diff options
Diffstat (limited to 'test/CodeGenOpenCL/cl20-device-side-enqueue.cl')
| -rw-r--r-- | test/CodeGenOpenCL/cl20-device-side-enqueue.cl | 269 |
1 files changed, 165 insertions, 104 deletions
diff --git a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl index d74a1dfbd484..473219478a2f 100644 --- a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl +++ b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl @@ -1,30 +1,33 @@ // RUN: %clang_cc1 %s -cl-std=CL2.0 -ffake-address-space-map -O0 -emit-llvm -o - -triple "spir-unknown-unknown" | FileCheck %s --check-prefix=COMMON --check-prefix=B32 // RUN: %clang_cc1 %s -cl-std=CL2.0 -ffake-address-space-map -O0 -emit-llvm -o - -triple "spir64-unknown-unknown" | FileCheck %s --check-prefix=COMMON --check-prefix=B64 +// RUN: %clang_cc1 %s -cl-std=CL2.0 -ffake-address-space-map -O1 -emit-llvm -o - -triple "spir64-unknown-unknown" | FileCheck %s --check-prefix=CHECK-LIFETIMES #pragma OPENCL EXTENSION cl_khr_subgroups : enable typedef void (^bl_t)(local void *); typedef struct {int a;} ndrange_t; +// COMMON: %struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* } + // For a block global variable, first emit the block literal as a global variable, then emit the block variable itself. -// COMMON: [[BL_GLOBAL:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: @block_G = addrspace(1) constant void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BL_GLOBAL]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*) +// COMMON: [[BL_GLOBAL:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* [[INV_G:@[^ ]+]] to i8*) to i8 addrspace(4)*) } +// COMMON: @block_G = addrspace(1) constant void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*) // For anonymous blocks without captures, emit block literals as global variable. -// COMMON: [[BLG1:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG2:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG3:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG4:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG5:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG6:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG7:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG8:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG9:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG10:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } -// COMMON: [[BLG11:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32 } { i32 {{[0-9]+}}, i32 {{[0-9]+}} } +// COMMON: [[BLG1:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG2:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG3:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG4:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG5:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG6:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG7:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG8:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVG8:@[^ ]+]] to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG9:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* [[INVG9:@[^ ]+]] to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG10:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } +// COMMON: [[BLG11:@__block_literal_global[^ ]*]] = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 {{[0-9]+}}, i32 {{[0-9]+}}, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* {{@[^ ]+}} to i8*) to i8 addrspace(4)*) } // Emits block literal [[BL_GLOBAL]], invoke function [[INV_G]] and global block variable @block_G -// COMMON: define internal spir_func void [[INV_G:.*]](i8 addrspace(4)* %{{.*}}, i8 addrspace(3)* %{{.*}}) +// COMMON: define internal spir_func void [[INV_G]](i8 addrspace(4)* %{{.*}}, i8 addrspace(3)* %{{.*}}) const bl_t block_G = (bl_t) ^ (local void *a) {}; void callee(int id, __global int *out) { @@ -46,12 +49,36 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON: %event_wait_list2 = alloca [1 x %opencl.clk_event_t*] clk_event_t event_wait_list2[] = {clk_event}; - // Emits block literal on stack and block kernel [[INVLK1]]. // COMMON: [[NDR:%[a-z0-9]+]] = alloca %struct.ndrange_t, align 4 + + // B32: %[[BLOCK_SIZES1:.*]] = alloca [1 x i32] + // B64: %[[BLOCK_SIZES1:.*]] = alloca [1 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES1:.*]] = alloca [1 x i64] + // B32: %[[BLOCK_SIZES2:.*]] = alloca [1 x i32] + // B64: %[[BLOCK_SIZES2:.*]] = alloca [1 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES2:.*]] = alloca [1 x i64] + // B32: %[[BLOCK_SIZES3:.*]] = alloca [1 x i32] + // B64: %[[BLOCK_SIZES3:.*]] = alloca [1 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES3:.*]] = alloca [1 x i64] + // B32: %[[BLOCK_SIZES4:.*]] = alloca [1 x i32] + // B64: %[[BLOCK_SIZES4:.*]] = alloca [1 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES4:.*]] = alloca [1 x i64] + // B32: %[[BLOCK_SIZES5:.*]] = alloca [1 x i32] + // B64: %[[BLOCK_SIZES5:.