diff --git a/llvm/test/CodeGen/Thumb2/mve-sext.ll b/llvm/test/CodeGen/Thumb2/mve-sext.ll index 452e68405feb..be4148821815 100644 --- a/llvm/test/CodeGen/Thumb2/mve-sext.ll +++ b/llvm/test/CodeGen/Thumb2/mve-sext.ll @@ -32,6 +32,131 @@ entry: ret <4 x i32> %0 } +define arm_aapcs_vfpcc <16 x i16> @sext_v16i8_v16i16(<16 x i8> %src) { +; CHECK-LABEL: sext_v16i8_v16i16: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vmov.u8 r0, q0[0] +; CHECK-NEXT: vmov.16 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[1] +; CHECK-NEXT: vmov.16 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[2] +; CHECK-NEXT: vmov.16 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[3] +; CHECK-NEXT: vmov.16 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[4] +; CHECK-NEXT: vmov.16 q1[4], r0 +; CHECK-NEXT: vmov.u8 r0, q0[5] +; CHECK-NEXT: vmov.16 q1[5], r0 +; CHECK-NEXT: vmov.u8 r0, q0[6] +; CHECK-NEXT: vmov.16 q1[6], r0 +; CHECK-NEXT: vmov.u8 r0, q0[7] +; CHECK-NEXT: vmov.16 q1[7], r0 +; CHECK-NEXT: vmov.u8 r0, q0[8] +; CHECK-NEXT: vmovlb.s8 q2, q1 +; CHECK-NEXT: vmov.16 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[9] +; CHECK-NEXT: vmov.16 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[10] +; CHECK-NEXT: vmov.16 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[11] +; CHECK-NEXT: vmov.16 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[12] +; CHECK-NEXT: vmov.16 q1[4], r0 +; CHECK-NEXT: vmov.u8 r0, q0[13] +; CHECK-NEXT: vmov.16 q1[5], r0 +; CHECK-NEXT: vmov.u8 r0, q0[14] +; CHECK-NEXT: vmov.16 q1[6], r0 +; CHECK-NEXT: vmov.u8 r0, q0[15] +; CHECK-NEXT: vmov.16 q1[7], r0 +; CHECK-NEXT: vmov q0, q2 +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: bx lr +entry: + %0 = sext <16 x i8> %src to <16 x i16> + ret <16 x i16> %0 +} + +define arm_aapcs_vfpcc <8 x i32> @sext_v8i16_v8i32(<8 x i16> %src) { +; CHECK-LABEL: sext_v8i16_v8i32: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vmov.u16 r0, q0[0] +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u16 r0, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u16 r0, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u16 r0, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov.u16 r0, q0[4] +; CHECK-NEXT: vmovlb.s16 q2, q1 +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u16 r0, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u16 r0, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u16 r0, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov q0, q2 +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: bx lr +entry: + %0 = sext <8 x i16> %src to <8 x i32> + ret <8 x i32> %0 +} + +define arm_aapcs_vfpcc <16 x i32> @sext_v16i8_v16i32(<16 x i8> %src) { +; CHECK-LABEL: sext_v16i8_v16i32: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: .vsave {d8, d9} +; CHECK-NEXT: vpush {d8, d9} +; CHECK-NEXT: vmov.u8 r0, q0[0] +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[4] +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vmovlb.s16 q4, q1 +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[8] +; CHECK-NEXT: vmov.32 q2[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[9] +; CHECK-NEXT: vmov.32 q2[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[10] +; CHECK-NEXT: vmov.32 q2[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[11] +; CHECK-NEXT: vmov.32 q2[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[12] +; CHECK-NEXT: vmov.32 q3[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[13] +; CHECK-NEXT: vmov.32 q3[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[14] +; CHECK-NEXT: vmov.32 q3[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[15] +; CHECK-NEXT: vmov.32 