summaryrefslogtreecommitdiffstats
path: root/test/CodeGen/PTX/ld.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/PTX/ld.ll')
-rw-r--r--test/CodeGen/PTX/ld.ll150
1 files changed, 75 insertions, 75 deletions
diff --git a/test/CodeGen/PTX/ld.ll b/test/CodeGen/PTX/ld.ll
index 377a95a..d184d12 100644
--- a/test/CodeGen/PTX/ld.ll
+++ b/test/CodeGen/PTX/ld.ll
@@ -63,7 +63,7 @@
define ptx_device i16 @t1_u16(i16* %p) {
entry:
-;CHECK: ld.global.u16 rh0, [r1];
+;CHECK: ld.global.u16 rh{{[0-9]+}}, [r{{[0-9]+}}];
;CHECK-NEXT: ret;
%x = load i16* %p
ret i16 %x
@@ -71,7 +71,7 @@ entry:
define ptx_device i32 @t1_u32(i32* %p) {
entry:
-;CHECK: ld.global.u32 r0, [r1];
+;CHECK: ld.global.u32 r{{[0-9]+}}, [r{{[0-9]+}}];
;CHECK-NEXT: ret;
%x = load i32* %p
ret i32 %x
@@ -79,7 +79,7 @@ entry:
define ptx_device i64 @t1_u64(i64* %p) {
entry:
-;CHECK: ld.global.u64 rd0, [r1];
+;CHECK: ld.global.u64 rd{{[0-9]+}}, [r{{[0-9]+}}];
;CHECK-NEXT: ret;
%x = load i64* %p
ret i64 %x
@@ -87,7 +87,7 @@ entry:
define ptx_device float @t1_f32(float* %p) {
entry:
-;CHECK: ld.global.f32 f0, [r1];
+;CHECK: ld.global.f32 r{{[0-9]+}}, [r{{[0-9]+}}];
;CHECK-NEXT: ret;
%x = load float* %p
ret float %x
@@ -95,7 +95,7 @@ entry:
define ptx_device double @t1_f64(double* %p) {
entry:
-;CHECK: ld.global.f64 fd0, [r1];
+;CHECK: ld.global.f64 rd{{[0-9]+}}, [r{{[0-9]+}}];
;CHECK-NEXT: ret;
%x = load double* %p
ret double %x
@@ -103,7 +103,7 @@ entry:
define ptx_device i16 @t2_u16(i16* %p) {
entry:
-;CHECK: ld.global.u16 rh0, [r1+2];
+;CHECK: ld.global.u16 rh{{[0-9]+}}, [r{{[0-9]+}}+2];
;CHECK-NEXT: ret;
%i = getelementptr i16* %p, i32 1
%x = load i16* %i
@@ -112,7 +112,7 @@ entry:
define ptx_device i32 @t2_u32(i32* %p) {
entry:
-;CHECK: ld.global.u32 r0, [r1+4];
+;CHECK: ld.global.u32 r{{[0-9]+}}, [r{{[0-9]+}}+4];
;CHECK-NEXT: ret;
%i = getelementptr i32* %p, i32 1
%x = load i32* %i
@@ -121,7 +121,7 @@ entry:
define ptx_device i64 @t2_u64(i64* %p) {
entry:
-;CHECK: ld.global.u64 rd0, [r1+8];
+;CHECK: ld.global.u64 rd{{[0-9]+}}, [r{{[0-9]+}}+8];
;CHECK-NEXT: ret;
%i = getelementptr i64* %p, i32 1
%x = load i64* %i
@@ -130,7 +130,7 @@ entry:
define ptx_device float @t2_f32(float* %p) {
entry:
-;CHECK: ld.global.f32 f0, [r1+4];
+;CHECK: ld.global.f32 r{{[0-9]+}}, [r{{[0-9]+}}+4];
;CHECK-NEXT: ret;
%i = getelementptr float* %p, i32 1
%x = load float* %i
@@ -139,7 +139,7 @@ entry:
define ptx_device double @t2_f64(double* %p) {
entry:
-;CHECK: ld.global.f64 fd0, [r1+8];
+;CHECK: ld.global.f64 rd{{[0-9]+}}, [r{{[0-9]+}}+8];
;CHECK-NEXT: ret;
%i = getelementptr double* %p, i32 1
%x = load double* %i
@@ -148,9 +148,9 @@ entry:
define ptx_device i16 @t3_u16(i16* %p, i32 %q) {
entry:
-;CHECK: shl.b32 r0, r2, 1;
-;CHECK-NEXT: add.u32 r0, r1, r0;
-;CHECK-NEXT: ld.global.u16 rh0, [r0];
+;CHECK: shl.b32 r[[R0:[0-9]+]], r{{[0-9]+}}, 1;
+;CHECK-NEXT: add.u32 r[[R0]], r{{[0-9]+}}, r[[R0]];
+;CHECK-NEXT: ld.global.u16 rh{{[0-9]+}}, [r[[R0]]];
%i = getelementptr i16* %p, i32 %q
%x = load i16* %i
ret i16 %x
@@ -158,9 +158,9 @@ entry:
define ptx_device i32 @t3_u32(i32* %p, i32 %q) {
entry:
-;CHECK: shl.b32 r0, r2, 2;
-;CHECK-NEXT: add.u32 r0, r1, r0;
-;CHECK-NEXT: ld.global.u32 r0, [r0];
+;CHECK: shl.b32 r[[R0:[0-9]+]], r{{[0-9]+}}, 2;
+;CHECK-NEXT: add.u32 r[[R0]], r{{[0-9]+}}, r[[R0]];
+;CHECK-NEXT: ld.global.u32 r{{[0-9]+}}, [r[[R0]]];
%i = getelementptr i32* %p, i32 %q
%x = load i32* %i
ret i32 %x
@@ -168,9 +168,9 @@ entry:
