; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -mtriple=x86_64-unknown -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=SSE
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=slm -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=SLM
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=+prefer-128-bit -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX128
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=-prefer-128-bit -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX256
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=+prefer-128-bit -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX128
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=-prefer-128-bit -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX256
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=knl -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX512
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=-prefer-256-bit -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX512
; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=+prefer-256-bit -basic-aa -slp-vectorizer -S | FileCheck %s --check-prefix=AVX256

@a64 = common global [8 x i64] zeroinitializer, align 64
@b64 = common global [8 x i64] zeroinitializer, align 64
@c64 = common global [8 x i64] zeroinitializer, align 64
@a32 = common global [16 x i32] zeroinitializer, align 64
@b32 = common global [16 x i32] zeroinitializer, align 64
@c32 = common global [16 x i32] zeroinitializer, align 64
@a16 = common global [32 x i16] zeroinitializer, align 64
@b16 = common global [32 x i16] zeroinitializer, align 64
@c16 = common global [32 x i16] zeroinitializer, align 64
@a8  = common global [64 x i8] zeroinitializer, align 64
@b8  = common global [64 x i8] zeroinitializer, align 64
@c8  = common global [64 x i8] zeroinitializer, align 64

define void @mul_v8i64() {
; SSE-LABEL: @mul_v8i64(
; SSE-NEXT:    [[A0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 0), align 8
; SSE-NEXT:    [[A1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 1), align 8
; SSE-NEXT:    [[A2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 2), align 8
; SSE-NEXT:    [[A3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 3), align 8
; SSE-NEXT:    [[A4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 4), align 8
; SSE-NEXT:    [[A5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 5), align 8
; SSE-NEXT:    [[A6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 6), align 8
; SSE-NEXT:    [[A7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 7), align 8
; SSE-NEXT:    [[B0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 0), align 8
; SSE-NEXT:    [[B1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 1), align 8
; SSE-NEXT:    [[B2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 2), align 8
; SSE-NEXT:    [[B3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 3), align 8
; SSE-NEXT:    [[B4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 4), align 8
; SSE-NEXT:    [[B5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 5), align 8
; SSE-NEXT:    [[B6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 6), align 8
; SSE-NEXT:    [[B7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 7), align 8
; SSE-NEXT:    [[R0:%.*]] = mul i64 [[A0]], [[B0]]
; SSE-NEXT:    [[R1:%.*]] = mul i64 [[A1]], [[B1]]
; SSE-NEXT:    [[R2:%.*]] = mul i64 [[A2]], [[B2]]
; SSE-NEXT:    [[R3:%.*]] = mul i64 [[A3]], [[B3]]
; SSE-NEXT:    [[R4:%.*]] = mul i64 [[A4]], [[B4]]
; SSE-NEXT:    [[R5:%.*]] = mul i64 [[A5]], [[B5]]
; SSE-NEXT:    [[R6:%.*]] = mul i64 [[A6]], [[B6]]
; SSE-NEXT:    [[R7:%.*]] = mul i64 [[A7]], [[B7]]
; SSE-NEXT:    store i64 [[R0]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 0), align 8
; SSE-NEXT:    store i64 [[R1]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 1), align 8
; SSE-NEXT:    store i64 [[R2]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 2), align 8
; SSE-NEXT:    store i64 [[R3]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 3), align 8
; SSE-NEXT:    store i64 [[R4]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 4), align 8
; SSE-NEXT:    store i64 [[R5]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 5), align 8
; SSE-NEXT:    store i64 [[R6]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 6), align 8
; SSE-NEXT:    store i64 [[R7]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 7), align 8
; SSE-NEXT:    ret void
;
; SLM-LABEL: @mul_v8i64(
; SLM-NEXT:    [[A0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 0), align 8
; SLM-NEXT:    [[A1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 1), align 8
; SLM-NEXT:    [[A2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 2), align 8
; SLM-NEXT:    [[A3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 3), align 8
; SLM-NEXT:    [[A4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 4), align 8
; SLM-NEXT:    [[A5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 5), align 8
; SLM-NEXT:    [[A6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 6), align 8
; SLM-NEXT:    [[A7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 7), align 8
; SLM-NEXT:    [[B0:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 0), align 8
; SLM-NEXT:    [[B1:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 1), align 8
; SLM-NEXT:    [[B2:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 2), align 8
; SLM-NEXT:    [[B3:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 3), align 8
; SLM-NEXT:    [[B4:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 4), align 8
; SLM-NEXT:    [[B5:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 5), align 8
; SLM-NEXT:    [[B6:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 6), align 8
; SLM-NEXT:    [[B7:%.*]] = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 7), align 8
; SLM-NEXT:    [[R0:%.*]] = mul i64 [[A0]], [[B0]]
; SLM-NEXT:    [[R1:%.*]] = mul i64 [[A1]], [[B1]]
; SLM-NEXT:    [[R2:%.*]] = mul i64 [[A2]], [[B2]]
; SLM-NEXT:    [[R3:%.*]] = mul i64 [[A3]], [[B3]]
; SLM-NEXT:    [[R4:%.*]] = mul i64 [[A4]], [[B4]]
; SLM-NEXT:    [[R5:%.*]] = mul i64 [[A5]], [[B5]]
; SLM-NEXT:    [[R6:%.*]] = mul i64 [[A6]], [[B6]]
; SLM-NEXT:    [[R7:%.*]] = mul i64 [[A7]], [[B7]]
; SLM-NEXT:    store i64 [[R0]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 0), align 8
; SLM-NEXT:    store i64 [[R1]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 1), align 8
; SLM-NEXT:    store i64 [[R2]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 2), align 8
; SLM-NEXT:    store i64 [[R3]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 3), align 8
; SLM-NEXT:    store i64 [[R4]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 4), align 8
; SLM-NEXT:    store i64 [[R5]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 5), align 8
