maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/SPARC/reserved-regs.ll

138 lines
11 KiB
LLVM
Raw Normal View History

[Sparc] Check register use with isPhysRegUsed() instead of reg_nodbg_empty() Summary: By using reg_nodbg_empty() to determine if a function can be treated as a leaf function or not, we miss the case when the register pair L0_L1 is used but not L0 by itself. This has the effect that use_all_i32_regs(), a test in reserved-regs.ll which tries to use all registers, gets treated as a leaf function. Reviewers: jyknight, venkatra Reviewed By: jyknight Subscribers: davide, RKSimon, sepavloff, llvm-commits Differential Revision: https://reviews.llvm.org/D27089 llvm-svn: 297285
2017-03-08 23:23:10 +08:00
; RUN: llc -march=sparc -verify-machineinstrs < %s | FileCheck %s
[Sparc] Implement i64 load/store support for 32-bit sparc. The LDD/STD instructions can load/store a 64bit quantity from/to memory to/from a consecutive even/odd pair of (32-bit) registers. They are part of SparcV8, and also present in SparcV9. (Although deprecated there, as you can store 64bits in one register). As recommended on llvmdev in the thread "How to enable use of 64bit load/store for 32bit architecture" from Apr 2015, I've modeled the 64-bit load/store operations as working on a v2i32 type, rather than making i64 a legal type, but with few legal operations. The latter does not (currently) work, as there is much code in llvm which assumes that if i64 is legal, operations like "add" will actually work on it. The same assumption does not hold for v2i32 -- for vector types, it is workable to support only load/store, and expand everything else. This patch: - Adds a new register class, IntPair, for even/odd pairs of registers. - Modifies the list of reserved registers, the stack spilling code, and register copying code to support the IntPair register class. - Adds support in AsmParser. (note that in asm text, you write the name of the first register of the pair only. So the parser has to morph the single register into the equivalent paired register). - Adds the new instructions themselves (LDD/STD/LDDA/STDA). - Hooks up the instructions and registers as a vector type v2i32. Adds custom legalizer to transform i64 load/stores into v2i32 load/stores and bitcasts, so that the new instructions can actually be generated, and marks all operations other than load/store on v2i32 as needing to be expanded. - Copies the unfortunate SelectInlineAsm hack from ARMISelDAGToDAG. This hack undoes the transformation of i64 operands into two arbitrarily-allocated separate i32 registers in SelectionDAGBuilder. and instead passes them in a single IntPair. (Arbitrarily allocated registers are not useful, asm code expects to be receiving a pair, which can be passed to ldd/std.) Also adds a bunch of test cases covering all the bugs I've added along the way. Differential Revision: http://reviews.llvm.org/D8713 llvm-svn: 244484
2015-08-11 03:11:39 +08:00
@g = common global [32 x i32] zeroinitializer, align 16
@h = common global [16 x i64] zeroinitializer, align 16
;; Ensures that we don't use registers which are supposed to be reserved.
; CHECK-LABEL: use_all_i32_regs:
[Sparc] Check register use with isPhysRegUsed() instead of reg_nodbg_empty() Summary: By using reg_nodbg_empty() to determine if a function can be treated as a leaf function or not, we miss the case when the register pair L0_L1 is used but not L0 by itself. This has the effect that use_all_i32_regs(), a test in reserved-regs.ll which tries to use all registers, gets treated as a leaf function. Reviewers: jyknight, venkatra Reviewed By: jyknight Subscribers: davide, RKSimon, sepavloff, llvm-commits Differential Revision: https://reviews.llvm.org/D27089 llvm-svn: 297285
2017-03-08 23:23:10 +08:00
; CHECK: save %sp
[Sparc] Implement i64 load/store support for 32-bit sparc. The LDD/STD instructions can load/store a 64bit quantity from/to memory to/from a consecutive even/odd pair of (32-bit) registers. They are part of SparcV8, and also present in SparcV9. (Although deprecated there, as you can store 64bits in one register). As recommended on llvmdev in the thread "How to enable use of 64bit load/store for 32bit architecture" from Apr 2015, I've modeled the 64-bit load/store operations as working on a v2i32 type, rather than making i64 a legal type, but with few legal operations. The latter does not (currently) work, as there is much code in llvm which assumes that if i64 is legal, operations like "add" will actually work on it. The same assumption does not hold for v2i32 -- for vector types, it is workable to support only load/store, and expand everything else. This patch: - Adds a new register class, IntPair, for even/odd pairs of registers. - Modifies the list of reserved registers, the stack spilling code, and register copying code to support the IntPair register class. - Adds support in AsmParser. (note that in asm text, you write the name of the first register of the pair only. So the parser has to morph the single register into the equivalent paired register). - Adds the new instructions themselves (LDD/STD/LDDA/STDA). - Hooks up the instructions and registers as a vector type v2i32. Adds custom legalizer to transform i64 load/stores into v2i32 load/stores and bitcasts, so that the new instructions can actually be generated, and marks all operations other than load/store on v2i32 as needing to be expanded. - Copies the unfortunate SelectInlineAsm hack from ARMISelDAGToDAG. This hack undoes the transformation of i64 operands into two arbitrarily-allocated separate i32 registers in SelectionDAGBuilder. and instead passes them in a single IntPair. (Arbitrarily allocated registers are not useful, asm code expects to be receiving a pair, which can be passed to ldd/std.) Also adds a bunch of test cases covering all the bugs I've added along the way. Differential Revision: http://reviews.llvm.org/D8713 llvm-svn: 244484
