maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[WebAssembly] Restore defaults for stores per memop 

Summary:
Large slowdowns were observed in Rust due to many small, constant
sized copies in conjunction with poorly-optimized memory.copy
implementations. Since memory.copy cannot be expected to be inlined
efficiently by engines at this time, stop using it for the smallest
copies. We continue to lower all memcpy intrinsics to memory.copy,
though.

Reviewers: aheejin, alexcrichton

Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, JDevlieghere, sunfish, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67639

llvm-svn: 372275
This commit is contained in:
Thomas Lively 2019-09-18 23:18:16 +00:00
parent 8535ba6fa0
commit dbcd7f5602
2 changed files with 20 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
View File

@ -259,16 +259,6 @@ WebAssemblyTargetLowering::WebAssemblyTargetLowering(
setMaxAtomicSizeInBitsSupported(64); setMaxAtomicSizeInBitsSupported(64);
if (Subtarget->hasBulkMemory()) {
// Use memory.copy and friends over multiple loads and stores
MaxStoresPerMemcpy = 1;
MaxStoresPerMemcpyOptSize = 1;
MaxStoresPerMemmove = 1;
MaxStoresPerMemmoveOptSize = 1;
MaxStoresPerMemset = 1;
MaxStoresPerMemsetOptSize = 1;
}
// Override the __gnu_f2h_ieee/__gnu_h2f_ieee names so that the f32 name is // Override the __gnu_f2h_ieee/__gnu_h2f_ieee names so that the f32 name is
// consistent with the f64 and f128 names. // consistent with the f64 and f128 names.
setLibcallName(RTLIB::FPEXT_F16_F32, "__extendhfsf2"); setLibcallName(RTLIB::FPEXT_F16_F32, "__extendhfsf2");