*]] = alloca [1 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES5:.*]] = alloca [1 x i64] + // B32: %[[BLOCK_SIZES6:.*]] = alloca [3 x i32] + // B64: %[[BLOCK_SIZES6:.*]] = alloca [3 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES6:.*]] = alloca [3 x i64] + // B32: %[[BLOCK_SIZES7:.*]] = alloca [1 x i32] + // B64: %[[BLOCK_SIZES7:.*]] = alloca [1 x i64] + // CHECK-LIFETIMES: %[[BLOCK_SIZES7:.*]] = alloca [1 x i64] + + // Emits block literal on stack and block kernel [[INVLK1]]. // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // B32: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block to void ()* - // B64: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i32 addrspace(1)*, i32 addrspace(1)*, i32 }>* %block to void ()* + // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL1:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke + // B32: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block to void ()* + // B64: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32 addrspace(1)*, i32 }>* %block to void ()* // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* [[BL]] to i8 addrspace(4)* // COMMON-LABEL: call i32 @__enqueue_kernel_basic( // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* byval [[NDR]]{{([0-9]+)?}}, @@ -67,54 +94,68 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %event_wait_list to %opencl.clk_event_t{{.*}}* addrspace(4)* // COMMON: [[EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)* - // COMMON: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()* + // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL2:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke + // COMMON: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()* // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* [[BL]] to i8 addrspace(4)* // COMMON-LABEL: call i32 @__enqueue_kernel_basic_events // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVLK2:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), // COMMON-SAME: i8 addrspace(4)* [[BL_I8]]) - enqueue_kernel(default_queue, flags, ndrange, 2, &event_wait_list, &clk_event, ^(void) { a[i] = b[i]; }); + // COMMON-LABEL: call i32 @__enqueue_kernel_basic_events + // COMMON-SAME: (%opencl.queue_t{{.*}}* {{%[0-9]+}}, i32 {{%[0-9]+}}, %struct.ndrange_t* {{.*}}, i32 1, %opencl.clk_event_t{{.*}}* addrspace(4)* {{%[0-9]+}}, %opencl.clk_event_t{{.*}}* addrspace(4)* null, + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, 0, + ^(void) { + return; + }); + // Emits global block literal [[BLG1]] and block kernel [[INVGK1]]. // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // B32: %[[TMP:.*]] = alloca [1 x i32] - // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 256, i32* %[[TMP1]], align 4 - // B64: %[[TMP:.*]] = alloca [1 x i64] - // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 256, i64* %[[TMP1]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES1]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES1]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [1 x i32], [1 x i32]* %[[BLOCK_SIZES1]], i32 0, i32 0 + // B32: store i32 256, i32* %[[TMP]], align 4 + // B64: %[[TMP:.*]] = getelementptr [1 x i64], [1 x i64]* %[[BLOCK_SIZES1]], i32 0, i32 0 + // B64: store i64 256, i64* %[[TMP]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_varargs( // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK1:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG1]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG1]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; }, 256); + char c; // Emits global block literal [[BLG2]] and block kernel [[INVGK2]]. // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // B32: %[[TMP:.*]] = alloca [1 x i32] - // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4 - // B64: %[[TMP:.*]] = alloca [1 x i64] - // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES2]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES2]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [1 x i32], [1 x i32]* %[[BLOCK_SIZES2]], i32 0, i32 0 + // B32: store i32 %{{.*}}, i32* %[[TMP]], align 4 + // B64: %[[TMP:.*]] = getelementptr [1 x i64], [1 x i64]* %[[BLOCK_SIZES2]], i32 0, i32 0 + // B64: store i64 %{{.*}}, i64* %[[TMP]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_varargs( // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK2:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG2]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG2]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -127,18 +168,21 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON: [[AD:%arraydecay[0-9]*]] = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0 // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** [[AD]] to %opencl.clk_event_t{{.*}}* addrspace(4)* // COMMON: [[EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)* - // B32: %[[TMP:.