q3[3], r0 +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vmovlb.s8 q2, q2 +; CHECK-NEXT: vmovlb.s8 q0, q3 +; CHECK-NEXT: vmovlb.s16 q3, q0 +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vmovlb.s16 q2, q2 +; CHECK-NEXT: vmov q0, q4 +; CHECK-NEXT: vpop {d8, d9} +; CHECK-NEXT: bx lr +entry: + %0 = sext <16 x i8> %src to <16 x i32> + ret <16 x i32> %0 +} + define arm_aapcs_vfpcc <2 x i64> @sext_v2i32_v2i64(<2 x i32> %src) { ; CHECK-LABEL: sext_v2i32_v2i64: ; CHECK: @ %bb.0: @ %entry @@ -82,16 +207,138 @@ entry: ret <4 x i32> %0 } +define arm_aapcs_vfpcc <16 x i16> @zext_v16i8_v16i16(<16 x i8> %src) { +; CHECK-LABEL: zext_v16i8_v16i16: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vmov.u8 r0, q0[0] +; CHECK-NEXT: vmov.16 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[1] +; CHECK-NEXT: vmov.16 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[2] +; CHECK-NEXT: vmov.16 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[3] +; CHECK-NEXT: vmov.16 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[4] +; CHECK-NEXT: vmov.16 q1[4], r0 +; CHECK-NEXT: vmov.u8 r0, q0[5] +; CHECK-NEXT: vmov.16 q1[5], r0 +; CHECK-NEXT: vmov.u8 r0, q0[6] +; CHECK-NEXT: vmov.16 q1[6], r0 +; CHECK-NEXT: vmov.u8 r0, q0[7] +; CHECK-NEXT: vmov.16 q1[7], r0 +; CHECK-NEXT: vmov.u8 r0, q0[8] +; CHECK-NEXT: vmovlb.u8 q2, q1 +; CHECK-NEXT: vmov.16 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[9] +; CHECK-NEXT: vmov.16 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[10] +; CHECK-NEXT: vmov.16 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[11] +; CHECK-NEXT: vmov.16 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[12] +; CHECK-NEXT: vmov.16 q1[4], r0 +; CHECK-NEXT: vmov.u8 r0, q0[13] +; CHECK-NEXT: vmov.16 q1[5], r0 +; CHECK-NEXT: vmov.u8 r0, q0[14] +; CHECK-NEXT: vmov.16 q1[6], r0 +; CHECK-NEXT: vmov.u8 r0, q0[15] +; CHECK-NEXT: vmov.16 q1[7], r0 +; CHECK-NEXT: vmov q0, q2 +; CHECK-NEXT: vmovlb.u8 q1, q1 +; CHECK-NEXT: bx lr +entry: + %0 = zext <16 x i8> %src to <16 x i16> + ret <16 x i16> %0 +} + +define arm_aapcs_vfpcc <8 x i32> @zext_v8i16_v8i32(<8 x i16> %src) { +; CHECK-LABEL: zext_v8i16_v8i32: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vmov.u16 r0, q0[0] +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u16 r0, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u16 r0, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u16 r0, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov.u16 r0, q0[4] +; CHECK-NEXT: vmovlb.u16 q2, q1 +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u16 r0, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u16 r0, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u16 r0, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov q0, q2 +; CHECK-NEXT: vmovlb.u16 q1, q1 +; CHECK-NEXT: bx lr +entry: + %0 = zext <8 x i16> %src to <8 x i32> + ret <8 x i32> %0 +} + +define arm_aapcs_vfpcc <16 x i32> @zext_v16i8_v16i32(<16 x i8> %src) { +; CHECK-LABEL: zext_v16i8_v16i32: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: .vsave {d8, d9, d10, d11} +; CHECK-NEXT: vpush {d8, d9, d10, d11} +; CHECK-NEXT: vmov.u8 r0, q0[0] +; CHECK-NEXT: vmov.i32 q3, #0xff +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[4] +; CHECK-NEXT: vand q4, q1, q3 +; CHECK-NEXT: vmov.32 q1[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[8] +; CHECK-NEXT: vmov.32 q2[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[9] +; CHECK-NEXT: vmov.32 q2[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[10] +; CHECK-NEXT: vmov.32 q2[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[11] +; CHECK-NEXT: vmov.32 q2[3], r0 +; CHECK-NEXT: vmov.u8 r0, q0[12] +; CHECK-NEXT: vmov.32 q5[0], r0 +; CHECK-NEXT: vmov.u8 r0, q0[13] +; CHECK-NEXT: vmov.32 q5[1], r0 +; CHECK-NEXT: vmov.u8 r0, q0[14] +; CHECK-NEXT: vmov.32 q5[2], r0 +; CHECK-NEXT: vmov.u8 r0, q0[15] +; CHECK-NEXT: vmov.32 q5[3], r0 +; CHECK-NEXT: vand q1, q1, q3 +; CHECK-NEXT: vand q2, q2, q3 +; CHECK-NEXT: vand q3, q5, q3 +; CHECK-NEXT: vmov q0, q4 +; CHECK-NEXT: vpop {d8, d9, d10, d11} +; CHECK-NEXT: bx lr +entry: + %0 = zext <16 x i8> %src to <16 x i32> + ret <16 x i32> %0 +} + define arm_aapcs_vfpcc <2 x i64> @zext_v2i32_v2i64(<2 x i32> %src) { ; CHECK-LABEL: zext_v2i32_v2i64: ; CHECK: @ %bb.0: @ %entry -; CHECK-NEXT: adr r0, .LCPI7_0 +; CHECK-NEXT: adr r0, .LCPI13_0 ; CHECK-NEXT: vldrw.u32 q1, [r0] ; CHECK-NEXT: vand q0, q0, q1 ; CHECK-NEXT: bx lr ; CHECK-NEXT: .p2align 4 ; CHECK-NEXT: @ %bb.1: -; CHECK-NEXT: .LCPI7_0: +; CHECK-NEXT: .LCPI13_0: ; CHECK-NEXT: .long 4294967295 @ 0xffffffff ; CHECK-NEXT: .long 0 @ 0x0 ; CHECK-NEXT: .long 4294967295 @ 0xffffffff @@ -129,6 +376,119 @@ entry: ret <4 x i8> %0 } +define arm_aapcs_vfpcc <16 x i8> @trunc_v16i16_v16i8(<16 x i16> %src) { +; CHECK-LABEL: trunc_v16i16_v16i8: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vmov q2, q0 +; CHECK-NEXT: vmov.u16 r0, q0[0] +; CHECK-NEXT: vmov.8 q0[0], r0 +; CHECK-NEXT: vmov.u16 r0, q2[1] +; CHECK-NEXT: vmov.8 q0[1], r0 +; CHECK-NEXT: vmov.u16 r0, q2[2] +; CHECK-NEXT: vmov.8 q0[2], r0 +; CHECK-NEXT: vmov.u16 r0, q2[3] +; CHECK-NEXT: vmov.8 q0[3], r0 +; CHECK-NEXT: vmov.u16 r0, q2[4] +; CHECK-NEXT: vmov.8 q0[4], r0 +; CHECK-NEXT: vmov.u16 r0, q2[5] +; CHECK-NEXT: vmov.8 q0[5], r0 +; CHECK-NEXT: vmov.u16 r0, q2[6] +; CHECK-NEXT: vmov.8 q0[6], r0 +; CHECK-NEXT: vmov.u16 r0, q2[7] +; CHECK-NEXT: vmov.8 q0[7], r0 +; CHECK-NEXT: vmov.u16 r0, q1[0] +; CHECK-NEXT: vmov.8 q0[8], r0 +; CHECK-NEXT: vmov.u16 r0, q1[1] +; CHECK-NEXT: vmov.8 q0[9], r0 +; CHECK-NEXT: vmov.u16 r0, q1[2] +; CHECK-NEXT: vmov.8 q0[10], r0 +; CHECK-NEXT: vmov.u16 r0, q1[3] +; CHECK-NEXT: vmov.8 q0[11], r0 +; CHECK-NEXT: vmov.u16 r0, q1[4] +; CHECK-NEXT: vmov.8 q0[12], r0 +; CHECK-NEXT: vmov.u16 r0, q1[5] +; CHECK-NEXT: vmov.8 q0[13], r0 +; CHECK-NEXT: vmov.u16 r0, q1[6] +; CHECK-NEXT: vmov.8 q0[14], r0 +; CHECK-NEXT: vmov.u16 r0, q1[7] +; CHECK-NEXT: vmov.8 q0[15], r0 +; CHECK-NEXT: bx lr +entry: + %0 = trunc <16 x i16> %src to <16 x i8> + ret <16 x i8> %0 +} + +define arm_aapcs_vfpcc <8 x i16> @trunc_v8i32_v8i16(<8 x i32> %src) { +; CHECK-LABEL: trunc_v8i32_v8i16: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vmov q2, q0 +; CHECK-NEXT: vmov r0, s8 +; CHECK-NEXT: vmov.16 q0[0], r0 +; CHECK-NEXT: vmov r0, s9 +; CHECK-NEXT: vmov.16 q0[1], r0 +; CHECK-NEXT: vmov r0, s10 +; CHECK-NEXT: vmov.16 q0[2], r0 +; CHECK-NEXT: vmov r0, s11 +; CHECK-NEXT: vmov.16 q0[3], r0 +; CHECK-NEXT: vmov r0, s4 +; CHECK-NEXT: vmov.16 q0[4], r0 +; CHECK-NEXT: vmov r0, s5 +; CHECK-NEXT: vmov.16 q0[5], r0 +; CHECK-NEXT: vmov r0, s6 +; CHECK-NEXT: vmov.16 q0[6], r0 +; CHECK-NEXT: vmov r0, s7 +; CHECK-NEXT: vmov.16 q0[7], r0 +; CHECK-NEXT: bx lr +entry: + %0 = trunc <8 x i32> %src to <8 x i16> + ret <8 x i16> %0 +} + +define arm_aapcs_vfpcc <16 x i8> @trunc_v16i32_v16i8(<16 x i32> %src) { +; CHECK-LABEL: trunc_v16i32_v16i8: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: .vsave {d8, d9} +; CHECK-NEXT: vpush {d8, d9} +; CHECK-NEXT: vmov q4, q0 +; CHECK-NEXT: vmov r0, s16 +; CHECK-NEXT: vmov.8 q0[0], r0 +; CHECK-NEXT: vmov r0, s17 +; CHECK-NEXT: vmov.8 q0[1], r0 +; CHECK-NEXT: vmov r0, s18 +; CHECK-NEXT: vmov.8 q0[2], r0 +; CHECK-NEXT: vmov r0, s19 +; CHECK-NEXT: vmov.8 q0[3], r0 +; CHECK-NEXT: vmov r0, s4 +; CHECK-NEXT: vmov.8 q0[4], r0 +; CHECK-NEXT: vmov r0, s5 +; CHECK-NEXT: vmov.8 q0[5], r0 +; CHECK-NEXT: vmov r0, s6 +; CHECK-NEXT: vmov.8 q0[6], r0 +; CHECK-NEXT: vmov r0, s7 +; CHECK-NEXT: vmov.8 q0[7], r0 +; CHECK-NEXT: vmov r0, s8 +; CHECK-NEXT: vmov.8 q0[8], r0 +; CHECK-NEXT: vmov r0, s9 +; CHECK-NEXT: vmov.8 q0[9], r0 +; CHECK-NEXT: vmov r0, s10 +; CHECK-NEXT: vmov.8 q0[10], r0 +; CHECK-NEXT: vmov r0, s11 +; CHECK-NEXT: vmov.8 q0[11], r0 +; CHECK-NEXT: vmov r0, s12 +; CHECK-NEXT: vmov.8 q0[12], r0 +; CHECK-NEXT: vmov r0, s13 +; CHECK-NEXT: vmov.8 q0[13], r0 +; CHECK-NEXT: vmov r0, s14 +; CHECK-NEXT: vmov.8 q0[14], r0 +; CHECK-NEXT: vmov r0, s15 +; CHECK-NEXT: vmov.8 q0[15], r0 +; CHECK-NEXT: vpop {d8, d9} +; CHECK-NEXT: bx lr +entry: + %0 = trunc <16 x i32> %src to <16 x i8> + ret <16 x i8> %0 +} + define arm_aapcs_vfpcc <2 x i32> @trunc_v2i64_v2i32(<2 x i64> %src) { ; CHECK-LABEL: trunc_v2i64_v2i32: ; CHECK: @ %bb.0: @ %entry diff --git a/llvm/test/CodeGen/Thumb2/mve-widen-narrow.ll b/llvm/test/CodeGen/Thumb2/mve-widen-narrow.ll index 7b0a64c7ba6f..b3f342f58469 100644 --- a/llvm/test/CodeGen/Thumb2/mve-widen-narrow.ll +++ b/llvm/test/CodeGen/Thumb2/mve-widen-narrow.ll @@ -41,6 +41,57 @@ entry: ret void } + +define void @foo_int8_int32_double(<16 x i8>* %dest, <16 x i32>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int8_int32_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrw.u32 q0, [r1] +; CHECK-NEXT: vldrw.u32 q1, [r1, #16] +; CHECK-NEXT: vldrw.u32 q2, [r1, #32] +; CHECK-NEXT: vldrw.u32 q3, [r1, #48] +; CHECK-NEXT: vstrb.32 q1, [r0, #4] +; CHECK-NEXT: vstrb.32 q0, [r0] +; CHECK-NEXT: vstrb.32 q3, [r0, #12] +; CHECK-NEXT: vstrb.32 q2, [r0, #8] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i32>, <16 x i32>* %src, align 4 + %0 = trunc <16 x i32> %wide.load to <16 x i8> + store <16 x i8> %0, <16 x i8>* %dest, align 1 + ret void +} + +define void @foo_int16_int32_double(<8 x i16>* %dest, <8 x i32>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int16_int32_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrw.u32 q0, [r1] +; CHECK-NEXT: vldrw.u32 q1, [r1, #16] +; CHECK-NEXT: vstrh.32 q1, [r0, #8] +; CHECK-NEXT: vstrh.32 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <8 x i32>, <8 x i32>* %src, align 4 + %0 = trunc <8 x i32> %wide.load to <8 x i16> + store <8 x i16> %0, <8 x i16>* %dest, align 2 + ret void +} + +define void @foo_int8_int16_double(<16 x i8>* %dest, <16 x i16>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int8_int16_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrh.u16 q0, [r1] +; CHECK-NEXT: vldrh.u16 q1, [r1, #16] +; CHECK-NEXT: vstrb.16 q1, [r0, #8] +; CHECK-NEXT: vstrb.16 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i16>, <16 x i16>* %src, align 2 + %0 = trunc <16 x i16> %wide.load to <16 x i8> + store <16 x i8> %0, <16 x i8>* %dest, align 1 + ret void +} + + define void @foo_int32_int8(<4 x i32>* %dest, <4 x i8>* readonly %src, i32 %n) { ; CHECK-LABEL: foo_int32_int8: ; CHECK: @ %bb.0: @ %entry @@ -80,6 +131,143 @@ entry: ret void } +define void @foo_int32_int8_double(<16 x i32>* %dest, <16 x i8>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int32_int8_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrb.u8 q0, [r1] +; CHECK-NEXT: vmov.u8 r1, q0[12] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[13] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[14] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[15] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[8] +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #48] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[9] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[10] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[11] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[4] +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #32] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[0] +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #16] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmovlb.s8 