define ptx_device i64 @t3_u64(i64* %p, i32 %q) {
entry:
-;CHECK: shl.b32 r0, r2, 3;
-;CHECK-NEXT: add.u32 r0, r1, r0;
-;CHECK-NEXT: ld.global.u64 rd0, [r0];
+;CHECK: shl.b32 r[[R0:[0-9]+]], r{{[0-9]+}}, 3;
+;CHECK-NEXT: add.u32 r[[R0]], r{{[0-9]+}}, r[[R0]];
+;CHECK-NEXT: ld.global.u64 rd{{[0-9]+}}, [r[[R0]]];
%i = getelementptr i64* %p, i32 %q
%x = load i64* %i
ret i64 %x
@@ -178,9 +178,9 @@ entry:
define ptx_device float @t3_f32(float* %p, i32 %q) {
entry:
-;CHECK: shl.b32 r0, r2, 2;
-;CHECK-NEXT: add.u32 r0, r1, r0;
-;CHECK-NEXT: ld.global.f32 f0, [r0];
+;CHECK: shl.b32 r[[R0:[0-9]+]], r{{[0-9]+}}, 2;
+;CHECK-NEXT: add.u32 r[[R0]], r{{[0-9]+}}, r[[R0]];
+;CHECK-NEXT: ld.global.f32 r{{[0-9]+}}, [r[[R0]]];
%i = getelementptr float* %p, i32 %q
%x = load float* %i
ret float %x
@@ -188,9 +188,9 @@ entry:
define ptx_device double @t3_f64(double* %p, i32 %q) {
entry:
-;CHECK: shl.b32 r0, r2, 3;
-;CHECK-NEXT: add.u32 r0, r1, r0;
-;CHECK-NEXT: ld.global.f64 fd0, [r0];
+;CHECK: shl.b32 r[[R0:[0-9]+]], r{{[0-9]+}}, 3;
+;CHECK-NEXT: add.u32 r[[R0]], r{{[0-9]+}}, r[[R0]];
+;CHECK-NEXT: ld.global.f64 rd{{[0-9]+}}, [r[[R0]]];
%i = getelementptr double* %p, i32 %q
%x = load double* %i
ret double %x
@@ -198,8 +198,8 @@ entry:
define ptx_device i16 @t4_global_u16() {
entry:
-;CHECK: mov.u32 r0, array_i16;
-;CHECK-NEXT: ld.global.u16 rh0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_i16;
+;CHECK-NEXT: ld.global.u16 rh{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i16]* @array_i16, i32 0, i32 0
%x = load i16* %i
@@ -208,8 +208,8 @@ entry:
define ptx_device i32 @t4_global_u32() {
entry:
-;CHECK: mov.u32 r0, array_i32;
-;CHECK-NEXT: ld.global.u32 r0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_i32;
+;CHECK-NEXT: ld.global.u32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i32]* @array_i32, i32 0, i32 0
%x = load i32* %i
@@ -218,8 +218,8 @@ entry:
define ptx_device i64 @t4_global_u64() {
entry:
-;CHECK: mov.u32 r0, array_i64;
-;CHECK-NEXT: ld.global.u64 rd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_i64;
+;CHECK-NEXT: ld.global.u64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i64]* @array_i64, i32 0, i32 0
%x = load i64* %i
@@ -228,8 +228,8 @@ entry:
define ptx_device float @t4_global_f32() {
entry:
-;CHECK: mov.u32 r0, array_float;
-;CHECK-NEXT: ld.global.f32 f0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_float;
+;CHECK-NEXT: ld.global.f32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x float]* @array_float, i32 0, i32 0
%x = load float* %i
@@ -238,8 +238,8 @@ entry:
define ptx_device double @t4_global_f64() {
entry:
-;CHECK: mov.u32 r0, array_double;
-;CHECK-NEXT: ld.global.f64 fd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_double;
+;CHECK-NEXT: ld.global.f64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x double]* @array_double, i32 0, i32 0
%x = load double* %i
@@ -248,8 +248,8 @@ entry:
define ptx_device i16 @t4_const_u16() {
entry:
-;CHECK: mov.u32 r0, array_constant_i16;
-;CHECK-NEXT: ld.const.u16 rh0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_constant_i16;
+;CHECK-NEXT: ld.const.u16 rh{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i16] addrspace(1)* @array_constant_i16, i32 0, i32 0
%x = load i16 addrspace(1)* %i
@@ -258,8 +258,8 @@ entry:
define ptx_device i32 @t4_const_u32() {
entry:
-;CHECK: mov.u32 r0, array_constant_i32;
-;CHECK-NEXT: ld.const.u32 r0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_constant_i32;