*]] = alloca [1 x i32] - // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 256, i32* %[[TMP1]], align 4 - // B64: %[[TMP:.*]] = alloca [1 x i64] - // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 256, i64* %[[TMP1]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES3]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES3]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_events_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [1 x i32], [1 x i32]* %[[BLOCK_SIZES3]], i32 0, i32 0 + // B32: store i32 256, i32* %[[TMP]], align 4 + // B64: %[[TMP:.*]] = getelementptr [1 x i64], [1 x i64]* %[[BLOCK_SIZES3]], i32 0, i32 0 + // B64: store i64 256, i64* %[[TMP]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_events_varargs // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK3:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG3]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG3]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event, ^(local void *p) { return; @@ -151,18 +195,21 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON: [[AD:%arraydecay[0-9]*]] = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0 // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** [[AD]] to %opencl.clk_event_t{{.*}}* addrspace(4)* // COMMON: [[EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)* - // B32: %[[TMP:.*]] = alloca [1 x i32] - // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4 - // B64: %[[TMP:.*]] = alloca [1 x i64] - // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES4]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES4]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_events_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [1 x i32], [1 x i32]* %[[BLOCK_SIZES4]], i32 0, i32 0 + // B32: store i32 %{{.*}}, i32* %[[TMP]], align 4 + // B64: %[[TMP:.*]] = getelementptr [1 x i64], [1 x i64]* %[[BLOCK_SIZES4]], i32 0, i32 0 + // B64: store i64 %{{.*}}, i64* %[[TMP]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_events_varargs // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK4:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG4]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG4]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event, ^(local void *p) { return; @@ -173,18 +220,21 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // Emits global block literal [[BLG5]] and block kernel [[INVGK5]]. // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // B32: %[[TMP:.*]] = alloca [1 x i32] - // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4 - // B64: %[[TMP:.*]] = alloca [1 x i64] - // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES5]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES5]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [1 x i32], [1 x i32]* %[[BLOCK_SIZES5]], i32 0, i32 0 + // B32: store i32 %{{.*}}, i32* %[[TMP]], align 4 + // B64: %[[TMP:.*]] = getelementptr [1 x i64], [1 x i64]* %[[BLOCK_SIZES5]], i32 0, i32 0 + // B64: store i64 %{{.*}}, i64* %[[TMP]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_varargs // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK5:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG5]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG5]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -194,26 +244,29 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // Emits global block literal [[BLG6]] and block kernel [[INVGK6]]. // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // B32: %[[TMP:.*]] = alloca [3 x i32] - // B32: %[[TMP1:.*]] = getelementptr [3 x i32], [3 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 1, i32* %[[TMP1]], align 4 - // B32: %[[TMP2:.*]] = getelementptr [3 x i32], [3 x i32]* %[[TMP]], i32 0, i32 1 - // B32: store i32 2, i32* %[[TMP2]], align 4 - // B32: %[[TMP3:.*]] = getelementptr [3 x i32], [3 x i32]* %[[TMP]], i32 0, i32 2 - // B32: store i32 4, i32* %[[TMP3]], align 4 - // B64: %[[TMP:.*]] = alloca [3 x i64] - // B64: %[[TMP1:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 1, i64* %[[TMP1]], align 8 - // B64: %[[TMP2:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 1 - // B64: store i64 2, i64* %[[TMP2]], align 8 - // B64: %[[TMP3:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 2 - // B64: store i64 4, i64* %[[TMP3]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [3 x i64]* %[[BLOCK_SIZES6]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 24, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [3 x i64], [3 x i64]* %[[BLOCK_SIZES6]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 24, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [3 x i32], [3 x i32]* %[[BLOCK_SIZES6]], i32 0, i32 0 + // B32: store i32 1, i32* %[[TMP]], align 4 + // B32: %[[BLOCK_SIZES62:.*]] = getelementptr [3 x i32], [3 x i32]* %[[BLOCK_SIZES6]], i32 0, i32 1 + // B32: store i32 2, i32* %[[BLOCK_SIZES62]], align 4 + // B32: %[[BLOCK_SIZES63:.