q0, q1 +; CHECK-NEXT: vmovlb.s16 q0, q0 +; CHECK-NEXT: vstrw.32 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i8>, <16 x i8>* %src, align 1 + %0 = sext <16 x i8> %wide.load to <16 x i32> + store <16 x i32> %0, <16 x i32>* %dest, align 4 + ret void +} + +define void @foo_int16_int8_double(<16 x i16>* %dest, <16 x i8>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int16_int8_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrb.u8 q0, [r1] +; CHECK-NEXT: vmov.u8 r1, q0[8] +; CHECK-NEXT: vmov.16 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[9] +; CHECK-NEXT: vmov.16 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[10] +; CHECK-NEXT: vmov.16 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[11] +; CHECK-NEXT: vmov.16 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[12] +; CHECK-NEXT: vmov.16 q1[4], r1 +; CHECK-NEXT: vmov.u8 r1, q0[13] +; CHECK-NEXT: vmov.16 q1[5], r1 +; CHECK-NEXT: vmov.u8 r1, q0[14] +; CHECK-NEXT: vmov.16 q1[6], r1 +; CHECK-NEXT: vmov.u8 r1, q0[15] +; CHECK-NEXT: vmov.16 q1[7], r1 +; CHECK-NEXT: vmov.u8 r1, q0[0] +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vstrh.16 q1, [r0, #16] +; CHECK-NEXT: vmov.16 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[1] +; CHECK-NEXT: vmov.16 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[2] +; CHECK-NEXT: vmov.16 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[3] +; CHECK-NEXT: vmov.16 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[4] +; CHECK-NEXT: vmov.16 q1[4], r1 +; CHECK-NEXT: vmov.u8 r1, q0[5] +; CHECK-NEXT: vmov.16 q1[5], r1 +; CHECK-NEXT: vmov.u8 r1, q0[6] +; CHECK-NEXT: vmov.16 q1[6], r1 +; CHECK-NEXT: vmov.u8 r1, q0[7] +; CHECK-NEXT: vmov.16 q1[7], r1 +; CHECK-NEXT: vmovlb.s8 q0, q1 +; CHECK-NEXT: vstrh.16 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i8>, <16 x i8>* %src, align 1 + %0 = sext <16 x i8> %wide.load to <16 x i16> + store <16 x i16> %0, <16 x i16>* %dest, align 2 + ret void +} + +define void @foo_int32_int16_double(<8 x i32>* %dest, <8 x i16>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int32_int16_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrh.u16 q0, [r1] +; CHECK-NEXT: vmov.u16 r1, q0[4] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u16 r1, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u16 r1, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u16 r1, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmov.u16 r1, q0[0] +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #16] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u16 r1, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u16 r1, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u16 r1, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmovlb.s16 q0, q1 +; CHECK-NEXT: vstrw.32 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <8 x i16>, <8 x i16>* %src, align 2 + %0 = sext <8 x i16> %wide.load to <8 x i32> + store <8 x i32> %0, <8 x i32>* %dest, align 4 + ret void +} + + define void @foo_uint32_uint8(<4 x i32>* %dest, <4 x i8>* readonly %src, i32 %n) { ; CHECK-LABEL: foo_uint32_uint8: ; CHECK: @ %bb.0: @ %entry @@ -120,6 +308,315 @@ entry: } +define void @foo_uint32_uint8_double(<16 x i32>* %dest, <16 x i8>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_uint32_uint8_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrb.u8 