; SLM-NEXT:    store i64 [[R6]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 6), align 8
; SLM-NEXT:    store i64 [[R7]], i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 7), align 8
; SLM-NEXT:    ret void
;
; AVX128-LABEL: @mul_v8i64(
; AVX128-NEXT:    [[TMP1:%.*]] = load <2 x i64>, <2 x i64>* bitcast ([8 x i64]* @a64 to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 2) to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 4) to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP4:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 6) to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP5:%.*]] = load <2 x i64>, <2 x i64>* bitcast ([8 x i64]* @b64 to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP6:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 2) to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 4) to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP8:%.*]] = load <2 x i64>, <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 6) to <2 x i64>*), align 8
; AVX128-NEXT:    [[TMP9:%.*]] = mul <2 x i64> [[TMP1]], [[TMP5]]
; AVX128-NEXT:    [[TMP10:%.*]] = mul <2 x i64> [[TMP2]], [[TMP6]]
; AVX128-NEXT:    [[TMP11:%.*]] = mul <2 x i64> [[TMP3]], [[TMP7]]
; AVX128-NEXT:    [[TMP12:%.*]] = mul <2 x i64> [[TMP4]], [[TMP8]]
; AVX128-NEXT:    store <2 x i64> [[TMP9]], <2 x i64>* bitcast ([8 x i64]* @c64 to <2 x i64>*), align 8
; AVX128-NEXT:    store <2 x i64> [[TMP10]], <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 2) to <2 x i64>*), align 8
; AVX128-NEXT:    store <2 x i64> [[TMP11]], <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 4) to <2 x i64>*), align 8
; AVX128-NEXT:    store <2 x i64> [[TMP12]], <2 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 6) to <2 x i64>*), align 8
; AVX128-NEXT:    ret void
;
; AVX256-LABEL: @mul_v8i64(
; AVX256-NEXT:    [[TMP1:%.*]] = load <4 x i64>, <4 x i64>* bitcast ([8 x i64]* @a64 to <4 x i64>*), align 8
; AVX256-NEXT:    [[TMP2:%.*]] = load <4 x i64>, <4 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 4) to <4 x i64>*), align 8
; AVX256-NEXT:    [[TMP3:%.*]] = load <4 x i64>, <4 x i64>* bitcast ([8 x i64]* @b64 to <4 x i64>*), align 8
; AVX256-NEXT:    [[TMP4:%.*]] = load <4 x i64>, <4 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 4) to <4 x i64>*), align 8
; AVX256-NEXT:    [[TMP5:%.*]] = mul <4 x i64> [[TMP1]], [[TMP3]]
; AVX256-NEXT:    [[TMP6:%.*]] = mul <4 x i64> [[TMP2]], [[TMP4]]
; AVX256-NEXT:    store <4 x i64> [[TMP5]], <4 x i64>* bitcast ([8 x i64]* @c64 to <4 x i64>*), align 8
; AVX256-NEXT:    store <4 x i64> [[TMP6]], <4 x i64>* bitcast (i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 4) to <4 x i64>*), align 8
; AVX256-NEXT:    ret void
;
; AVX512-LABEL: @mul_v8i64(
; AVX512-NEXT:    [[TMP1:%.*]] = load <8 x i64>, <8 x i64>* bitcast ([8 x i64]* @a64 to <8 x i64>*), align 8
; AVX512-NEXT:    [[TMP2:%.*]] = load <8 x i64>, <8 x i64>* bitcast ([8 x i64]* @b64 to <8 x i64>*), align 8
; AVX512-NEXT:    [[TMP3:%.*]] = mul <8 x i64> [[TMP1]], [[TMP2]]
; AVX512-NEXT:    store <8 x i64> [[TMP3]], <8 x i64>* bitcast ([8 x i64]* @c64 to <8 x i64>*), align 8
; AVX512-NEXT:    ret void
;
  %a0 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 0), align 8
  %a1 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 1), align 8
  %a2 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 2), align 8
  %a3 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 3), align 8
  %a4 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 4), align 8
  %a5 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 5), align 8
  %a6 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 6), align 8
  %a7 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @a64, i32 0, i64 7), align 8
  %b0 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 0), align 8
  %b1 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 1), align 8
  %b2 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 2), align 8
  %b3 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 3), align 8
  %b4 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 4), align 8
  %b5 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 5), align 8
  %b6 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 6), align 8
  %b7 = load i64, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @b64, i32 0, i64 7), align 8
  %r0 = mul i64 %a0, %b0
  %r1 = mul i64 %a1, %b1
  %r2 = mul i64 %a2, %b2
  %r3 = mul i64 %a3, %b3
  %r4 = mul i64 %a4, %b4
  %r5 = mul i64 %a5, %b5
  %r6 = mul i64 %a6, %b6
  %r7 = mul i64 %a7, %b7
  store i64 %r0, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 0), align 8
  store i64 %r1, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 1), align 8
  store i64 %r2, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 2), align 8
  store i64 %r3, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 3), align 8
  store i64 %r4, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 4), align 8
  store i64 %r5, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 5), align 8
  store i64 %r6, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 6), align 8
  store i64 %r7, i64* getelementptr inbounds ([8 x i64], [8 x i64]* @c64, i32 0, i64 7), align 8
  ret void
}

define void @mul_v16i32() {
; SSE-LABEL: @mul_v16i32(
; SSE-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @a32 to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 4) to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 8) to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 12) to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @b32 to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP6:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 4) to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP7:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 8) to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP8:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 12) to <4 x i32>*), align 4
; SSE-NEXT:    [[TMP9:%.*]] = mul <4 x i32> [[TMP1]], [[TMP5]]
; SSE-NEXT:    [[TMP10:%.*]] = mul <4 x i32> [[TMP2]], [[TMP6]]
; SSE-NEXT:    [[TMP11:%.*]] = mul <4 x i32> [[TMP3]], [[TMP7]]
; SSE-NEXT:    [[TMP12:%.*]] = mul <4 x i32> [[TMP4]], [[TMP8]]
; SSE-NEXT:    store <4 x i32> [[TMP9]], <4 x i32>* bitcast ([16 x i32]* @c32 to <4 x i32>*), align 4
; SSE-NEXT:    store <4 x i32> [[TMP10]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 4) to <4 x i32>*), align 4
; SSE-NEXT:    store <4 x i32> [[TMP11]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 8) to <4 x i32>*), align 4
; SSE-NEXT:    store <4 x i32> [[TMP12]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 12) to <4 x i32>*), align 4
; SSE-NEXT:    ret void
;
; SLM-LABEL: @mul_v16i32(