*]] = getelementptr [3 x i32], [3 x i32]* %[[BLOCK_SIZES6]], i32 0, i32 2 + // B32: store i32 4, i32* %[[BLOCK_SIZES63]], align 4 + // B64: %[[TMP:.*]] = getelementptr [3 x i64], [3 x i64]* %[[BLOCK_SIZES6]], i32 0, i32 0 + // B64: store i64 1, i64* %[[TMP]], align 8 + // B64: %[[BLOCK_SIZES62:.*]] = getelementptr [3 x i64], [3 x i64]* %[[BLOCK_SIZES6]], i32 0, i32 1 + // B64: store i64 2, i64* %[[BLOCK_SIZES62]], align 8 + // B64: %[[BLOCK_SIZES63:.*]] = getelementptr [3 x i64], [3 x i64]* %[[BLOCK_SIZES6]], i32 0, i32 2 + // B64: store i64 4, i64* %[[BLOCK_SIZES63]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_varargs // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK6:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG6]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG6]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p1, local void *p2, local void *p3) { return; @@ -223,18 +276,21 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // Emits global block literal [[BLG7]] and block kernel [[INVGK7]]. // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // B32: %[[TMP:.*]] = alloca [1 x i32] - // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 - // B32: store i32 0, i32* %[[TMP1]], align 4 - // B64: %[[TMP:.*]] = alloca [1 x i64] - // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 - // B64: store i64 4294967296, i64* %[[TMP1]], align 8 + // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES7]] to i8* + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES7]], i64 0, i64 0 + // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_varargs( + // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]]) + // B32: %[[TMP:.*]] = getelementptr [1 x i32], [1 x i32]* %[[BLOCK_SIZES7]], i32 0, i32 0 + // B32: store i32 0, i32* %[[TMP]], align 4 + // B64: %[[TMP:.*]] = getelementptr [1 x i64], [1 x i64]* %[[BLOCK_SIZES7]], i32 0, i32 0 + // B64: store i64 4294967296, i64* %[[TMP]], align 8 // COMMON-LABEL: call i32 @__enqueue_kernel_varargs // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK7:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG7]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, - // B32-SAME: i32* %[[TMP1]]) - // B64-SAME: i64* %[[TMP1]]) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG7]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, + // B32-SAME: i32* %[[TMP]]) + // B64-SAME: i64* %[[TMP]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -244,19 +300,21 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // Emits global block literal [[BLG8]] and invoke function [[INVG8]]. // The full type of these expressions are long (and repeated elsewhere), so we // capture it as part of the regex for convenience and clarity. - // COMMON: store void () addrspace(4)* addrspacecast (void () addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to void () addrspace(1)*) to void () addrspace(4)*), void () addrspace(4)** %block_A + // COMMON: store void () addrspace(4)* addrspacecast (void () addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to void () addrspace(1)*) to void () addrspace(4)*), void () addrspace(4)** %block_A void (^const block_A)(void) = ^{ return; }; // Emits global block literal [[BLG9]] and invoke function [[INVG9]]. - // COMMON: store void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG9]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*), void (i8 addrspace(3)*) addrspace(4)** %block_B + // COMMON: store void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG9]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*), void (i8 addrspace(3)*) addrspace(4)** %block_B void (^const block_B)(local void *) = ^(local void *a) { return; }; // Uses global block literal [[BLG8]] and invoke function [[INVG8]]. - // COMMON: call spir_func void [[INVG8:.*]](i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON: [[r1:%.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* getelementptr inbounds (%struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), i32 0, i32 2) + // COMMON: [[r2:%.*]] = addrspacecast i8 addrspace(4)* [[r1]] to void (i8 addrspace(4)*)* + // COMMON: call spir_func void [[r2]](i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) block_A(); // Emits global block literal [[BLG8]] and block kernel [[INVGK8]]. [[INVGK8]] calls [[INVG8]]. @@ -265,17 +323,19 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON-LABEL: call i32 @__enqueue_kernel_basic( // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* byval [[NDR]]{{([0-9]+)?}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK8:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) enqueue_kernel(default_queue, flags, ndrange, block_A); // Uses block kernel [[INVGK8]] and global block literal [[BLG8]]. // COMMON: call i32 @__get_kernel_work_group_size_impl( // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK8]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) unsigned size = get_kernel_work_group_size(block_A); // Uses global block literal [[BLG8]] and invoke function [[INVG8]]. Make sure no redundant block literal and invoke functions are emitted. - // COMMON: call spir_func void [[INVG8]](i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON: [[r1:%.