1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-21 12:02:58 +02:00
llvm-mirror/test/CodeGen/AMDGPU/si-instr-info-correct-implicit-operands.ll
Matt Arsenault 2dfb6d03c5 AMDGPU: Run SIFoldOperands after PeepholeOptimizer
PeepholeOptimizer cleans up redundant copies, which makes
the operand folding more effective.

shader-db stats:

Totals:
SGPRS: 34200 -> 34336 (0.40 %)
VGPRS: 22118 -> 21655 (-2.09 %)
Code Size: 632144 -> 633460 (0.21 %) bytes
LDS: 11 -> 11 (0.00 %) blocks
Scratch: 10240 -> 11264 (10.00 %) bytes per wave
Max Waves: 8822 -> 8918 (1.09 %)
Wait states: 0 -> 0 (0.00 %)

Totals from affected shaders:
SGPRS: 7704 -> 7840 (1.77 %)
VGPRS: 5169 -> 4706 (-8.96 %)
Code Size: 234444 -> 235760 (0.56 %) bytes
LDS: 2 -> 2 (0.00 %) blocks
Scratch: 0 -> 1024 (0.00 %) bytes per wave
Max Waves: 1188 -> 1284 (8.08 %)
Wait states: 0 -> 0 (0.00 %)

Increases:
SGPRS: 35 (0.01 %)
VGPRS: 1 (0.00 %)
Code Size: 59 (0.02 %)
LDS: 0 (0.00 %)
Scratch: 1 (0.00 %)
Max Waves: 48 (0.02 %)
Wait states: 0 (0.00 %)

Decreases:
SGPRS: 26 (0.01 %)
VGPRS: 54 (0.02 %)
Code Size: 68 (0.03 %)
LDS: 0 (0.00 %)
Scratch: 0 (0.00 %)
Max Waves: 4 (0.00 %)
Wait states: 0 (0.00 %)

llvm-svn: 266378
2016-04-14 21:58:24 +00:00

17 lines
735 B
LLVM

; RUN: llc -o /dev/null %s -march=amdgcn -mcpu=verde -verify-machineinstrs -stop-after expand-isel-pseudos 2>&1 | FileCheck %s
; This test verifies that the instruction selection will add the implicit
; register operands in the correct order when modifying the opcode of an
; instruction to V_ADD_I32_e32.
; CHECK: %{{[0-9]+}} = V_ADD_I32_e32 killed %{{[0-9]+}}, killed %{{[0-9]+}}, implicit-def %vcc, implicit %exec
define void @test(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
entry:
%b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 1
%a = load volatile i32, i32 addrspace(1)* %in
%b = load volatile i32, i32 addrspace(1)* %b_ptr
%result = add i32 %a, %b
store i32 %result, i32 addrspace(1)* %out
ret void
}