; SLM-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @a32 to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 4) to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 8) to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 12) to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @b32 to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP6:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 4) to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP7:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 8) to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP8:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 12) to <4 x i32>*), align 4
; SLM-NEXT:    [[TMP9:%.*]] = mul <4 x i32> [[TMP1]], [[TMP5]]
; SLM-NEXT:    [[TMP10:%.*]] = mul <4 x i32> [[TMP2]], [[TMP6]]
; SLM-NEXT:    [[TMP11:%.*]] = mul <4 x i32> [[TMP3]], [[TMP7]]
; SLM-NEXT:    [[TMP12:%.*]] = mul <4 x i32> [[TMP4]], [[TMP8]]
; SLM-NEXT:    store <4 x i32> [[TMP9]], <4 x i32>* bitcast ([16 x i32]* @c32 to <4 x i32>*), align 4
; SLM-NEXT:    store <4 x i32> [[TMP10]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 4) to <4 x i32>*), align 4
; SLM-NEXT:    store <4 x i32> [[TMP11]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 8) to <4 x i32>*), align 4
; SLM-NEXT:    store <4 x i32> [[TMP12]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 12) to <4 x i32>*), align 4
; SLM-NEXT:    ret void
;
; AVX128-LABEL: @mul_v16i32(
; AVX128-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @a32 to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 4) to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 8) to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP4:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 12) to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([16 x i32]* @b32 to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP6:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 4) to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP7:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 8) to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP8:%.*]] = load <4 x i32>, <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 12) to <4 x i32>*), align 4
; AVX128-NEXT:    [[TMP9:%.*]] = mul <4 x i32> [[TMP1]], [[TMP5]]
; AVX128-NEXT:    [[TMP10:%.*]] = mul <4 x i32> [[TMP2]], [[TMP6]]
; AVX128-NEXT:    [[TMP11:%.*]] = mul <4 x i32> [[TMP3]], [[TMP7]]
; AVX128-NEXT:    [[TMP12:%.*]] = mul <4 x i32> [[TMP4]], [[TMP8]]
; AVX128-NEXT:    store <4 x i32> [[TMP9]], <4 x i32>* bitcast ([16 x i32]* @c32 to <4 x i32>*), align 4
; AVX128-NEXT:    store <4 x i32> [[TMP10]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 4) to <4 x i32>*), align 4
; AVX128-NEXT:    store <4 x i32> [[TMP11]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 8) to <4 x i32>*), align 4
; AVX128-NEXT:    store <4 x i32> [[TMP12]], <4 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 12) to <4 x i32>*), align 4
; AVX128-NEXT:    ret void
;
; AVX256-LABEL: @mul_v16i32(
; AVX256-NEXT:    [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* bitcast ([16 x i32]* @a32 to <8 x i32>*), align 4
; AVX256-NEXT:    [[TMP2:%.*]] = load <8 x i32>, <8 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 8) to <8 x i32>*), align 4
; AVX256-NEXT:    [[TMP3:%.*]] = load <8 x i32>, <8 x i32>* bitcast ([16 x i32]* @b32 to <8 x i32>*), align 4
; AVX256-NEXT:    [[TMP4:%.*]] = load <8 x i32>, <8 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 8) to <8 x i32>*), align 4
; AVX256-NEXT:    [[TMP5:%.*]] = mul <8 x i32> [[TMP1]], [[TMP3]]
; AVX256-NEXT:    [[TMP6:%.*]] = mul <8 x i32> [[TMP2]], [[TMP4]]
; AVX256-NEXT:    store <8 x i32> [[TMP5]], <8 x i32>* bitcast ([16 x i32]* @c32 to <8 x i32>*), align 4
; AVX256-NEXT:    store <8 x i32> [[TMP6]], <8 x i32>* bitcast (i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 8) to <8 x i32>*), align 4
; AVX256-NEXT:    ret void
;
; AVX512-LABEL: @mul_v16i32(
; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i32>, <16 x i32>* bitcast ([16 x i32]* @a32 to <16 x i32>*), align 4
; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i32>, <16 x i32>* bitcast ([16 x i32]* @b32 to <16 x i32>*), align 4
; AVX512-NEXT:    [[TMP3:%.*]] = mul <16 x i32> [[TMP1]], [[TMP2]]
; AVX512-NEXT:    store <16 x i32> [[TMP3]], <16 x i32>* bitcast ([16 x i32]* @c32 to <16 x i32>*), align 4
; AVX512-NEXT:    ret void
;
  %a0  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 0 ), align 4
  %a1  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 1 ), align 4
  %a2  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 2 ), align 4
  %a3  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 3 ), align 4
  %a4  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 4 ), align 4
  %a5  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 5 ), align 4
  %a6  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 6 ), align 4
  %a7  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 7 ), align 4
  %a8  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 8 ), align 4
  %a9  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 9 ), align 4
  %a10 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 10), align 4
  %a11 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 11), align 4
  %a12 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 12), align 4
  %a13 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 13), align 4
  %a14 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 14), align 4
  %a15 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @a32, i32 0, i64 15), align 4
  %b0  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 0 ), align 4
  %b1  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 1 ), align 4
  %b2  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 2 ), align 4
  %b3  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 3 ), align 4
  %b4  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 4 ), align 4
  %b5  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 5 ), align 4
  %b6  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 6 ), align 4
  %b7  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 7 ), align 4
  %b8  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 8 ), align 4
  %b9  = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 9 ), align 4
  %b10 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 10), align 4
  %b11 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 11), align 4
  %b12 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 12), align 4
  %b13 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 13), align 4
  %b14 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 14), align 4
  %b15 = load i32, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @b32, i32 0, i64 15), align 4
