0f1b5f115a
ptxas is a proprietary compiler from Nvidia that can compile PTX to machine code (SASS). It has a lot of diagnostics to catch errors in PTX, which can be used to verify PTX output from llc. Set -DPXTAS_EXECUTABLE=/path/to/ptxas CMake option to enable it. If this option is not set, then ptxas is substituted to true which effectively disables all ptxas RUN lines. LLVM_PTXAS_EXECUTABLE environment variable takes precedence over the CMake option, and allows to override ptxas executable that is used for LIT without complete re-configuration. Differential Revision: https://reviews.llvm.org/D121727
67 lines
2.2 KiB
LLVM
67 lines
2.2 KiB
LLVM
; RUN: llc < %s -march=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | FileCheck %s
|
|
; RUN: %if ptxas-11.0 %{ llc < %s -march=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.umin(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_min_u32
|
|
define i32 @redux_sync_min_u32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.min.u32
|
|
%val = call i32 @llvm.nvvm.redux.sync.umin(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.umax(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_max_u32
|
|
define i32 @redux_sync_max_u32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.max.u32
|
|
%val = call i32 @llvm.nvvm.redux.sync.umax(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.add(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_add_s32
|
|
define i32 @redux_sync_add_s32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.add.s32
|
|
%val = call i32 @llvm.nvvm.redux.sync.add(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.min(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_min_s32
|
|
define i32 @redux_sync_min_s32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.min.s32
|
|
%val = call i32 @llvm.nvvm.redux.sync.min(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.max(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_max_s32
|
|
define i32 @redux_sync_max_s32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.max.s32
|
|
%val = call i32 @llvm.nvvm.redux.sync.max(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.and(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_and_b32
|
|
define i32 @redux_sync_and_b32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.and.b32
|
|
%val = call i32 @llvm.nvvm.redux.sync.and(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.xor(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_xor_b32
|
|
define i32 @redux_sync_xor_b32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.xor.b32
|
|
%val = call i32 @llvm.nvvm.redux.sync.xor(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.or(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_or_b32
|
|
define i32 @redux_sync_or_b32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.or.b32
|
|
%val = call i32 @llvm.nvvm.redux.sync.or(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|