q0, [r1] +; CHECK-NEXT: vmov.i32 q1, #0xff +; CHECK-NEXT: vmov.u8 r1, q0[12] +; CHECK-NEXT: vmov.32 q2[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[13] +; CHECK-NEXT: vmov.32 q2[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[14] +; CHECK-NEXT: vmov.32 q2[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[15] +; CHECK-NEXT: vmov.32 q2[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[8] +; CHECK-NEXT: vand q2, q2, q1 +; CHECK-NEXT: vstrw.32 q2, [r0, #48] +; CHECK-NEXT: vmov.32 q2[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[9] +; CHECK-NEXT: vmov.32 q2[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[10] +; CHECK-NEXT: vmov.32 q2[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[11] +; CHECK-NEXT: vmov.32 q2[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[4] +; CHECK-NEXT: vand q2, q2, q1 +; CHECK-NEXT: vstrw.32 q2, [r0, #32] +; CHECK-NEXT: vmov.32 q2[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[5] +; CHECK-NEXT: vmov.32 q2[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[6] +; CHECK-NEXT: vmov.32 q2[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[7] +; CHECK-NEXT: vmov.32 q2[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[0] +; CHECK-NEXT: vand q2, q2, q1 +; CHECK-NEXT: vstrw.32 q2, [r0, #16] +; CHECK-NEXT: vmov.32 q2[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[1] +; CHECK-NEXT: vmov.32 q2[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[2] +; CHECK-NEXT: vmov.32 q2[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[3] +; CHECK-NEXT: vmov.32 q2[3], r1 +; CHECK-NEXT: vand q0, q2, q1 +; CHECK-NEXT: vstrw.32 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i8>, <16 x i8>* %src, align 1 + %0 = zext <16 x i8> %wide.load to <16 x i32> + store <16 x i32> %0, <16 x i32>* %dest, align 4 + ret void +} + +define void @foo_uint16_uint8_double(<16 x i16>* %dest, <16 x i8>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_uint16_uint8_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrb.u8 q0, [r1] +; CHECK-NEXT: vmov.u8 r1, q0[8] +; CHECK-NEXT: vmov.16 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[9] +; CHECK-NEXT: vmov.16 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[10] +; CHECK-NEXT: vmov.16 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[11] +; CHECK-NEXT: vmov.16 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[12] +; CHECK-NEXT: vmov.16 q1[4], r1 +; CHECK-NEXT: vmov.u8 r1, q0[13] +; CHECK-NEXT: vmov.16 q1[5], r1 +; CHECK-NEXT: vmov.u8 r1, q0[14] +; CHECK-NEXT: vmov.16 q1[6], r1 +; CHECK-NEXT: vmov.u8 r1, q0[15] +; CHECK-NEXT: vmov.16 q1[7], r1 +; CHECK-NEXT: vmov.u8 r1, q0[0] +; CHECK-NEXT: vmovlb.u8 q1, q1 +; CHECK-NEXT: vstrh.16 q1, [r0, #16] +; CHECK-NEXT: vmov.16 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[1] +; CHECK-NEXT: vmov.16 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[2] +; CHECK-NEXT: vmov.16 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[3] +; CHECK-NEXT: vmov.16 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[4] +; CHECK-NEXT: vmov.16 q1[4], r1 +; CHECK-NEXT: vmov.u8 r1, q0[5] +; CHECK-NEXT: vmov.16 q1[5], r1 +; CHECK-NEXT: vmov.u8 r1, q0[6] +; CHECK-NEXT: vmov.16 q1[6], r1 +; CHECK-NEXT: vmov.u8 r1, q0[7] +; CHECK-NEXT: vmov.16 q1[7], r1 +; CHECK-NEXT: vmovlb.u8 q0, q1 +; CHECK-NEXT: vstrh.16 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i8>, <16 x i8>* %src, align 1 + %0 = zext <16 x i8> %wide.load to <16 x i16> + store <16 x i16> %0, <16 x i16>* %dest, align 2 + ret void +} + +define void @foo_uint32_uint16_double(<8 x i32>* %dest, <8 x