  %r0  = mul i32 %a0 , %b0
  %r1  = mul i32 %a1 , %b1
  %r2  = mul i32 %a2 , %b2
  %r3  = mul i32 %a3 , %b3
  %r4  = mul i32 %a4 , %b4
  %r5  = mul i32 %a5 , %b5
  %r6  = mul i32 %a6 , %b6
  %r7  = mul i32 %a7 , %b7
  %r8  = mul i32 %a8 , %b8
  %r9  = mul i32 %a9 , %b9
  %r10 = mul i32 %a10, %b10
  %r11 = mul i32 %a11, %b11
  %r12 = mul i32 %a12, %b12
  %r13 = mul i32 %a13, %b13
  %r14 = mul i32 %a14, %b14
  %r15 = mul i32 %a15, %b15
  store i32 %r0 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 0 ), align 4
  store i32 %r1 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 1 ), align 4
  store i32 %r2 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 2 ), align 4
  store i32 %r3 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 3 ), align 4
  store i32 %r4 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 4 ), align 4
  store i32 %r5 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 5 ), align 4
  store i32 %r6 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 6 ), align 4
  store i32 %r7 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 7 ), align 4
  store i32 %r8 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 8 ), align 4
  store i32 %r9 , i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 9 ), align 4
  store i32 %r10, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 10), align 4
  store i32 %r11, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 11), align 4
  store i32 %r12, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 12), align 4
  store i32 %r13, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 13), align 4
  store i32 %r14, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 14), align 4
  store i32 %r15, i32* getelementptr inbounds ([16 x i32], [16 x i32]* @c32, i32 0, i64 15), align 4
  ret void
}

define void @mul_v32i16() {
; SSE-LABEL: @mul_v32i16(
; SSE-NEXT:    [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @a16 to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP4:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 24) to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP5:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @b16 to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP6:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP7:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP8:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 24) to <8 x i16>*), align 2
; SSE-NEXT:    [[TMP9:%.*]] = mul <8 x i16> [[TMP1]], [[TMP5]]
; SSE-NEXT:    [[TMP10:%.*]] = mul <8 x i16> [[TMP2]], [[TMP6]]
; SSE-NEXT:    [[TMP11:%.*]] = mul <8 x i16> [[TMP3]], [[TMP7]]
; SSE-NEXT:    [[TMP12:%.*]] = mul <8 x i16> [[TMP4]], [[TMP8]]
; SSE-NEXT:    store <8 x i16> [[TMP9]], <8 x i16>* bitcast ([32 x i16]* @c16 to <8 x i16>*), align 2
; SSE-NEXT:    store <8 x i16> [[TMP10]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 8) to <8 x i16>*), align 2
; SSE-NEXT:    store <8 x i16> [[TMP11]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <8 x i16>*), align 2
; SSE-NEXT:    store <8 x i16> [[TMP12]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 24) to <8 x i16>*), align 2
; SSE-NEXT:    ret void
;
; SLM-LABEL: @mul_v32i16(
; SLM-NEXT:    [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @a16 to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 8) to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP4:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 24) to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP5:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @b16 to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP6:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 8) to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP7:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP8:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 24) to <8 x i16>*), align 2
; SLM-NEXT:    [[TMP9:%.*]] = mul <8 x i16> [[TMP1]], [[TMP5]]
; SLM-NEXT:    [[TMP10:%.*]] = mul <8 x i16> [[TMP2]], [[TMP6]]
; SLM-NEXT:    [[TMP11:%.*]] = mul <8 x i16> [[TMP3]], [[TMP7]]
; SLM-NEXT:    [[TMP12:%.*]] = mul <8 x i16> [[TMP4]], [[TMP8]]
; SLM-NEXT:    store <8 x i16> [[TMP9]], <8 x i16>* bitcast ([32 x i16]* @c16 to <8 x i16>*), align 2
; SLM-NEXT:    store <8 x i16> [[TMP10]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 8) to <8 x i16>*), align 2
; SLM-NEXT:    store <8 x i16> [[TMP11]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <8 x i16>*), align 2
; SLM-NEXT:    store <8 x i16> [[TMP12]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 24) to <8 x i16>*), align 2
; SLM-NEXT:    ret void
;
; AVX128-LABEL: @mul_v32i16(
; AVX128-NEXT:    [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @a16 to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 8) to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP3:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP4:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 24) to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP5:%.*]] = load <8 x i16>, <8 x i16>* bitcast ([32 x i16]* @b16 to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP6:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 8) to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP7:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP8:%.*]] = load <8 x i16>, <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 24) to <8 x i16>*), align 2
; AVX128-NEXT:    [[TMP9:%.*]] = mul <8 x i16> [[TMP1]], [[TMP5]]
; AVX128-NEXT:    [[TMP10:%.*]] = mul <8 x i16> [[TMP2]], [[TMP6]]
; AVX128-NEXT:    [[TMP11:%.*]] = mul <8 x i16> [[TMP3]], [[TMP7]]
; AVX128-NEXT:    [[TMP12:%.*]] = mul <8 x i16> [[TMP4]], [[TMP8]]
; AVX128-NEXT:    store <8 x i16> [[TMP9]], <8 x i16>* bitcast ([32 x i16]* @c16 to <8 x i16>*), align 2
; AVX128-NEXT:    store <8 x i16> [[TMP10]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 8) to <8 x i16>*), align 2
; AVX128-NEXT:    store <8 x i16> [[TMP11]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <8 x i16>*), align 2
; AVX128-NEXT:    store <8 x i16> [[TMP12]], <8 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 24) to <8 x i16>*), align 2
; AVX128-NEXT:    ret void
;
; AVX256-LABEL: @mul_v32i16(
; AVX256-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
; AVX256-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
; AVX256-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
; AVX256-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
; AVX256-NEXT:    [[TMP5:%.*]] = mul <16 x i16> [[TMP1]], [[TMP3]]
; AVX256-NEXT:    [[TMP6:%.*]] = mul <16 x i16> [[TMP2]], [[TMP4]]
; AVX256-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
; AVX256-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
; AVX256-NEXT:    ret void
;
; AVX512-LABEL: @mul_v32i16(
; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