+;CHECK-NEXT: ld.const.u32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i32] addrspace(1)* @array_constant_i32, i32 0, i32 0
%x = load i32 addrspace(1)* %i
@@ -268,8 +268,8 @@ entry:
define ptx_device i64 @t4_const_u64() {
entry:
-;CHECK: mov.u32 r0, array_constant_i64;
-;CHECK-NEXT: ld.const.u64 rd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_constant_i64;
+;CHECK-NEXT: ld.const.u64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i64] addrspace(1)* @array_constant_i64, i32 0, i32 0
%x = load i64 addrspace(1)* %i
@@ -278,8 +278,8 @@ entry:
define ptx_device float @t4_const_f32() {
entry:
-;CHECK: mov.u32 r0, array_constant_float;
-;CHECK-NEXT: ld.const.f32 f0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_constant_float;
+;CHECK-NEXT: ld.const.f32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x float] addrspace(1)* @array_constant_float, i32 0, i32 0
%x = load float addrspace(1)* %i
@@ -288,8 +288,8 @@ entry:
define ptx_device double @t4_const_f64() {
entry:
-;CHECK: mov.u32 r0, array_constant_double;
-;CHECK-NEXT: ld.const.f64 fd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_constant_double;
+;CHECK-NEXT: ld.const.f64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x double] addrspace(1)* @array_constant_double, i32 0, i32 0
%x = load double addrspace(1)* %i
@@ -298,8 +298,8 @@ entry:
define ptx_device i16 @t4_local_u16() {
entry:
-;CHECK: mov.u32 r0, array_local_i16;
-;CHECK-NEXT: ld.local.u16 rh0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_local_i16;
+;CHECK-NEXT: ld.local.u16 rh{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i16] addrspace(2)* @array_local_i16, i32 0, i32 0
%x = load i16 addrspace(2)* %i
@@ -308,8 +308,8 @@ entry:
define ptx_device i32 @t4_local_u32() {
entry:
-;CHECK: mov.u32 r0, array_local_i32;
-;CHECK-NEXT: ld.local.u32 r0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_local_i32;
+;CHECK-NEXT: ld.local.u32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i32] addrspace(2)* @array_local_i32, i32 0, i32 0
%x = load i32 addrspace(2)* %i
@@ -318,8 +318,8 @@ entry:
define ptx_device i64 @t4_local_u64() {
entry:
-;CHECK: mov.u32 r0, array_local_i64;
-;CHECK-NEXT: ld.local.u64 rd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_local_i64;
+;CHECK-NEXT: ld.local.u64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i64] addrspace(2)* @array_local_i64, i32 0, i32 0
%x = load i64 addrspace(2)* %i
@@ -328,8 +328,8 @@ entry:
define ptx_device float @t4_local_f32() {
entry:
-;CHECK: mov.u32 r0, array_local_float;
-;CHECK-NEXT: ld.local.f32 f0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_local_float;
+;CHECK-NEXT: ld.local.f32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x float] addrspace(2)* @array_local_float, i32 0, i32 0
%x = load float addrspace(2)* %i
@@ -338,8 +338,8 @@ entry:
define ptx_device double @t4_local_f64() {
entry:
-;CHECK: mov.u32 r0, array_local_double;
-;CHECK-NEXT: ld.local.f64 fd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_local_double;
+;CHECK-NEXT: ld.local.f64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x double] addrspace(2)* @array_local_double, i32 0, i32 0
%x = load double addrspace(2)* %i
@@ -348,8 +348,8 @@ entry:
define ptx_device i16 @t4_shared_u16() {
entry:
-;CHECK: mov.u32 r0, array_shared_i16;
-;CHECK-NEXT: ld.shared.u16 rh0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_shared_i16;
