[PPC64][VSX] Add short, char, and bool data type for vec_vsx_ld and vec_vsx_st intrinsics

[cycheng]

Summary

Issue: https://llvm.org/bugs/show_bug.cgi?id=26720

Fix compile error when building ffmpeg for PowerPC64LE because of some vec_vsx_ld/vec_vsx_st intrinsics are not supported by current clang.

New added intrinsics:

1. (vector) {signed|unsigned} {short|char} vec_vsx_ld: (total: 8)
2. bool vec_vsx_ld: (total: 1)
3. (vector) {signed|unsigned} {short|char} vec_vsx_st: (total: 8)
4. bool vec_vsx_st: (total: 1)

Total: 18 intrinsics

[kbarton]

LGTM.
I will commit this a bit later, when I'll be around to watch the bots.

[kbarton]

This failed testing:

---

Testing: 0 .. 10.. 20.. 30.. 40.. 50.. 60.. 70.. 80.. 90..

1 warning(s) in tests.
Testing Time: 225.81s

---

Failing Tests (1):

  Clang :: CodeGen/builtins-ppc-vsx.c

Expected Passes    : 25406
Expected Failures  : 166
Unsupported Tests  : 558
Unexpected Failures: 1

gmake[3]: * [CMakeFiles/check-all] Error 1
gmake[2]: * [CMakeFiles/check-all.dir/all] Error 2
gmake[1]: * [CMakeFiles/check-all.dir/rule] Error 2
gmake: * [check-all] Error 2
Test finished. Check results in /home/kbarton/llvm/build/dev.git/CHECK.log
Tests PASSED!

Reproduce with:
llvm-lit tools/clang/test/CodeGen/builtins-ppc-vsx.c

[cycheng]

Fix clang testing failure.
Thanks Kit!

I have checked the result by: make check-all
Testing result:

Testing Time: 33.36s
  Expected Passes    : 24505
  Expected Failures  : 152
  Unsupported Tests  : 365
[100%] Built target check-all

[kbarton]

Committed r262359

lib/Headers/altivec.h

vec_vsx_ld(int __a, const vector unsigned long long *__b) {
   return (vector unsigned long long)__builtin_vsx_lxvd2x(__a, __b);
 }
 
 static vector double __ATTRS_o_ai vec_vsx_ld(int __a,
                                              const vector double *__b) {
   return (vector double)__builtin_vsx_lxvd2x(__a, __b);
 }
 
+static vector signed short __ATTRS_o_ai
+vec_vsx_ld(int __a, const vector signed short *__b) {
+  return (vector signed short)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector signed short __ATTRS_o_ai
+vec_vsx_ld(int __a, const signed short *__b) {
+  return (vector signed short)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector unsigned short __ATTRS_o_ai
+vec_vsx_ld(int __a, const vector unsigned short *__b) {
+  return (vector unsigned short)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector unsigned short __ATTRS_o_ai
+vec_vsx_ld(int __a, const unsigned short *__b) {
+  return (vector unsigned short)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector bool char __ATTRS_o_ai
+vec_vsx_ld(int __a, const vector bool char *__b) {
+  return (vector bool char)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector signed char __ATTRS_o_ai
+vec_vsx_ld(int __a, const vector signed char *__b) {
+  return (vector signed char)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector signed char __ATTRS_o_ai
+vec_vsx_ld(int __a, const signed char *__b) {
+  return (vector signed char)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector unsigned char __ATTRS_o_ai
+vec_vsx_ld(int __a, const vector unsigned char *__b) {
+  return (vector unsigned char)__builtin_vsx_lxvw4x(__a, __b);
+}
+
+static vector unsigned char __ATTRS_o_ai
+vec_vsx_ld(int __a, const unsigned char *__b) {
+  return (vector unsigned char)__builtin_vsx_lxvw4x(__a, __b);
+}
+
 #endif
 
 /* vec_vsx_st */
 
 #ifdef __VSX__
 
 static void __ATTRS_o_ai vec_vsx_st(vector signed int __a, int __b,
                                     vector signed int *__c) {
   __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
 }
 
+static void __ATTRS_o_ai vec_vsx_st(vector signed int __a, int __b,
+                                           signed int *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
 static void __ATTRS_o_ai vec_vsx_st(vector unsigned int __a, int __b,
                                     vector unsigned int *__c) {
   __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
 }
 