; AVX512-NEXT:    [[TMP3:%.*]] = mul <32 x i16> [[TMP1]], [[TMP2]]
; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
; AVX512-NEXT:    ret void
;
  %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
  %a1  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 1 ), align 2
  %a2  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 2 ), align 2
  %a3  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 3 ), align 2
  %a4  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 4 ), align 2
  %a5  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 5 ), align 2
  %a6  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 6 ), align 2
  %a7  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 7 ), align 2
  %a8  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 8 ), align 2
  %a9  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 9 ), align 2
  %a10 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 10), align 2
  %a11 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 11), align 2
  %a12 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 12), align 2
  %a13 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 13), align 2
  %a14 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 14), align 2
  %a15 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 15), align 2
  %a16 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16), align 2
  %a17 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 17), align 2
  %a18 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 18), align 2
  %a19 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 19), align 2
  %a20 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 20), align 2
  %a21 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 21), align 2
  %a22 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 22), align 2
  %a23 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 23), align 2
  %a24 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 24), align 2
  %a25 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 25), align 2
  %a26 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 26), align 2
  %a27 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 27), align 2
  %a28 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 28), align 2
  %a29 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 29), align 2
  %a30 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 30), align 2
  %a31 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 31), align 2
  %b0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 0 ), align 2
  %b1  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 1 ), align 2
  %b2  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 2 ), align 2
  %b3  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 3 ), align 2
  %b4  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 4 ), align 2
  %b5  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 5 ), align 2
  %b6  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 6 ), align 2
  %b7  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 7 ), align 2
  %b8  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 8 ), align 2
  %b9  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 9 ), align 2
  %b10 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 10), align 2
  %b11 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 11), align 2
  %b12 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 12), align 2
  %b13 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 13), align 2
  %b14 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 14), align 2
  %b15 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 15), align 2
  %b16 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16), align 2
  %b17 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 17), align 2
  %b18 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 18), align 2
  %b19 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 19), align 2
  %b20 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 20), align 2
  %b21 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 21), align 2
  %b22 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 22), align 2
  %b23 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 23), align 2
  %b24 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 24), align 2
  %b25 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 25), align 2
  %b26 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 26), align 2
  %b27 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 27), align 2
  %b28 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 28), align 2
  %b29 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 29), align 2
  %b30 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 30), align 2
  %b31 = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 31), align 2
  %r0  = mul i16 %a0 , %b0
  %r1  = mul i16 %a1 , %b1
  %r2  = mul i16 %a2 , %b2
  %r3  = mul i16 %a3 , %b3
  %r4  = mul i16 %a4 , %b4
  %r5  = mul i16 %a5 , %b5
  %r6  = mul i16 %a6 , %b6
  %r7  = mul i16 %a7 , %b7
  %r8  = mul i16 %a8 , %b8
  %r9  = mul i16 %a9 , %b9
  %r10 = mul i16 %a10, %b10
  %r11 = mul i16 %a11, %b11
  %r12 = mul i16 %a12, %b12
  %r13 = mul i16 %a13, %b13
  %r14 = mul i16 %a14, %b14
  %r15 = mul i16 %a15, %b15
  %r16 = mul i16 %a16, %b16
  %r17 = mul i16 %a17, %b17
  %r18 = mul i16 %a18, %b18
  %r19 = mul i16 %a19, %b19
  %r20 = mul i16 %a20, %b20
  %r21 = mul i16 %a21, %b21
  %r22 = mul i16 %a22, %b22
  %r23 = mul i16 %a23, %b23
  %r24 = mul i16 %a24, %b24
  %r25 = mul i16 %a25, %b25
  %r26 = mul i16 %a26, %b26
  %r27 = mul i16 %a27, %b27
  %r28 = mul i16 %a28, %b28
  %r29 = mul i16 %a29, %b29
  %r30 = mul i16 %a30, %b30
  %r31 = mul i16 %a31, %b31
  store i16 %r0 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 0 ), align 2
  store i16 %r1 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 1 ), align 2
  store i16 %r2 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 2 ), align 2
  store i16 %r3 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 3 ), align 2
  store i16 %r4 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 4 ), align 2
  store i16 %r5 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 5 ), align 2
  store i16 %r6 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 6 ), align 2
  store i16 %r7 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 7 ), align 2
  store i16 %r8 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 8 ), align 2
  store i16 %r9 , i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 9 ), align 2
  store i16 %r10, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 10), align 2
  store i16 %r11, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 11), align 2