40
llvm/test/CodeGen/WebAssembly/bulk-memory.ll
View File

@ -142,8 +142,8 @@ define void @memset_1024(i8* %dest, i8 %val) {
} }
; The following tests check that frame index elimination works for ; The following tests check that frame index elimination works for
; bulk memory instructions. The stack pointer is bumped by 16 instead ; bulk memory instructions. The stack pointer is bumped by 112 instead
; of 10 because the stack pointer in WebAssembly is currently always ; of 100 because the stack pointer in WebAssembly is currently always
; 16-byte aligned, even in leaf functions, although it is not written ; 16-byte aligned, even in leaf functions, although it is not written
; back to the global in this case. ; back to the global in this case.
@ -156,17 +156,17 @@ define void @memset_1024(i8* %dest, i8 %val) {
; NO-BULK-MEM-NOT: memory.copy ; NO-BULK-MEM-NOT: memory.copy
; BULK-MEM-NEXT: .functype memcpy_alloca_src (i32) -> () ; BULK-MEM-NEXT: .functype memcpy_alloca_src (i32) -> ()
; BULK-MEM-NEXT: global.get $push[[L0:[0-9]+]]=, __stack_pointer ; BULK-MEM-NEXT: global.get $push[[L0:[0-9]+]]=, __stack_pointer
; BULK-MEM-NEXT: i32.const $push[[L1:[0-9]+]]=, 16 ; BULK-MEM-NEXT: i32.const $push[[L1:[0-9]+]]=, 112
; BULK-MEM-NEXT: i32.sub $push[[L2:[0-9]+]]=, $pop[[L0]], $pop[[L1]] ; BULK-MEM-NEXT: i32.sub $push[[L2:[0-9]+]]=, $pop[[L0]], $pop[[L1]]
; BULK-MEM-NEXT: i32.const $push[[L3:[0-9]+]]=, 6 ; BULK-MEM-NEXT: i32.const $push[[L3:[0-9]+]]=, 12
; BULK-MEM-NEXT: i32.add $push[[L4:[0-9]+]]=, $pop[[L2]], $pop[[L3]] ; BULK-MEM-NEXT: i32.add $push[[L4:[0-9]+]]=, $pop[[L2]], $pop[[L3]]
; BULK-MEM-NEXT: i32.const $push[[L5:[0-9]+]]=, 10 ; BULK-MEM-NEXT: i32.const $push[[L5:[0-9]+]]=, 100
; BULK-MEM-NEXT: memory.copy 0, 0, $0, $pop[[L4]], $pop[[L5]] ; BULK-MEM-NEXT: memory.copy 0, 0, $0, $pop[[L4]], $pop[[L5]]
; BULK-MEM-NEXT: return ; BULK-MEM-NEXT: return
define void @memcpy_alloca_src(i8* %dst) { define void @memcpy_alloca_src(i8* %dst) {
%a = alloca [10 x i8] %a = alloca [100 x i8]
%p = bitcast [10 x i8]* %a to i8* %p = bitcast [100 x i8]* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %p, i32 10, i1 false) call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %p, i32 100, i1 false)
ret void ret void
} }
@ -174,17 +174,17 @@ define void @memcpy_alloca_src(i8* %dst) {
; NO-BULK-MEM-NOT: memory.copy ; NO-BULK-MEM-NOT: memory.copy
; BULK-MEM-NEXT: .functype memcpy_alloca_dst (i32) -> () ; BULK-MEM-NEXT: .functype memcpy_alloca_dst (i32) -> ()
; BULK-MEM-NEXT: global.get $push[[L0:[0-9]+]]=, __stack_pointer ; BULK-MEM-NEXT: global.get $push[[L0:[0-9]+]]=, __stack_pointer
; BULK-MEM-NEXT: i32.const $push[[L1:[0-9]+]]=, 16 ; BULK-MEM-NEXT: i32.const $push[[L1:[0-9]+]]=, 112
; BULK-MEM-NEXT: i32.sub $push[[L2:[0-9]+]]=, $pop[[L0]], $pop[[L1]] ; BULK-MEM-NEXT: i32.sub $push[[L2:[0-9]+]]=, $pop[[L0]], $pop[[L1]]
; BULK-MEM-NEXT: i32.const $push[[L3:[0-9]+]]=, 6 ; BULK-MEM-NEXT: i32.const $push[[L3:[0-9]+]]=, 12
; BULK-MEM-NEXT: i32.add $push[[L4:[0-9]+]]=, $pop[[L2]], $pop[[L3]] ; BULK-MEM-NEXT: i32.add $push[[L4:[0-9]+]]=, $pop[[L2]], $pop[[L3]]
; BULK-MEM-NEXT: i32.const $push[[L5:[0-9]+]]=, 10 ; BULK-MEM-NEXT: i32.const $push[[L5:[0-9]+]]=, 100
; BULK-MEM-NEXT: memory.copy 0, 0, $pop[[L4]], $0, $pop[[L5]] ; BULK-MEM-NEXT: memory.copy 0, 0, $pop[[L4]], $0, $pop[[L5]]
; BULK-MEM-NEXT: return ; BULK-MEM-NEXT: return
define void @memcpy_alloca_dst(i8* %src) { define void @memcpy_alloca_dst(i8* %src) {
%a = alloca [10 x i8] %a = alloca [100 x i8]
%p = bitcast [10 x i8]* %a to i8* %p = bitcast [100 x i8]* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %p, i8* %src, i32 10, i1 false) call void @llvm.memcpy.p0i8.p0i8.i32(i8* %p, i8* %src, i32 100, i1 false)
ret void ret void
} }
@ -192,16 +192,16 @@ define void @memcpy_alloca_dst(i8* %src) {
; NO-BULK-MEM-NOT: memory.fill ; NO-BULK-MEM-NOT: memory.fill
; BULK-MEM-NEXT: .functype memset_alloca (i32) -> () ; BULK-MEM-NEXT: .functype memset_alloca (i32) -> ()
; BULK-MEM-NEXT: global.get $push[[L0:[0-9]+]]=, __stack_pointer ; BULK-MEM-NEXT: global.get $push[[L0:[0-9]+]]=, __stack_pointer
; BULK-MEM-NEXT: i32.const $push[[L1:[0-9]+]]=, 16 ; BULK-MEM-NEXT: i32.const $push[[L1:[0-9]+]]=, 112
; BULK-MEM-NEXT: i32.sub $push[[L2:[0-9]+]]=, $pop[[L0]], $pop[[L1]] ; BULK-MEM-NEXT: i32.sub $push[[L2:[0-9]+]]=, $pop[[L0]], $pop[[L1]]
; BULK-MEM-NEXT: i32.const $push[[L3:[0-9]+]]=, 6 ; BULK-MEM-NEXT: i32.const $push[[L3:[0-9]+]]=, 12
; BULK-MEM-NEXT: i32.add $push[[L4:[0-9]+]]=, $pop[[L2]], $pop[[L3]] ; BULK-MEM-NEXT: i32.add $push[[L4:[0-9]+]]=, $pop[[L2]], $pop[[L3]]
; BULK-MEM-NEXT: i32.const $push[[L5:[0-9]+]]=, 10 ; BULK-MEM-NEXT: i32.const $push[[L5:[0-9]+]]=, 100
; BULK-MEM-NEXT: memory.fill 0, $pop[[L4]], $0, $pop[[L5]] ; BULK-MEM-NEXT: memory.fill 0, $pop[[L4]], $0, $pop[[L5]]
; BULK-MEM-NEXT: return ; BULK-MEM-NEXT: return
define void @memset_alloca(i8 %val) { define void @memset_alloca(i8 %val) {
%a = alloca [10 x i8] %a = alloca [100 x i8]
%p = bitcast [10 x i8]* %a to i8* %p = bitcast [100 x i8]* %a to i8*
call void @llvm.memset.p0i8.i32(i8* %p, i8 %val, i32 10, i1 false) call void @llvm.memset.p0i8.i32(i8* %p, i8 %val, i32 100, i1 false)
ret void ret void
} }