+static void __ATTRS_o_ai vec_vsx_st(vector unsigned int __a, int __b,
+                                           unsigned int *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
 static void __ATTRS_o_ai vec_vsx_st(vector float __a, int __b,
                                     vector float *__c) {
   __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
 }
 
 static void __ATTRS_o_ai vec_vsx_st(vector signed long long __a, int __b,
                                     vector signed long long *__c) {
   __builtin_vsx_stxvd2x((vector double)__a, __b, __c);
 }
 
 static void __ATTRS_o_ai vec_vsx_st(vector unsigned long long __a, int __b,
                                     vector unsigned long long *__c) {
   __builtin_vsx_stxvd2x((vector double)__a, __b, __c);
 }
 
 static void __ATTRS_o_ai vec_vsx_st(vector double __a, int __b,
                                     vector double *__c) {
   __builtin_vsx_stxvd2x((vector double)__a, __b, __c);
 }
 
+static void __ATTRS_o_ai vec_vsx_st(vector signed short __a, int __b,
+                                    vector signed short *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector signed short __a, int __b,
+                                           signed short *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector unsigned short __a, int __b,
+                                    vector unsigned short *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector unsigned short __a, int __b,
+                                           unsigned short *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector signed char __a, int __b,
+                                    vector signed char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector signed char __a, int __b,
+                                           signed char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector unsigned char __a, int __b,
+                                    vector unsigned char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector unsigned char __a, int __b,
+                                           unsigned char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector bool char __a, int __b,
+                                    vector bool char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector bool char __a, int __b,
+                                           signed char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
+static void __ATTRS_o_ai vec_vsx_st(vector bool char __a, int __b,
+                                           unsigned char *__c) {
+  __builtin_vsx_stxvw4x((vector int)__a, __b, __c);
+}
+
 #endif
 
 /* vec_xor */
 
 #define __builtin_altivec_vxor vec_xor
 
 static vector signed char __ATTRS_o_ai vec_xor(vector signed char __a,
                                                vector signed char __b) {

test/CodeGen/builtins-ppc-vsx.c

 // REQUIRES: powerpc-registered-target
 // RUN: %clang_cc1 -faltivec -target-feature +vsx -triple powerpc64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
 // RUN: %clang_cc1 -faltivec -target-feature +vsx -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK-LE
 
+vector signed char vsc = { -8,  9, -10, 11, -12, 13, -14, 15,
+                           -0,  1,  -2,  3,  -4,  5,  -6,  7};
 vector unsigned char vuc = { 8,  9, 10, 11, 12, 13, 14, 15,
                              0,  1,  2,  3,  4,  5,  6,  7};
+vector bool char vbc = { 0, 1, 0, 1, 0, 1, 0, 1,
+                         0, 1, 0, 1, 0, 1, 0, 1 };
 vector float vf = { -1.5, 2.5, -3.5, 4.5 };
 vector double vd = { 3.5, -7.5 };
 vector signed int vsi = { -1, 2, -3, 4 };
 vector unsigned int vui = { 0, 1, 2, 3 };
 vector bool long long vbll = { 1, 0 };
 vector signed long long vsll = { 255LL, -937LL };
 vector unsigned long long vull = { 1447LL, 2894LL };
+vector signed short vss = { -1, 2, -3, 4, -5, 6, -7, 8 };
+vector unsigned short vus = { 0, 1, 2, 3, 4, 5, 6, 7 };
 double d = 23.4;
+signed char sc = { -8,  9, -10, 11, -12, 13, -14, 15,
+                   -0,  1,  -2,  3,  -4,  5,  -6,  7};
+unsigned char uc = { 8,  9, 10, 11, 12, 13, 14, 15,
+                     0,  1,  2,  3,  4,  5,  6,  7};
+signed short ss = { -1, 2, -3, 4, -5, 6, -7, 8 };
+unsigned short us = { 0, 1, 2, 3, 4, 5, 6, 7 };
 
 vector float res_vf;
 vector double res_vd;
 vector signed int res_vsi;
 vector unsigned int res_vui;
 vector bool int res_vbi;
 vector bool long long res_vbll;
 vector signed long long res_vsll;
 vector unsigned long long res_vull;
+vector signed short res_vss;
+vector unsigned short res_vus;
+vector bool char res_vbc;
+vector signed char res_vsc;
+vector unsigned char res_vuc;
+
 double res_d;
+signed char res_sc;
+unsigned char res_uc;
+signed short res_ss;
+unsigned short res_us;
 