  store i16 %r12, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 12), align 2
  store i16 %r13, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 13), align 2
  store i16 %r14, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 14), align 2
  store i16 %r15, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 15), align 2
  store i16 %r16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16), align 2
  store i16 %r17, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 17), align 2
  store i16 %r18, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 18), align 2
  store i16 %r19, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 19), align 2
  store i16 %r20, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 20), align 2
  store i16 %r21, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 21), align 2
  store i16 %r22, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 22), align 2
  store i16 %r23, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 23), align 2
  store i16 %r24, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 24), align 2
  store i16 %r25, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 25), align 2
  store i16 %r26, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 26), align 2
  store i16 %r27, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 27), align 2
  store i16 %r28, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 28), align 2
  store i16 %r29, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 29), align 2
  store i16 %r30, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 30), align 2
  store i16 %r31, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 31), align 2
  ret void
}

define void @mul_v64i8() {
; SSE-LABEL: @mul_v64i8(
; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
; SSE-NEXT:    [[TMP9:%.*]] = mul <16 x i8> [[TMP1]], [[TMP5]]
; SSE-NEXT:    [[TMP10:%.*]] = mul <16 x i8> [[TMP2]], [[TMP6]]
; SSE-NEXT:    [[TMP11:%.*]] = mul <16 x i8> [[TMP3]], [[TMP7]]
; SSE-NEXT:    [[TMP12:%.*]] = mul <16 x i8> [[TMP4]], [[TMP8]]
; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
; SSE-NEXT:    ret void
;
; SLM-LABEL: @mul_v64i8(
; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
; SLM-NEXT:    [[TMP9:%.*]] = mul <16 x i8> [[TMP1]], [[TMP5]]
; SLM-NEXT:    [[TMP10:%.*]] = mul <16 x i8> [[TMP2]], [[TMP6]]
; SLM-NEXT:    [[TMP11:%.*]] = mul <16 x i8> [[TMP3]], [[TMP7]]
; SLM-NEXT:    [[TMP12:%.*]] = mul <16 x i8> [[TMP4]], [[TMP8]]
; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
; SLM-NEXT:    ret void
;
; AVX128-LABEL: @mul_v64i8(
; AVX128-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
; AVX128-NEXT:    [[TMP9:%.*]] = mul <16 x i8> [[TMP1]], [[TMP5]]
; AVX128-NEXT:    [[TMP10:%.*]] = mul <16 x i8> [[TMP2]], [[TMP6]]
; AVX128-NEXT:    [[TMP11:%.*]] = mul <16 x i8> [[TMP3]], [[TMP7]]
; AVX128-NEXT:    [[TMP12:%.*]] = mul <16 x i8> [[TMP4]], [[TMP8]]
; AVX128-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
; AVX128-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
; AVX128-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
; AVX128-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
; AVX128-NEXT:    ret void
;
; AVX256-LABEL: @mul_v64i8(
; AVX256-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
; AVX256-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
; AVX256-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
; AVX256-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
; AVX256-NEXT:    [[TMP5:%.*]] = mul <32 x i8> [[TMP1]], [[TMP3]]
; AVX256-NEXT:    [[TMP6:%.*]] = mul <32 x i8> [[TMP2]], [[TMP4]]
; AVX256-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
; AVX256-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
; AVX256-NEXT:    ret void
;
; AVX512-LABEL: @mul_v64i8(
; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
; AVX512-NEXT:    [[TMP3:%.*]] = mul <64 x i8> [[TMP1]], [[TMP2]]
; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
; AVX512-NEXT:    ret void
;
  %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
  %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
  %a2  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 2 ), align 1
  %a3  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 3 ), align 1
  %a4  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 4 ), align 1
  %a5  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 5 ), align 1
  %a6  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 6 ), align 1
  %a7  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 7 ), align 1
  %a8  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 8 ), align 1
  %a9  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 9 ), align 1
  %a10 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 10), align 1
  %a11 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 11), align 1
  %a12 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 12), align 1
  %a13 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 13), align 1
  %a14 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 14), align 1
  %a15 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 15), align 1
  %a16 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16), align 1
  %a17 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 17), align 1
  %a18 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 18), align 1
  %a19 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 19), align 1
  %a20 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 20), align 1
  %a21 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 21), align 1
  %a22 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 22), align 1
  %a23 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 23), align 1
  %a24 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 24), align 1
  %a25 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 25), align 1
  %a26 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 26), align 1
  %a27 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 27), align 1
  %a28 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 28), align 1
  %a29 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 29), align 1
  %a30 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 30), align 1
  %a31 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 31), align 1
  %a32 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32), align 1
  %a33 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 33), align 1
  %a34 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 34), align 1
  %a35 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 35), align 1
  %a36 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 36), align 1
  %a37 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 37), align 1
  %a38 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 38), align 1
