_i32(ptr %x, ptr %y) { |
| ; RV32-LABEL: vwmulsu_vx_v2i64_i32: |
| ; RV32: # %bb.0: |
| ; RV32-NEXT: addi sp, sp, -16 |
| ; RV32-NEXT: .cfi_def_cfa_offset 16 |
| ; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma |
| ; RV32-NEXT: lw a1, 0(a1) |
| ; RV32-NEXT: vle32.v v8, (a0) |
| ; RV32-NEXT: sw zero, 12(sp) |
| ; RV32-NEXT: sw a1, 8(sp) |
| ; RV32-NEXT: addi a0, sp, 8 |
| ; RV32-NEXT: vlse64.v v9, (a0), zero |
| ; RV32-NEXT: vsext.vf2 v10, v8 |
| ; RV32-NEXT: vmul.vv v8, v9, v10 |
| ; RV32-NEXT: addi sp, sp, 16 |
| ; RV32-NEXT: ret |
| ; |
| ; RV64-LABEL: vwmulsu_vx_v2i64_i32: |
| ; RV64: # %bb.0: |
| ; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, ma |
| ; RV64-NEXT: vle32.v v9, (a0) |
| ; RV64-NEXT: lwu a0, 0(a1) |
| ; RV64-NEXT: vwmulsu.vx v8, v9, a0 |
| ; RV64-NEXT: ret |
| %a = load <2 x i32>, ptr %x |
| %b = load i32, ptr %y |
| %c = zext i32 %b to i64 |
| %d = insertelement <2 x i64> poison, i64 %c, i64 0 |
| %e = shufflevector <2 x i64> %d, <2 x i64> poison, <2 x i32> zeroinitializer |
| %f = sext <2 x i32> %a to <2 x i64> |
| %g = mul <2 x i64> %e, %f |
| ret <2 x i64> %g |
| } |
| |
| define <8 x i16> @vwmulsu_vx_v8i16_i8_and(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i16_i8_and: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i8>, ptr %x |
| %b = and i16 %y, 255 |
| %c = insertelement <8 x i16> poison, i16 %b, i32 0 |
| %d = shufflevector <8 x i16> %c, <8 x i16> poison, <8 x i32> zeroinitializer |
| %e = sext <8 x i8> %a to <8 x i16> |
| %f = mul <8 x i16> %d, %e |
| ret <8 x i16> %f |
| } |
| |
| define <8 x i16> @vwmulsu_vx_v8i16_i8_and1(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v8i16_i8_and1: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma |
| ; CHECK-NEXT: vle8.v v9, (a0) |
| ; CHECK-NEXT: andi a0, a1, 254 |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a0 |
| ; CHECK-NEXT: ret |
| %a = load <8 x i8>, ptr %x |
| %b = and i16 %y, 254 |
| %c = insertelement <8 x i16> poison, i16 %b, i32 0 |
| %d = shufflevector <8 x i16> %c, <8 x i16> poison, <8 x i32> zeroinitializer |
| %e = sext <8 x i8> %a to <8 x i16> |
| %f = mul <8 x i16> %d, %e |
| ret <8 x i16> %f |
| } |
| |
| define <4 x i32> @vwmulsu_vx_v4i32_i16_and(ptr %x, i32 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i32_i16_and: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i16>, ptr %x |
| %b = and i32 %y, 65535 |
| %c = insertelement <4 x i32> poison, i32 %b, i32 0 |
| %d = shufflevector <4 x i32> %c, <4 x i32> poison, <4 x i32> zeroinitializer |
| %e = sext <4 x i16> %a to <4 x i32> |
| %f = mul <4 x i32> %d, %e |
| ret <4 x i32> %f |
| } |
| |
| define <4 x i32> @vwmulsu_vx_v4i32_i16_zext(ptr %x, i16 %y) { |
| ; CHECK-LABEL: vwmulsu_vx_v4i32_i16_zext: |
| ; CHECK: # %bb.0: |
| ; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma |
| ; CHECK-NEXT: vle16.v v9, (a0) |
| ; CHECK-NEXT: vwmulsu.vx v8, v9, a1 |
| ; CHECK-NEXT: ret |
| %a = load <4 x i16>, ptr %x |
| %b = zext i16 %y to i32 |
| %c = insertelement <4 x i32> poison, i32 %b, i32 0 |
| %d = shufflevector <4 x i32> %c, <4 x i32> poison, <4 x i32> zeroinitializer |
| %e = sext <4 x i16> %a to <4 x i32> |
| %f = mul <4 x i32> %d, %e |
| ret <4 x i32> %f |
| } |