Skip to content
Merged
Show file tree
Hide file tree
Changes from 9 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/access-non-generic.ll
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix PTX
; RUN: opt -mtriple=nvptx-- < %s -S -passes=infer-address-spaces | FileCheck %s --check-prefix IR
; RUN: opt -mtriple=nvptx64-- < %s -S -passes=infer-address-spaces | FileCheck %s --check-prefix IR
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}

@array = internal addrspace(3) global [10 x float] zeroinitializer, align 4
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/activemask.ll
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
; RUN: llc < %s -mtriple=nvptx64 -O2 -mcpu=sm_52 -mattr=+ptx62 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_52 -mattr=+ptx62 | %ptxas-verify %}
; RUN: %if ptxas-isa-6.2 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_52 -mattr=+ptx62 | %ptxas-verify %}

declare i32 @llvm.nvvm.activemask()

Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/addrspacecast-ptx64.ll
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | FileCheck %s -check-prefixes=NOPTRCONV
; RUN: llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 --nvptx-short-ptr | FileCheck %s -check-prefixes=PTRCONV
; RUN: %if ptxas-12.8 %{ llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-12.8 %{ llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 --nvptx-short-ptr | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-7.8 %{ llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-7.8 %{ llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 --nvptx-short-ptr | %ptxas-verify -arch=sm_90 %}

; ALL-LABEL: conv_shared_cluster_to_generic
define i32 @conv_shared_cluster_to_generic(ptr addrspace(7) %ptr) {
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/addrspacecast.ll
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; RUN: llc -O0 < %s -mtriple=nvptx -mcpu=sm_20 | FileCheck %s -check-prefixes=ALL,CLS32
; RUN: llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s -check-prefixes=ALL,NOPTRCONV,CLS64
; RUN: llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_20 --nvptx-short-ptr | FileCheck %s -check-prefixes=ALL,PTRCONV,CLS64
; RUN: %if ptxas && !ptxas-12.0 %{ llc -O0 < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas-ptr32 %{ llc -O0 < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas %{ llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas %{ llc -O0 < %s -mtriple=nvptx64 -mcpu=sm_20 --nvptx-short-ptr | %ptxas-verify %}

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/alias.ll
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_30 -mattr=+ptx64 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_30 -mattr=+ptx64 | %ptxas-verify %}
; RUN: %if ptxas-isa-6.4 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_30 -mattr=+ptx64 | %ptxas-verify %}

define i32 @a() { ret i32 0 }
@b = internal alias i32 (), ptr @a
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/annotations.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_20 | FileCheck %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}

@texture = internal addrspace(1) global i64 0, align 8
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/applypriority.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx74| FileCheck --check-prefixes=CHECK-PTX64 %s
; RUN: %if ptxas-11.4 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx74| %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.4 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx74| %ptxas-verify -arch=sm_80 %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/arithmetic-fp-sm20.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_20 -fp-contract=fast | FileCheck %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 -fp-contract=fast | FileCheck %s
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 -fp-contract=fast | %ptxas-verify %}
; RUN: %if ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 -fp-contract=fast | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 -fp-contract=fast | %ptxas-verify %}

;; These tests should run for all targets
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/arithmetic-int.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_20 | FileCheck %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}

;; These tests should run for all targets
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/async-copy.ll
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_80 -mattr=+ptx70 | FileCheck -check-prefixes=CHECK,CHECK_PTX32 %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | FileCheck -check-prefixes=CHECK,CHECK_PTX64 %s
; RUN: %if ptxas-11.0 && ! ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-11.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.0 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}

declare void @llvm.nvvm.cp.async.wait.group(i32)

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/atomicrmw-expand.ll
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_30 | FileCheck %s --check-prefixes=ALL,SM30
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_60 | FileCheck %s --check-prefixes=ALL,SM60
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_30 | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas-sm_60 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}

; CHECK-LABEL: fadd_double
define void @fadd_double(ptr %0, double %1) {
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/atomics-sm60.ll
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_60 | FileCheck %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_60 | FileCheck %s
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas-sm_60 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas-sm_60 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}