  %a39 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 39), align 1
  %a40 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 40), align 1
  %a41 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 41), align 1
  %a42 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 42), align 1
  %a43 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 43), align 1
  %a44 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 44), align 1
  %a45 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 45), align 1
  %a46 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 46), align 1
  %a47 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 47), align 1
  %a48 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48), align 1
  %a49 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 49), align 1
  %a50 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 50), align 1
  %a51 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 51), align 1
  %a52 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 52), align 1
  %a53 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 53), align 1
  %a54 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 54), align 1
  %a55 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 55), align 1
  %a56 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 56), align 1
  %a57 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 57), align 1
  %a58 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 58), align 1
  %a59 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 59), align 1
  %a60 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 60), align 1
  %a61 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 61), align 1
  %a62 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 62), align 1
  %a63 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 63), align 1
  %b0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 0 ), align 1
  %b1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 1 ), align 1
  %b2  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 2 ), align 1
  %b3  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 3 ), align 1
  %b4  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 4 ), align 1
  %b5  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 5 ), align 1
  %b6  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 6 ), align 1
  %b7  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 7 ), align 1
  %b8  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 8 ), align 1
  %b9  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 9 ), align 1
  %b10 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 10), align 1
  %b11 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 11), align 1
  %b12 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 12), align 1
  %b13 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 13), align 1
  %b14 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 14), align 1
  %b15 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 15), align 1
  %b16 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16), align 1
  %b17 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 17), align 1
  %b18 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 18), align 1
  %b19 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 19), align 1
  %b20 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 20), align 1
  %b21 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 21), align 1
  %b22 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 22), align 1
  %b23 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 23), align 1
  %b24 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 24), align 1
  %b25 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 25), align 1
  %b26 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 26), align 1
  %b27 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 27), align 1
  %b28 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 28), align 1
  %b29 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 29), align 1
  %b30 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 30), align 1
  %b31 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 31), align 1
  %b32 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32), align 1
  %b33 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 33), align 1
  %b34 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 34), align 1
  %b35 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 35), align 1
  %b36 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 36), align 1
  %b37 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 37), align 1
  %b38 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 38), align 1
  %b39 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 39), align 1
  %b40 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 40), align 1
  %b41 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 41), align 1
  %b42 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 42), align 1
  %b43 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 43), align 1
  %b44 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 44), align 1
  %b45 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 45), align 1
  %b46 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 46), align 1
  %b47 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 47), align 1
  %b48 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48), align 1
  %b49 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 49), align 1
  %b50 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 50), align 1
  %b51 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 51), align 1
  %b52 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 52), align 1
  %b53 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 53), align 1
  %b54 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 54), align 1
  %b55 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 55), align 1
  %b56 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 56), align 1
  %b57 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 57), align 1
  %b58 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 58), align 1
  %b59 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 59), align 1
  %b60 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 60), align 1
  %b61 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 61), align 1
  %b62 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 62), align 1
  %b63 = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 63), align 1
  %r0  = mul i8 %a0 , %b0
  %r1  = mul i8 %a1 , %b1
  %r2  = mul i8 %a2 , %b2
  %r3  = mul i8 %a3 , %b3
  %r4  = mul i8 %a4 , %b4
  %r5  = mul i8 %a5 , %b5
  %r6  = mul i8 %a6 , %b6
  %r7  = mul i8 %a7 , %b7
  %r8  = mul i8 %a8 , %b8