2015-08-11 03:11:39 +08:00
; CHECK-NOT: %g0
; CHECK-NOT: %g1
; CHECK-NOT: %g5
; CHECK-NOT: %g6
; CHECK-NOT: %g7
; CHECK-NOT: %o6
; CHECK-NOT: %i6
; CHECK-NOT: %i7
; CHECK: ret
define void @use_all_i32_regs() {
entry:
%0 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 0), align 16
%1 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 1), align 4
%2 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 2), align 8
%3 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 3), align 4
%4 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 4), align 16
%5 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 5), align 4
%6 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 6), align 8
%7 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 7), align 4
%8 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 8), align 16
%9 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 9), align 4
%10 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 10), align 8
%11 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 11), align 4
%12 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 12), align 16
%13 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 13), align 4
%14 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 14), align 8
%15 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 15), align 4
%16 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 16), align 16
%17 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 17), align 4
%18 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 18), align 8
%19 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 19), align 4
%20 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 20), align 16
%21 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 21), align 4
%22 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 22), align 8
%23 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 23), align 4
%24 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 24), align 16
%25 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 25), align 4
%26 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 26), align 8
%27 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 27), align 4
%28 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 28), align 16
%29 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 29), align 4
%30 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 30), align 8
%31 = load volatile i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 31), align 4
store volatile i32 %1, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 0), align 16
store volatile i32 %2, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 1), align 4
store volatile i32 %3, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 2), align 8
store volatile i32 %4, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 3), align 4
store volatile i32 %5, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 4), align 16
store volatile i32 %6, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 5), align 4
store volatile i32 %7, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 6), align 8
store volatile i32 %8, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 7), align 4
store volatile i32 %9, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 8), align 16
store volatile i32 %10, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 9), align 4
store volatile i32 %11, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 10), align 8
store volatile i32 %12, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 11), align 4
store volatile i32 %13, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 12), align 16
store volatile i32 %14, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 13), align 4
store volatile i32 %15, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 14), align 8
store volatile i32 %16, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 15), align 4
store volatile i32 %17, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 16), align 16
store volatile i32 %18, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 17), align 4
store volatile i32 %19, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 18), align 8
store volatile i32 %20, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 19), align 4
store volatile i32 %21, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 20), align 16
store volatile i32 %22, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 21), align 4
store volatile i32 %23, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 22), align 8
store volatile i32 %24, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 23), align 4
store volatile i32 %25, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 24), align 16
store volatile i32 %26, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 25), align 4
store volatile i32 %27, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 26), align 8
store volatile i32 %28, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 27), align 4
store volatile i32 %29, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 28), align 16
store volatile i32 %30, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 29), align 4
store volatile i32 %31, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 30), align 8
store volatile i32 %0, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @g, i64 0, i64 31), align 4