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* getelementptr inbounds (%struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* addrspacecast (%struct.__opencl_block_literal_generic addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to %struct.__opencl_block_literal_generic addrspace(1)*) to %struct.__opencl_block_literal_generic addrspace(4)*), i32 0, i32 2) + // COMMON: [[r2:%.*]] = addrspacecast i8 addrspace(4)* [[r1]] to void (i8 addrspace(4)*)* + // COMMON: call spir_func void [[r2]](i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) block_A(); void (^block_C)(void) = ^{ @@ -283,6 +343,7 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { }; // Emits block literal on stack and block kernel [[INVLK3]]. + // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*)* [[INVL3:@__device_side_enqueue_block_invoke[^ ]*]] to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* {{.*}} to i8 addrspace(4)* @@ -292,34 +353,34 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON-SAME: i8 addrspace(4)* [[BL_I8]]) enqueue_kernel(default_queue, flags, ndrange, block_C); - // Emits global block literal [[BLG9]] and block kernel [[INVGK9]]. [[INVGK9]] calls [[INVG9]]. + // Emits global block literal [[BLG9]] and block kernel [[INVGK9]]. [[INVGK9]] calls [[INV9]]. // COMMON: call i32 @__get_kernel_work_group_size_impl( // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK9:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG9]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG9]] to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_work_group_size(block_B); // Uses global block literal [[BLG8]] and block kernel [[INVGK8]]. Make sure no redundant block literal ind invoke functions are emitted. // COMMON: call i32 @__get_kernel_preferred_work_group_size_multiple_impl( // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK8]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_preferred_work_group_size_multiple(block_A); // Uses global block literal [[BL_GLOBAL]] and block kernel [[INV_G_K]]. [[INV_G_K]] calls [[INV_G]]. // COMMON: call i32 @__get_kernel_preferred_work_group_size_multiple_impl( // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INV_G_K:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_preferred_work_group_size_multiple(block_G); // Emits global block literal [[BLG10]] and block kernel [[INVGK10]]. // COMMON: call i32 @__get_kernel_max_sub_group_size_for_ndrange_impl(%struct.ndrange_t* {{[^,]+}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK10:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG10]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG10]] to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_max_sub_group_size_for_ndrange(ndrange, ^(){}); // Emits global block literal [[BLG11]] and block kernel [[INVGK11]]. // COMMON: call i32 @__get_kernel_sub_group_count_for_ndrange_impl(%struct.ndrange_t* {{[^,]+}}, // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK11:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*), - // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG11]] to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BLG11]] to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_sub_group_count_for_ndrange(ndrange, ^(){}); } @@ -336,12 +397,12 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) { // COMMON: define internal spir_kernel void [[INVGK5]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}}) // COMMON: define internal spir_kernel void [[INVGK6]](i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*) #{{[0-9]+}} { // COMMON: entry: -// COMMON: call void @__device_side_enqueue_block_invoke_8(i8 addrspace(4)* %0, i8 addrspace(3)* %1, i8 addrspace(3)* %2, i8 addrspace(3)* %3) +// COMMON: call void @__device_side_enqueue_block_invoke_9(i8 addrspace(4)* %0, i8 addrspace(3)* %1, i8 addrspace(3)* %2, i8 addrspace(3)* %3) // COMMON: ret void // COMMON: } // COMMON: define internal spir_kernel void [[INVGK7]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}}) // COMMON: define internal spir_func void [[INVG8]](i8 addrspace(4)*{{.*}}) -// COMMON: define internal spir_func void [[INVG9:.*]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)* %{{.*}}) +// COMMON: define internal spir_func void [[INVG9]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)* %{{.*}}) // COMMON: define internal spir_kernel void [[INVGK8]](i8 addrspace(4)*{{.*}}) // COMMON: define internal spir_kernel void [[INVLK3]](i8 addrspace(4)*{{.*}}) // COMMON: define internal spir_kernel void [[INVGK9]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}}) |