  %r9  = mul i8 %a9 , %b9
  %r10 = mul i8 %a10, %b10
  %r11 = mul i8 %a11, %b11
  %r12 = mul i8 %a12, %b12
  %r13 = mul i8 %a13, %b13
  %r14 = mul i8 %a14, %b14
  %r15 = mul i8 %a15, %b15
  %r16 = mul i8 %a16, %b16
  %r17 = mul i8 %a17, %b17
  %r18 = mul i8 %a18, %b18
  %r19 = mul i8 %a19, %b19
  %r20 = mul i8 %a20, %b20
  %r21 = mul i8 %a21, %b21
  %r22 = mul i8 %a22, %b22
  %r23 = mul i8 %a23, %b23
  %r24 = mul i8 %a24, %b24
  %r25 = mul i8 %a25, %b25
  %r26 = mul i8 %a26, %b26
  %r27 = mul i8 %a27, %b27
  %r28 = mul i8 %a28, %b28
  %r29 = mul i8 %a29, %b29
  %r30 = mul i8 %a30, %b30
  %r31 = mul i8 %a31, %b31
  %r32 = mul i8 %a32, %b32
  %r33 = mul i8 %a33, %b33
  %r34 = mul i8 %a34, %b34
  %r35 = mul i8 %a35, %b35
  %r36 = mul i8 %a36, %b36
  %r37 = mul i8 %a37, %b37
  %r38 = mul i8 %a38, %b38
  %r39 = mul i8 %a39, %b39
  %r40 = mul i8 %a40, %b40
  %r41 = mul i8 %a41, %b41
  %r42 = mul i8 %a42, %b42
  %r43 = mul i8 %a43, %b43
  %r44 = mul i8 %a44, %b44
  %r45 = mul i8 %a45, %b45
  %r46 = mul i8 %a46, %b46
  %r47 = mul i8 %a47, %b47
  %r48 = mul i8 %a48, %b48
  %r49 = mul i8 %a49, %b49
  %r50 = mul i8 %a50, %b50
  %r51 = mul i8 %a51, %b51
  %r52 = mul i8 %a52, %b52
  %r53 = mul i8 %a53, %b53
  %r54 = mul i8 %a54, %b54
  %r55 = mul i8 %a55, %b55
  %r56 = mul i8 %a56, %b56
  %r57 = mul i8 %a57, %b57
  %r58 = mul i8 %a58, %b58
  %r59 = mul i8 %a59, %b59
  %r60 = mul i8 %a60, %b60
  %r61 = mul i8 %a61, %b61
  %r62 = mul i8 %a62, %b62
  %r63 = mul i8 %a63, %b63
  store i8 %r0 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 0 ), align 1
  store i8 %r1 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 1 ), align 1
  store i8 %r2 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 2 ), align 1
  store i8 %r3 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 3 ), align 1
  store i8 %r4 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 4 ), align 1
  store i8 %r5 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 5 ), align 1
  store i8 %r6 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 6 ), align 1
  store i8 %r7 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 7 ), align 1
  store i8 %r8 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 8 ), align 1
  store i8 %r9 , i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 9 ), align 1
  store i8 %r10, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 10), align 1
  store i8 %r11, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 11), align 1
  store i8 %r12, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 12), align 1
  store i8 %r13, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 13), align 1
  store i8 %r14, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 14), align 1
  store i8 %r15, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 15), align 1
  store i8 %r16, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16), align 1
  store i8 %r17, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 17), align 1
  store i8 %r18, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 18), align 1
  store i8 %r19, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 19), align 1
  store i8 %r20, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 20), align 1
  store i8 %r21, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 21), align 1
  store i8 %r22, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 22), align 1
  store i8 %r23, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 23), align 1
  store i8 %r24, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 24), align 1
  store i8 %r25, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 25), align 1
  store i8 %r26, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 26), align 1
  store i8 %r27, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 27), align 1
  store i8 %r28, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 28), align 1
  store i8 %r29, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 29), align 1
  store i8 %r30, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 30), align 1
  store i8 %r31, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 31), align 1
  store i8 %r32, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32), align 1
  store i8 %r33, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 33), align 1
  store i8 %r34, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 34), align 1
  store i8 %r35, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 35), align 1
  store i8 %r36, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 36), align 1
  store i8 %r37, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 37), align 1
  store i8 %r38, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 38), align 1
  store i8 %r39, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 39), align 1
  store i8 %r40, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 40), align 1
  store i8 %r41, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 41), align 1
  store i8 %r42, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 42), align 1
  store i8 %r43, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 43), align 1
  store i8 %r44, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 44), align 1
  store i8 %r45, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 45), align 1
  store i8 %r46, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 46), align 1
  store i8 %r47, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 47), align 1
  store i8 %r48, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48), align 1
  store i8 %r49, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 49), align 1
  store i8 %r50, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 50), align 1
  store i8 %r51, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 51), align 1
  store i8 %r52, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 52), align 1
  store i8 %r53, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 53), align 1
  store i8 %r54, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 54), align 1
  store i8 %r55, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 55), align 1
  store i8 %r56, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 56), align 1
  store i8 %r57, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 57), align 1
  store i8 %r58, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 58), align 1
  store i8 %r59, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 59), align 1
  store i8 %r60, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 60), align 1
  store i8 %r61, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 61), align 1
  store i8 %r62, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 62), align 1
  store i8 %r63, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 63), align 1
  ret void
}