 void dummy() { }
 
 void test1() {
 // CHECK-LABEL: define void @test1
 // CHECK-LE-LABEL: define void @test1
 
   res_vd = vec_add(vd, vd);
// CHECK-LE: @llvm.ppc.vsx.lxvd2x
   res_vull = vec_vsx_ld(0, &vull);
 // CHECK: @llvm.ppc.vsx.lxvd2x
 // CHECK-LE: @llvm.ppc.vsx.lxvd2x
 
   res_vd = vec_vsx_ld(0, &vd);
 // CHECK: @llvm.ppc.vsx.lxvd2x
 // CHECK-LE: @llvm.ppc.vsx.lxvd2x
 
+  res_vull = vec_vsx_ld(0, &vull);
+// CHECK: @llvm.ppc.vsx.lxvd2x
+// CHECK-LE: @llvm.ppc.vsx.lxvd2x
+
+  res_vd = vec_vsx_ld(0, &vd);
+// CHECK: @llvm.ppc.vsx.lxvd2x
+// CHECK-LE: @llvm.ppc.vsx.lxvd2x
+
+  res_vss = vec_vsx_ld(0, &vss);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vss = vec_vsx_ld(0, &ss);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vus = vec_vsx_ld(0, &vus);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vus = vec_vsx_ld(0, &us);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vbc = vec_vsx_ld(0, &vbc);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vsc = vec_vsx_ld(0, &vsc);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vuc = vec_vsx_ld(0, &vuc);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vsc = vec_vsx_ld(0, &sc);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
+  res_vuc = vec_vsx_ld(0, &uc);
+// CHECK: @llvm.ppc.vsx.lxvw4x
+// CHECK-LE: @llvm.ppc.vsx.lxvw4x
+
   /* vec_vsx_st */
 
   vec_vsx_st(vsi, 0, &res_vsi);
 // CHECK: @llvm.ppc.vsx.stxvw4x
 // CHECK-LE: @llvm.ppc.vsx.stxvw4x
 
+  vec_vsx_st(vsi, 0, &res_si);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
   vec_vsx_st(vui, 0, &res_vui);
 // CHECK: @llvm.ppc.vsx.stxvw4x
 // CHECK-LE: @llvm.ppc.vsx.stxvw4x
 
+  vec_vsx_st(vui, 0, &res_ui);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
   vec_vsx_st(vf, 0, &res_vf);
 // CHECK: @llvm.ppc.vsx.stxvw4x
 // CHECK-LE: @llvm.ppc.vsx.stxvw4x
 
   vec_vsx_st(vsll, 0, &res_vsll);
 // CHECK: @llvm.ppc.vsx.stxvd2x
 // CHECK-LE: @llvm.ppc.vsx.stxvd2x
 
   vec_vsx_st(vull, 0, &res_vull);
 // CHECK: @llvm.ppc.vsx.stxvd2x
 // CHECK-LE: @llvm.ppc.vsx.stxvd2x
 
   vec_vsx_st(vd, 0, &res_vd);
 // CHECK: @llvm.ppc.vsx.stxvd2x
 // CHECK-LE: @llvm.ppc.vsx.stxvd2x
 
+  vec_vsx_st(vss, 0, &res_vss);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vss, 0, &res_ss);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vus, 0, &res_vus);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vus, 0, &res_us);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vsc, 0, &res_vsc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vsc, 0, &res_sc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vuc, 0, &res_vuc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vuc, 0, &res_uc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vbc, 0, &res_vbc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vbc, 0, &res_sc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
+  vec_vsx_st(vbc, 0, &res_uc);
+// CHECK: @llvm.ppc.vsx.stxvw4x
+// CHECK-LE: @llvm.ppc.vsx.stxvw4x
+
   /* vec_and */
   res_vsll = vec_and(vsll, vsll);
 // CHECK: and <2 x i64>
 // CHECK-LE: and <2 x i64>
 
   res_vsll = vec_and(vbll, vsll);
 // CHECK: and <2 x i64>
 // CHECK-LE: and <2 x i64>