i16>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_uint32_uint16_double: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrh.u16 q0, [r1] +; CHECK-NEXT: vmov.u16 r1, q0[4] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u16 r1, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u16 r1, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u16 r1, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmov.u16 r1, q0[0] +; CHECK-NEXT: vmovlb.u16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #16] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u16 r1, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u16 r1, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u16 r1, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmovlb.u16 q0, q1 +; CHECK-NEXT: vstrw.32 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <8 x i16>, <8 x i16>* %src, align 2 + %0 = zext <8 x i16> %wide.load to <8 x i32> + store <8 x i32> %0, <8 x i32>* %dest, align 4 + ret void +} + + +define void @foo_int32_int8_both(<16 x i32>* %dest, <16 x i8>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_int32_int8_both: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrb.u8 q0, [r1] +; CHECK-NEXT: vmov.u8 r1, q0[8] +; CHECK-NEXT: vmov.16 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[9] +; CHECK-NEXT: vmov.16 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[10] +; CHECK-NEXT: vmov.16 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[11] +; CHECK-NEXT: vmov.16 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[12] +; CHECK-NEXT: vmov.16 q1[4], r1 +; CHECK-NEXT: vmov.u8 r1, q0[13] +; CHECK-NEXT: vmov.16 q1[5], r1 +; CHECK-NEXT: vmov.u8 r1, q0[14] +; CHECK-NEXT: vmov.16 q1[6], r1 +; CHECK-NEXT: vmov.u8 r1, q0[15] +; CHECK-NEXT: vmov.16 q1[7], r1 +; CHECK-NEXT: vmovlb.s8 q1, q1 +; CHECK-NEXT: vmov.u16 r1, q1[4] +; CHECK-NEXT: vmov.32 q2[0], r1 +; CHECK-NEXT: vmov.u16 r1, q1[5] +; CHECK-NEXT: vmov.32 q2[1], r1 +; CHECK-NEXT: vmov.u16 r1, q1[6] +; CHECK-NEXT: vmov.32 q2[2], r1 +; CHECK-NEXT: vmov.u16 r1, q1[7] +; CHECK-NEXT: vmov.32 q2[3], r1 +; CHECK-NEXT: vmov.u16 r1, q1[0] +; CHECK-NEXT: vmovlb.u16 q2, q2 +; CHECK-NEXT: vstrw.32 q2, [r0, #48] +; CHECK-NEXT: vmov.32 q2[0], r1 +; CHECK-NEXT: vmov.u16 r1, q1[1] +; CHECK-NEXT: vmov.32 q2[1], r1 +; CHECK-NEXT: vmov.u16 r1, q1[2] +; CHECK-NEXT: vmov.32 q2[2], r1 +; CHECK-NEXT: vmov.u16 r1, q1[3] +; CHECK-NEXT: vmov.32 q2[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[0] +; CHECK-NEXT: vmovlb.u16 q1, q2 +; CHECK-NEXT: vstrw.32 q1, [r0, #32] +; CHECK-NEXT: vmov.16 q1[0], r1 +; CHECK-NEXT: vmov.u8 r1, q0[1] +; CHECK-NEXT: vmov.16 q1[1], r1 +; CHECK-NEXT: vmov.u8 r1, q0[2] +; CHECK-NEXT: vmov.16 q1[2], r1 +; CHECK-NEXT: vmov.u8 r1, q0[3] +; CHECK-NEXT: vmov.16 q1[3], r1 +; CHECK-NEXT: vmov.u8 r1, q0[4] +; CHECK-NEXT: vmov.16 q1[4], r1 +; CHECK-NEXT: vmov.u8 r1, q0[5] +; CHECK-NEXT: vmov.16 q1[5], r1 +; CHECK-NEXT: vmov.u8 r1, q0[6] +; CHECK-NEXT: vmov.16 q1[6], r1 +; CHECK-NEXT: vmov.u8 r1, q0[7] +; CHECK-NEXT: vmov.16 q1[7], r1 +; CHECK-NEXT: vmovlb.s8 q0, q1 +; CHECK-NEXT: vmov.u16 r1, q0[4] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u16 r1, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u16 r1, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u16 r1, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmov.u16 r1, q0[0] +; CHECK-NEXT: vmovlb.u16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #16] +; CHECK-NEXT: vmov.32 q1[0], r1 +; CHECK-NEXT: vmov.u16 r1, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r1 +; CHECK-NEXT: vmov.u16 r1, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r1 +; CHECK-NEXT: vmov.u16 