; CHECK-LABEL: .func test(
define void @test(ptr %dp0, ptr addrspace(1) %dp1, ptr addrspace(3) %dp3, double %d) {
Expand Down
6 changes: 3 additions & 3 deletions llvm/test/CodeGen/NVPTX/atomics-sm70.ll
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_70 -mattr=+ptx63 | FileCheck %s --check-prefixes=CHECK
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx63 | FileCheck %s --check-prefixes=CHECK64
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_70 -mattr=+ptx62 | FileCheck %s --check-prefixes=CHECKPTX62
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_70 -mattr=+ptx63 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx63 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_70 -mattr=+ptx62 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 && ptxas-isa-6.3 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_70 -mattr=+ptx63 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 && ptxas-isa-6.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_70 -mattr=+ptx63 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 && ptxas-isa-6.2 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_70 -mattr=+ptx62 | %ptxas-verify -arch=sm_70 %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
6 changes: 3 additions & 3 deletions llvm/test/CodeGen/NVPTX/atomics-sm90.ll
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_90 -mattr=+ptx78 | FileCheck %s --check-prefixes=CHECK
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | FileCheck %s --check-prefixes=CHECK64
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_86 -mattr=+ptx71 | FileCheck %s --check-prefixes=CHECKPTX71
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_86 -mattr=+ptx71 | %ptxas-verify -arch=sm_86 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-7.8 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-7.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_86 && ptxas-isa-7.1 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_86 -mattr=+ptx71 | %ptxas-verify -arch=sm_86 %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/atomics-with-scope.ll
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_60 | FileCheck %s -check-prefixes=CHECK,CHECK32
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_60 | FileCheck %s
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas-sm_60 && ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas-sm_60 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify -arch=sm_60 %}

; CHECK-LABEL: .func test_atomics_scope(
define void @test_atomics_scope(ptr %fp, float %f,
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/b52037.ll
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
; https://bugs.llvm.org/show_bug.cgi?id=52037 for the gory details.
;
; RUN: llc -mtriple=nvptx64-nvidia-cuda -mcpu=sm_70 -O3 -o - %s | FileCheck %s
; RUN: %if ptxas %{ llc -mtriple=nvptx64-nvidia-cuda -mcpu=sm_70 -O3 -o - %s | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 %{ llc -mtriple=nvptx64-nvidia-cuda -mcpu=sm_70 -O3 -o - %s | %ptxas-verify -arch=sm_70 %}

; CHECK-LABEL: .visible .entry barney(
; CHECK-NOT: .local{{.*}}__local_depot
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/barrier.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_30 -mattr=+ptx60 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_30 -mattr=+ptx60 | %ptxas-verify %}
; RUN: %if ptxas-isa-6.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_30 -mattr=+ptx60 | %ptxas-verify %}

declare void @llvm.nvvm.bar.warp.sync(i32)
declare void @llvm.nvvm.barrier.cta.sync.aligned.all(i32)
Expand Down
6 changes: 3 additions & 3 deletions llvm/test/CodeGen/NVPTX/bf16-instructions.ll
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | FileCheck --check-prefixes=CHECK,SM80 %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 -denormal-fp-math-f32=preserve-sign | FileCheck --check-prefixes=CHECK,SM80-FTZ %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | FileCheck --check-prefixes=CHECK,SM90 %s
; RUN: %if ptxas-11.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-11.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 -denormal-fp-math-f32=preserve-sign | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-11.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.1 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.1 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 -denormal-fp-math-f32=preserve-sign | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-7.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/bf16x2-instructions-approx.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | FileCheck --check-prefixes=CHECK %s
; RUN: %if ptxas-11.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.1 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | %ptxas-verify -arch=sm_80 %}

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"

Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/bf16x2-instructions.ll
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | FileCheck --check-prefixes=CHECK,SM80 %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | FileCheck --check-prefixes=CHECK,SM90 %s
; RUN: %if ptxas-11.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-11.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_80 && ptxas-isa-7.1 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71 | %ptxas-verify -arch=sm_80 %}
; RUN: %if ptxas-sm_90 && ptxas-isa-7.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx78 | %ptxas-verify -arch=sm_90 %}

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/bmsk.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -o - < %s -mcpu=sm_70 -mattr=+ptx76 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mcpu=sm_70 -mattr=+ptx76 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 && ptxas-isa-7.6 %{ llc < %s -mcpu=sm_70 -mattr=+ptx76 | %ptxas-verify -arch=sm_70 %}

target triple = "nvptx64-unknown-cuda"

Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/bswap.ll
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 -mattr=+ptx70 | FileCheck -check-prefixes CHECK,PTX70 %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas-11.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 -mattr=+ptx70 | %ptxas-verify %}
; RUN: %if ptxas-isa-7.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 -mattr=+ptx70 | %ptxas-verify %}
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 -mattr=+ptx71 | FileCheck -check-prefixes CHECK,PTX71 %s
; RUN: %if ptxas-11.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 -mattr=+ptx71 | %ptxas-verify %}
; RUN: %if ptxas-isa-7.1 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 -mattr=+ptx71 | %ptxas-verify %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/byval-arg-vectorize.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mcpu=sm_70 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mcpu=sm_70 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 %{ llc < %s -mcpu=sm_70 | %ptxas-verify -arch=sm_70 %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/byval-const-global.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mcpu=sm_70 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mcpu=sm_70 | %ptxas-verify -arch=sm_70 %}
; RUN: %if ptxas-sm_70 %{ llc < %s -mcpu=sm_70 | %ptxas-verify -arch=sm_70 %}

target triple = "nvptx64-nvidia-cuda"

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/calling-conv.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_20 | FileCheck %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas-ptr32 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}


Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/cluster-dim.ll
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 | FileCheck -check-prefixes=CHECK80 %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 | FileCheck -check-prefixes=CHECK90 %s
; RUN: %if ptxas-12.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 | %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-sm_90 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 | %ptxas-verify -arch=sm_90 %}

define ptx_kernel void @kernel_func_clusterxyz() "nvvm.cluster_dim"="3,5,7" {
; CHECK80-LABEL: kernel_func_clusterxyz(
Expand Down
12 changes: 6 additions & 6 deletions llvm/test/CodeGen/NVPTX/clusterlaunchcontrol-multicast.ll
Original file line number Diff line number Diff line change
@@ -1,16 +1,16 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -o - -mcpu=sm_100a -march=nvptx64 -mattr=+ptx86 %s | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 | %ptxas-verify -arch=sm_100a %}
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100a %}
; RUN: %if ptxas-sm_100a && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 | %ptxas-verify -arch=sm_100a %}
; RUN: %if ptxas-sm_100a && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100a %}
; RUN: llc -o - -mcpu=sm_101a -march=nvptx64 -mattr=+ptx86 %s | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 | %ptxas-verify -arch=sm_101a %}
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_101a %}
; RUN: %if ptxas-sm_101a && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 | %ptxas-verify -arch=sm_101a %}
; RUN: %if ptxas-sm_101a && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_101a %}
; RUN: llc -o - -mcpu=sm_120a -march=nvptx64 -mattr=+ptx86 %s | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 | %ptxas-verify -arch=sm_120a %}
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_120a %}
; RUN: %if ptxas-sm_120a && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 | %ptxas-verify -arch=sm_120a %}
; RUN: %if ptxas-sm_120a && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_120a %}

define void @nvvm_clusterlaunchcontrol_try_cancel_multicast(
; CHECK-PTX-SHARED64-LABEL: nvvm_clusterlaunchcontrol_try_cancel_multicast(
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/NVPTX/clusterlaunchcontrol.ll
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -march=nvptx64 -mcpu=sm_100 -mattr=+ptx86 | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
; RUN: llc < %s -march=nvptx64 -mcpu=sm_100 -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 | %ptxas-verify -arch=sm_100 %}
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100 %}
; RUN: %if ptxas-sm_100 && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 | %ptxas-verify -arch=sm_100 %}
; RUN: %if ptxas-sm_100 && ptxas-isa-8.6 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100 -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100 %}

define void @nvvm_clusterlaunchcontrol_try_cancel(
; CHECK-PTX-SHARED64-LABEL: nvvm_clusterlaunchcontrol_try_cancel(
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/cmpxchg-sm60.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -march=nvptx64 -mcpu=sm_60 -mattr=+ptx50 | FileCheck %s --check-prefix=SM60
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_60 -mattr=+ptx50 | %ptxas-verify -arch=sm_60 %}
; RUN: %if ptxas-sm_60 && ptxas-isa-5.0 %{ llc < %s -march=nvptx64 -mcpu=sm_60 -mattr=+ptx50 | %ptxas-verify -arch=sm_60 %}

define i8 @monotonic_monotonic_i8_global_cta(ptr addrspace(1) %addr, i8 %cmp, i8 %new) {
; SM60-LABEL: monotonic_monotonic_i8_global_cta(
Expand Down
Loading