ret void
}
; CHECK-LABEL: use_all_i64_regs:
[Sparc] Check register use with isPhysRegUsed() instead of reg_nodbg_empty() Summary: By using reg_nodbg_empty() to determine if a function can be treated as a leaf function or not, we miss the case when the register pair L0_L1 is used but not L0 by itself. This has the effect that use_all_i32_regs(), a test in reserved-regs.ll which tries to use all registers, gets treated as a leaf function. Reviewers: jyknight, venkatra Reviewed By: jyknight Subscribers: davide, RKSimon, sepavloff, llvm-commits Differential Revision: https://reviews.llvm.org/D27089 llvm-svn: 297285
2017-03-08 23:23:10 +08:00
; CHECK: save %sp
[Sparc] Implement i64 load/store support for 32-bit sparc. The LDD/STD instructions can load/store a 64bit quantity from/to memory to/from a consecutive even/odd pair of (32-bit) registers. They are part of SparcV8, and also present in SparcV9. (Although deprecated there, as you can store 64bits in one register). As recommended on llvmdev in the thread "How to enable use of 64bit load/store for 32bit architecture" from Apr 2015, I've modeled the 64-bit load/store operations as working on a v2i32 type, rather than making i64 a legal type, but with few legal operations. The latter does not (currently) work, as there is much code in llvm which assumes that if i64 is legal, operations like "add" will actually work on it. The same assumption does not hold for v2i32 -- for vector types, it is workable to support only load/store, and expand everything else. This patch: - Adds a new register class, IntPair, for even/odd pairs of registers. - Modifies the list of reserved registers, the stack spilling code, and register copying code to support the IntPair register class. - Adds support in AsmParser. (note that in asm text, you write the name of the first register of the pair only. So the parser has to morph the single register into the equivalent paired register). - Adds the new instructions themselves (LDD/STD/LDDA/STDA). - Hooks up the instructions and registers as a vector type v2i32. Adds custom legalizer to transform i64 load/stores into v2i32 load/stores and bitcasts, so that the new instructions can actually be generated, and marks all operations other than load/store on v2i32 as needing to be expanded. - Copies the unfortunate SelectInlineAsm hack from ARMISelDAGToDAG. This hack undoes the transformation of i64 operands into two arbitrarily-allocated separate i32 registers in SelectionDAGBuilder. and instead passes them in a single IntPair. (Arbitrarily allocated registers are not useful, asm code expects to be receiving a pair, which can be passed to ldd/std.) Also adds a bunch of test cases covering all the bugs I've added along the way. Differential Revision: http://reviews.llvm.org/D8713 llvm-svn: 244484
2015-08-11 03:11:39 +08:00
; CHECK-NOT: %g0
; CHECK-NOT: %g1
; CHECK-NOT: %g4
; CHECK-NOT: %g5
; CHECK-NOT: %g6
; CHECK-NOT: %g7
; CHECK-NOT: %o6
; CHECK-NOT: %o7
; CHECK-NOT: %i6
; CHECK-NOT: %i7
; CHECK: ret
define void @use_all_i64_regs() {
entry:
%0 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 0), align 16
%1 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 1), align 4
%2 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 2), align 8
%3 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 3), align 4
%4 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 4), align 16
%5 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 5), align 4
%6 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 6), align 8
%7 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 7), align 4
%8 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 8), align 16
%9 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 9), align 4
%10 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 10), align 8
%11 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 11), align 4
%12 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 12), align 16
%13 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 13), align 4
%14 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 14), align 8
%15 = load volatile i64, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 15), align 4
store volatile i64 %1, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 0), align 16
store volatile i64 %2, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 1), align 4
store volatile i64 %3, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 2), align 8
store volatile i64 %4, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 3), align 4
store volatile i64 %5, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 4), align 16
store volatile i64 %6, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 5), align 4
store volatile i64 %7, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 6), align 8
store volatile i64 %8, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 7), align 4
store volatile i64 %9, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 8), align 16
store volatile i64 %10, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 9), align 4
store volatile i64 %11, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 10), align 8
store volatile i64 %12, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 11), align 4
store volatile i64 %13, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 12), align 16
store volatile i64 %14, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 13), align 4
store volatile i64 %15, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 14), align 8
store volatile i64 %0, i64* getelementptr inbounds ([16 x i64], [16 x i64]* @h, i64 0, i64 15), align 4
ret void
}