r1, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r1 +; CHECK-NEXT: vmovlb.u16 q0, q1 +; CHECK-NEXT: vstrw.32 q0, [r0] +; CHECK-NEXT: bx lr +entry: + %wide.load = load <16 x i8>, <16 x i8>* %src, align 1 + %0 = sext <16 x i8> %wide.load to <16 x i16> + %1 = zext <16 x i16> %0 to <16 x i32> + store <16 x i32> %1, <16 x i32>* %dest, align 4 + ret void +} + +define <8 x i16>* @foo_uint32_uint16_double_offset(<8 x i32>* %dest, <8 x i16>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_uint32_uint16_double_offset: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrh.u16 q0, [r1, #16]! +; CHECK-NEXT: vmov.u16 r2, q0[4] +; CHECK-NEXT: vmov.32 q1[0], r2 +; CHECK-NEXT: vmov.u16 r2, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r2 +; CHECK-NEXT: vmov.u16 r2, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r2 +; CHECK-NEXT: vmov.u16 r2, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r2 +; CHECK-NEXT: vmov.u16 r2, q0[0] +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #16] +; CHECK-NEXT: vmov.32 q1[0], r2 +; CHECK-NEXT: vmov.u16 r2, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r2 +; CHECK-NEXT: vmov.u16 r2, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r2 +; CHECK-NEXT: vmov.u16 r2, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r2 +; CHECK-NEXT: vmovlb.s16 q0, q1 +; CHECK-NEXT: vstrw.32 q0, [r0] +; CHECK-NEXT: mov r0, r1 +; CHECK-NEXT: bx lr +entry: + %z = getelementptr inbounds <8 x i16>, <8 x i16>* %src, i32 1 + %wide.load = load <8 x i16>, <8 x i16>* %z, align 2 + %0 = sext <8 x i16> %wide.load to <8 x i32> + store <8 x i32> %0, <8 x i32>* %dest, align 4 + ret <8 x i16>* %z +} + +define <16 x i16>* @foo_uint32_uint16_quad_offset(<16 x i32>* %dest, <16 x i16>* readonly %src, i32 %n) { +; CHECK-LABEL: foo_uint32_uint16_quad_offset: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: vldrh.u16 q1, [r1, #32]! +; CHECK-NEXT: vmov.u16 r2, q1[4] +; CHECK-NEXT: vmov.32 q0[0], r2 +; CHECK-NEXT: vmov.u16 r2, q1[5] +; CHECK-NEXT: vmov.32 q0[1], r2 +; CHECK-NEXT: vmov.u16 r2, q1[6] +; CHECK-NEXT: vmov.32 q0[2], r2 +; CHECK-NEXT: vmov.u16 r2, q1[7] +; CHECK-NEXT: vmov.32 q0[3], r2 +; CHECK-NEXT: vmov.u16 r2, q1[0] +; CHECK-NEXT: vmovlb.s16 q2, q0 +; CHECK-NEXT: vldrh.u16 q0, [r1, #16] +; CHECK-NEXT: vstrw.32 q2, [r0, #16] +; CHECK-NEXT: vmov.32 q2[0], r2 +; CHECK-NEXT: vmov.u16 r2, q1[1] +; CHECK-NEXT: vmov.32 q2[1], r2 +; CHECK-NEXT: vmov.u16 r2, q1[2] +; CHECK-NEXT: vmov.32 q2[2], r2 +; CHECK-NEXT: vmov.u16 r2, q1[3] +; CHECK-NEXT: vmov.32 q2[3], r2 +; CHECK-NEXT: vmov.u16 r2, q0[4] +; CHECK-NEXT: vmovlb.s16 q1, q2 +; CHECK-NEXT: vstrw.32 q1, [r0] +; CHECK-NEXT: vmov.32 q1[0], r2 +; CHECK-NEXT: vmov.u16 r2, q0[5] +; CHECK-NEXT: vmov.32 q1[1], r2 +; CHECK-NEXT: vmov.u16 r2, q0[6] +; CHECK-NEXT: vmov.32 q1[2], r2 +; CHECK-NEXT: vmov.u16 r2, q0[7] +; CHECK-NEXT: vmov.32 q1[3], r2 +; CHECK-NEXT: vmov.u16 r2, q0[0] +; CHECK-NEXT: vmovlb.s16 q1, q1 +; CHECK-NEXT: vstrw.32 q1, [r0, #48] +; CHECK-NEXT: vmov.32 q1[0], r2 +; CHECK-NEXT: vmov.u16 r2, q0[1] +; CHECK-NEXT: vmov.32 q1[1], r2 +; CHECK-NEXT: vmov.u16 r2, q0[2] +; CHECK-NEXT: vmov.32 q1[2], r2 +; CHECK-NEXT: vmov.u16 r2, q0[3] +; CHECK-NEXT: vmov.32 q1[3], r2 +; CHECK-NEXT: vmovlb.s16 q0, q1 +; CHECK-NEXT: vstrw.32 q0, [r0, #32] +; CHECK-NEXT: mov r0, r1 +; CHECK-NEXT: bx lr +entry: + %z = getelementptr inbounds <16 x i16>, <16 x i16>* %src, i32 1 + %wide.load = load <16 x i16>, <16 x i16>* %z, align 2 + %0 = sext <16 x i16> %wide.load to <16 x i32> + store <16 x i32> %0, <16 x i32>* %dest, align 4 + ret <16 x i16>* %z +} define void @foo_int16_int32_align1(<4 x i16>* %dest, <4 x i32>* readonly %src, i32 %n) {