+;CHECK-NEXT: ld.shared.u16 rh{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i16] addrspace(4)* @array_shared_i16, i32 0, i32 0
%x = load i16 addrspace(4)* %i
@@ -358,8 +358,8 @@ entry:
define ptx_device i32 @t4_shared_u32() {
entry:
-;CHECK: mov.u32 r0, array_shared_i32;
-;CHECK-NEXT: ld.shared.u32 r0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_shared_i32;
+;CHECK-NEXT: ld.shared.u32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i32] addrspace(4)* @array_shared_i32, i32 0, i32 0
%x = load i32 addrspace(4)* %i
@@ -368,8 +368,8 @@ entry:
define ptx_device i64 @t4_shared_u64() {
entry:
-;CHECK: mov.u32 r0, array_shared_i64;
-;CHECK-NEXT: ld.shared.u64 rd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_shared_i64;
+;CHECK-NEXT: ld.shared.u64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i64] addrspace(4)* @array_shared_i64, i32 0, i32 0
%x = load i64 addrspace(4)* %i
@@ -378,8 +378,8 @@ entry:
define ptx_device float @t4_shared_f32() {
entry:
-;CHECK: mov.u32 r0, array_shared_float;
-;CHECK-NEXT: ld.shared.f32 f0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_shared_float;
+;CHECK-NEXT: ld.shared.f32 r{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x float] addrspace(4)* @array_shared_float, i32 0, i32 0
%x = load float addrspace(4)* %i
@@ -388,8 +388,8 @@ entry:
define ptx_device double @t4_shared_f64() {
entry:
-;CHECK: mov.u32 r0, array_shared_double;
-;CHECK-NEXT: ld.shared.f64 fd0, [r0];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_shared_double;
+;CHECK-NEXT: ld.shared.f64 rd{{[0-9]+}}, [r[[R0]]];
;CHECK-NEXT: ret;
%i = getelementptr [10 x double] addrspace(4)* @array_shared_double, i32 0, i32 0
%x = load double addrspace(4)* %i
@@ -398,8 +398,8 @@ entry:
define ptx_device i16 @t5_u16() {
entry:
-;CHECK: mov.u32 r0, array_i16;
-;CHECK-NEXT: ld.global.u16 rh0, [r0+2];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_i16;
+;CHECK-NEXT: ld.global.u16 rh{{[0-9]+}}, [r[[R0]]+2];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i16]* @array_i16, i32 0, i32 1
%x = load i16* %i
@@ -408,8 +408,8 @@ entry:
define ptx_device i32 @t5_u32() {
entry:
-;CHECK: mov.u32 r0, array_i32;
-;CHECK-NEXT: ld.global.u32 r0, [r0+4];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_i32;
+;CHECK-NEXT: ld.global.u32 r{{[0-9]+}}, [r[[R0]]+4];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i32]* @array_i32, i32 0, i32 1
%x = load i32* %i
@@ -418,8 +418,8 @@ entry:
define ptx_device i64 @t5_u64() {
entry:
-;CHECK: mov.u32 r0, array_i64;
-;CHECK-NEXT: ld.global.u64 rd0, [r0+8];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_i64;
+;CHECK-NEXT: ld.global.u64 rd{{[0-9]+}}, [r[[R0]]+8];
;CHECK-NEXT: ret;
%i = getelementptr [10 x i64]* @array_i64, i32 0, i32 1
%x = load i64* %i
@@ -428,8 +428,8 @@ entry:
define ptx_device float @t5_f32() {
entry:
-;CHECK: mov.u32 r0, array_float;
-;CHECK-NEXT: ld.global.f32 f0, [r0+4];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_float;
+;CHECK-NEXT: ld.global.f32 r{{[0-9]+}}, [r[[R0]]+4];
;CHECK-NEXT: ret;
%i = getelementptr [10 x float]* @array_float, i32 0, i32 1
%x = load float* %i
@@ -438,8 +438,8 @@ entry:
define ptx_device double @t5_f64() {
entry:
-;CHECK: mov.u32 r0, array_double;
-;CHECK-NEXT: ld.global.f64 fd0, [r0+8];
+;CHECK: mov.u32 r[[R0:[0-9]+]], array_double;
+;CHECK-NEXT: ld.global.f64 rd{{[0-9]+}}, [r[[R0]]+8];
;CHECK-NEXT: ret;
%i = getelementptr [10 x double]* @array_double, i32 0, i32 1
%x = load double* %i
OpenPOWER on IntegriCloud